Compare commits

..
Author SHA1 Message Date
Xubin Ren 7f3de6ea3e fix(providers): use canonical OpenRouter app URL 2026-07-26 15:56:51 +08:00
394 changed files with 9688 additions and 41753 deletions
-8
View File
@@ -24,14 +24,6 @@ Fix bugs by changing only what is necessary. Do not bundle unrelated refactors o
A bugfix should make the protected invariant clear, change the smallest surface that enforces it, and add only the closest regression test. If a diff starts changing ownership boundaries or mixing behavior changes with clean-up, split it before it becomes hard to review.
## Type dynamic boundaries at the edge
Wire payloads, persisted records, and third-party SDK objects are untrusted dynamic boundaries. Prefer a parser or small normalizer at the owning edge, and use `TypedDict` for stable dictionary shapes, so validation happens once and internal code receives a concrete type. Do not spread raw dynamic dictionaries or SDK objects through the core.
Stable first-party dependencies must be typed where they are stored or passed. Do not declare an internal service, context field, or callback result as `Any` and then recover its real type with consumer-side casts. Use the concrete type or a narrow `Protocol`; reserve `Any` for genuinely dynamic boundaries.
`typing.cast` performs no runtime validation. Every new cast must be supported by a runtime check on the same path or by an explicit invariant that is clear from construction and control flow (and documented locally when it is not obvious). If input can violate the claimed type, handle that invalid case before casting; never use `cast` only to silence BasedPyright.
## Explicit over magical
Configuration must be declared explicitly in `config/schema.py` Pydantic models. Error handling should raise clear exceptions rather than silently correcting bad input. Provider auto-detection exists, but every resolution path must be traceable from the factory to the concrete provider class.
+2 -2
View File
@@ -14,9 +14,9 @@ Shell execution (`ExecTool`, `agent/tools/shell.py`) also respects `restrict_to_
## SSRF Protection
All outbound HTTP requests from agent tools must pass through the shared URL guards in `security/network.py` (`validate_url_target` or `resolve_url_target`). By default they block loopback, RFC1918 private addresses, CGNAT ranges, link-local ranges, and cloud metadata endpoints (including `169.254.169.254`).
All outbound HTTP requests from agent tools must pass through `validate_url_target` (`security/network.py`). By default it blocks loopback, RFC1918 private addresses, CGNAT ranges, link-local ranges, and cloud metadata endpoints (including `169.254.169.254`).
For direct requests, the only escape hatch is `configure_ssrf_whitelist(cidrs)`, which reads from `config.tools.ssrf_whitelist` at load time. An explicitly configured `providers.<name>.proxy` is a separate user-authorized trust boundary for provider requests and provider-returned image URL downloads. Those downloads still reject malformed URLs and locally identifiable private/internal targets on every redirect, but hostnames unavailable to local DNS are delegated to the trusted proxy. The user-selected proxy owns final DNS resolution and network egress policy.
The only escape hatch is `configure_ssrf_whitelist(cidrs)`, which reads from `config.tools.ssrf_whitelist` at load time.
HTTP/SSE MCP transports are part of this boundary: validate configured MCP URLs before probing or constructing clients, and validate each outgoing HTTP request before redirects are followed. Local/private HTTP MCP endpoints are allowed only through the explicit SSRF whitelist. Stdio MCP servers are not part of the HTTP SSRF path.
+2 -39
View File
@@ -5,28 +5,10 @@ on:
branches: [main]
paths-ignore:
- docs/**
- .agent/**
- .github/ISSUE_TEMPLATE/**
- AGENTS.md
- CLAUDE.md
- COMMUNICATION.md
- CONTRIBUTING.md
- README.md
- SECURITY.md
- webui/README.md
pull_request:
branches: [main]
paths-ignore:
- docs/**
- .agent/**
- .github/ISSUE_TEMPLATE/**
- AGENTS.md
- CLAUDE.md
- COMMUNICATION.md
- CONTRIBUTING.md
- README.md
- SECURITY.md
- webui/README.md
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
@@ -51,20 +33,13 @@ jobs:
id: paths
shell: bash
env:
EVENT_NAME: ${{ github.event_name }}
BASE_SHA: ${{ github.event_name == 'pull_request' && github.event.pull_request.base.sha || github.event.before }}
HEAD_SHA: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
HEAD_SHA: ${{ github.sha }}
run: |
python_required=true
if [[ "$EVENT_NAME" == "pull_request" ]]; then
diff_range="${BASE_SHA}...${HEAD_SHA}"
else
diff_range="${BASE_SHA}..${HEAD_SHA}"
fi
if git cat-file -e "${BASE_SHA}^{commit}" 2>/dev/null &&
changed_files="$(git diff --name-only --no-renames "$diff_range")" &&
changed_files="$(git diff --name-only --no-renames "$BASE_SHA" "$HEAD_SHA")" &&
[[ -n "$changed_files" ]] &&
! grep -qvE '^(webui/|nanobot/channels/[^/]+/webui/|docs/)' <<< "$changed_files"; then
python_required=false
@@ -86,18 +61,14 @@ jobs:
os: ubuntu-latest
python-version: "3.11"
coverage: false
pytest_args: ""
- name: latest, 3.14 + coverage
os: ubuntu-latest
python-version: "3.14"
coverage: true
pytest_args: ""
- name: Windows, 3.14
os: windows-latest
python-version: "3.14"
coverage: false
# Keep each test file in one worker while using both hosted-runner cores.
pytest_args: "-n 2 --dist loadfile"
steps:
- uses: actions/checkout@v4
@@ -120,19 +91,12 @@ jobs:
- name: Install channel dependencies
run: uv run --no-sync python -m scripts.install_channel_dependencies --all-channels
- name: Verify dependency consistency
run: uv pip check
# Channel requirements live in manifests rather than uv.lock. Avoid a
# later uv run sync pruning the packages installed by the previous step.
- name: Lint with ruff
if: matrix.coverage
run: uv run --no-sync ruff check nanobot tests conftest.py
- name: Type check with BasedPyright (strict)
if: matrix.coverage
run: uv run --no-sync basedpyright
- name: Run tests with coverage
if: matrix.coverage
run: >-
@@ -144,7 +108,6 @@ jobs:
if: ${{ !matrix.coverage }}
run: >-
uv run --no-sync python -m pytest
${{ matrix.pytest_args }}
--durations=25 --durations-min=1.0
webui:
-5
View File
@@ -11,11 +11,6 @@ nanobot is a lightweight, open-source AI agent framework written in Python with
pytest tests/test_openai_api.py::test_function -v
ruff check nanobot/
# Strict type checking (matches CI)
uv sync --all-extras --dev
uv run --no-sync python -m scripts.install_channel_dependencies --all-channels
uv run --no-sync basedpyright
# WebUI: dev server (proxies API/WS to gateway :8765), build, test
# Build outputs to ../nanobot/web/dist (bundled into the Python wheel)
cd webui && bun run dev # or NANOBOT_API_URL=... bun run dev
-14
View File
@@ -78,20 +78,6 @@ ruff check nanobot/
ruff format <files-you-changed>
```
### Strict Type Checking
Strict type checking covers optional providers and channels. Reproduce the CI environment
with the same dependency sources and commands:
```bash
uv sync --all-extras --dev
uv run --no-sync python -m scripts.install_channel_dependencies --all-channels
uv run --no-sync basedpyright
```
Keep `--no-sync` on the final commands: channel dependencies come from their package
manifests and are installed explicitly by the setup step.
## Contribution License
By submitting a contribution, you confirm that you have the right to submit it
+79 -66
View File
@@ -17,24 +17,24 @@
<a href="https://nanobot.wiki/vi/docs/latest/getting-started/nanobot-overview">Tiếng Việt</a>
</p>
<p>
<a href="https://github.com/HKUDS/nanobot"><img src="https://img.shields.io/github/stars/HKUDS/nanobot?style=flat&logo=github" alt="GitHub stars"></a>
<a href="https://pypi.org/project/nanobot-ai/"><img src="https://img.shields.io/pypi/v/nanobot-ai" alt="PyPI version"></a>
<a href="https://pepy.tech/project/nanobot-ai"><img src="https://static.pepy.tech/badge/nanobot-ai" alt="PyPI downloads"></a>
<a href="https://github.com/HKUDS/nanobot/actions/workflows/ci.yml"><img src="https://github.com/HKUDS/nanobot/actions/workflows/ci.yml/badge.svg?branch=main" alt="Test Suite"></a>
<a href="https://pypi.org/project/nanobot-ai/"><img src="https://img.shields.io/badge/python-%3E%3D3.11-blue" alt="Python 3.11 or newer"></a>
<a href="./LICENSE"><img src="https://img.shields.io/github/license/HKUDS/nanobot" alt="MIT License"></a>
<a href="https://nanobot.wiki/docs/latest/getting-started/nanobot-overview"><img src="https://img.shields.io/badge/docs-nanobot.wiki-blue" alt="nanobot documentation"></a>
</p>
<p>
<a href="https://discord.gg/MnCvHqpUGB">Discord</a> ·
<a href="https://x.com/nanobot_project">X</a> ·
<a href="./COMMUNICATION.md">WeChat / Feishu</a>
<a href="https://pypi.org/project/nanobot-ai/"><img src="https://img.shields.io/pypi/v/nanobot-ai" alt="PyPI"></a>
<a href="https://pepy.tech/project/nanobot-ai"><img src="https://static.pepy.tech/badge/nanobot-ai" alt="Downloads"></a>
<img src="https://img.shields.io/badge/python-≥3.11-blue" alt="Python">
<img src="https://img.shields.io/badge/license-MIT-green" alt="License">
<a href="https://github.com/HKUDS/nanobot/graphs/commit-activity" target="_blank">
<img alt="Commits last month" src="https://img.shields.io/github/commit-activity/m/HKUDS/nanobot?labelColor=%20%2332b583&color=%20%2312b76a"></a>
<a href="https://github.com/HKUDS/nanobot/issues?q=is%3Aissue%20is%3Aclosed" target="_blank">
<img alt="Issues closed" src="https://img.shields.io/github/issues-search?query=repo%3AHKUDS%2Fnanobot%20is%3Aissue%20is%3Aclosed&label=issues%20closed&labelColor=%20%237d89b0&color=%20%235d6b98"></a>
<a href="https://twitter.com/intent/follow?screen_name=nanobot_project" target="_blank">
<img src="https://img.shields.io/twitter/follow/nanobot_project?logo=X&color=%20%23f5f5f5" alt="follow on X(Twitter)"></a>
<a href="https://nanobot.wiki/docs/latest/getting-started/nanobot-overview"><img src="https://img.shields.io/badge/Docs-nanobot.wiki-blue?style=flat&logo=readthedocs&logoColor=white" alt="Docs"></a>
<a href="./COMMUNICATION.md"><img src="https://img.shields.io/badge/Feishu-Group-E9DBFC?style=flat&logo=feishu&logoColor=white" alt="Feishu"></a>
<a href="./COMMUNICATION.md"><img src="https://img.shields.io/badge/WeChat-Group-C5EAB4?style=flat&logo=wechat&logoColor=white" alt="WeChat"></a>
<a href="https://discord.gg/MnCvHqpUGB"><img src="https://img.shields.io/badge/Discord-Community-5865F2?style=flat&logo=discord&logoColor=white" alt="Discord"></a>
</p>
</div>
# nanobot
🐈 **nanobot** is an ultra-lightweight, open-source, self-hosted personal AI agent framework written in Python. It runs in a WebUI, terminal, or chat apps and combines tools, long-term memory, MCP integrations, model routing, multi-agent delegation, scheduled automation, and an OpenAI-compatible API in a small, readable core.
🐈 **nanobot** is an open-source, ultra-lightweight personal AI agent you can truly own. It keeps the agent core small and readable while giving you the practical pieces for real long-running work: WebUI, chat channels, tools, memory, MCP, model routing, automation, and deployment.
## Start Here
@@ -46,7 +46,7 @@
| Connect Telegram, Discord, WeChat, Slack, Email, Mattermost, or another chat app | [Chat Apps](./docs/chat-apps.md) |
| Configure providers, fallback models, Langfuse, MCP, web tools, or security | [Docs](./docs/README.md) and [Configuration](./docs/configuration.md) |
| Understand or extend the internals | [Architecture](./docs/architecture.md) and [Development](./docs/development.md) |
| Deploy to the cloud or keep nanobot running as a service | [Deployment](./docs/deployment.md) |
| Deploy to the cloud or keep nanobot running as a service | [Deployment](./docs/deployment.md), including [one-click Render setup](./docs/deployment.md#render) |
## What can nanobot do?
@@ -60,6 +60,36 @@ nanobot is a self-hosted personal AI agent runtime. It can:
- expose a Python SDK and OpenAI-compatible API for integrations
- deploy as a long-running local or server-side agent gateway
## Releases
**Latest release: [v0.3.0 - The Agency Release](https://github.com/HKUDS/nanobot/releases/tag/v0.3.0)**
The Agency Release turns nanobot from a durable workbench into an agent runtime that can coordinate helpers, switch models per session, and carry authorized work through to completion.
- Consult inline subagents without leaving the current task
- Switch model presets per session directly from the composer
- Start from a guided WebUI setup with clearer execution controls
- Apply configuration changes live across a more reliable provider, channel, and tool runtime
[Read the v0.3.0 release notes](https://github.com/HKUDS/nanobot/releases/tag/v0.3.0)
## Open Source Partners
<p align="center">
<a href="https://platform.kimi.com?aff=nanobot"><picture><source media="(prefers-color-scheme: dark)" srcset="https://kimi-file.moonshot.cn/prod-chat-kimi/kfs/4/1/2026-06-05/1d8h69mt3v89kkekg24gg"><img alt="Kimi Open Source Friends" height="44" src="https://kimi-file.moonshot.cn/prod-chat-kimi/kfs/4/1/2026-06-05/1d8h69fudcmosb3pipls0"></picture></a>
<a href="https://platform.minimaxi.com/subscribe/token-plan?code=GILTJpMTqZ&source=link"><img alt="MiniMax" height="40" src="https://mintcdn.com/minimax-zh/1UjvBcdoC6r0UeyA/logo/light.svg?fit=max&auto=format&n=1UjvBcdoC6r0UeyA&q=85&s=672d724b639b2d88d0702fae329ea4f8"></a>
</p>
## Recent Updates
- **2026-07-24** Guided first-run setup, inline subagents, and model switching from the composer.
- **2026-07-23** Grok OAuth with hosted X Search, live image settings, and clearer fallback models.
- **2026-07-22** Parallel Search, live configuration reloads, richer app discovery, and a smoother mobile WebUI.
- **2026-07-21** Codex fast mode, visible skill references, safer configuration saves, and sturdier task cleanup.
- **2026-07-20** Cleaner code blocks and copy actions, self-contained channels, and steadier QQ reconnects.
For older updates, see the [release archive](./docs/release-archive.md) or [GitHub releases](https://github.com/HKUDS/nanobot/releases).
## 💡 Why nanobot
- **Persistent workflows**: goals, memory, tools, and chat context survive long-running work.
@@ -214,8 +244,6 @@ The one-shot form is useful for a quick provider check, shell scripts, and local
Need manual JSON, another device on your LAN, or help with provider/model matching? Continue with [Install and Quick Start](./docs/quick-start.md), [WebUI](./docs/webui.md), or [Troubleshooting](./docs/troubleshooting.md).
If nanobot worked for you, a star on GitHub is the simplest way to support the project.
- Want a pasteable provider setup? See [Provider Cookbook](./docs/provider-cookbook.md)
- Want to understand provider/model matching? See [Providers and Models](./docs/providers.md)
- Want web search, MCP, security settings, or more config options? See [Configuration](./docs/configuration.md)
@@ -223,22 +251,6 @@ If nanobot worked for you, a star on GitHub is the simplest way to support the p
- Want to run nanobot in chat apps like Telegram, Discord, WeChat or Feishu? See [Chat Apps](./docs/chat-apps.md)
- Want Docker or Linux service deployment? See [Deployment](./docs/deployment.md)
<a id="deploy-to-render"></a>
## ☁️ Deploy
**Render — one click**
Deploy nanobot's gateway and bundled WebUI from the repository's ready-to-use Blueprint:
[![Deploy to Render](https://render.com/images/deploy-to-render-button.svg)](https://render.com/deploy?repo=https://github.com/HKUDS/nanobot)
Render will ask for `ANTHROPIC_API_KEY` and a private `NANOBOT_WEB_TOKEN`, then provision persistent storage for sessions, memory, and WebUI history. Persistent disks require a paid Render service.
**Self-host**
Prefer your own infrastructure? Follow the [deployment guide](./docs/deployment.md) for Docker, Docker Compose, Linux services, and macOS LaunchAgent setup.
## 🌐 WebUI
The WebUI ships **inside the published wheel** with no separate frontend build. It is the browser workbench for persistent topics, visible agent activity, workspace controls, Apps, Skills, Automations, and settings.
@@ -264,6 +276,29 @@ See the [WebUI guide](./docs/webui.md) for LAN access, background operation, wor
🐈 nanobot stays lightweight by centering everything around a small agent loop: messages come in from chat apps, the LLM decides when tools are needed, and memory or skills are pulled in only as context instead of becoming a heavy orchestration layer. That keeps the core path readable and easy to extend, while still letting you add channels, tools, memory, and deployment options without turning the system into a monolith.
## ✨ Features
<table align="center">
<tr align="center">
<th><p align="center">📈 24/7 Real-Time Market Analysis</p></th>
<th><p align="center">🚀 Full-Stack Software Engineer</p></th>
<th><p align="center">📅 Smart Daily Routine Manager</p></th>
<th><p align="center">📚 Personal Knowledge Assistant</p></th>
</tr>
<tr>
<td align="center"><p align="center"><img src="case/search.gif" width="180" height="400"></p></td>
<td align="center"><p align="center"><img src="case/code.gif" width="180" height="400"></p></td>
<td align="center"><p align="center"><img src="case/schedule.gif" width="180" height="400"></p></td>
<td align="center"><p align="center"><img src="case/memory.gif" width="180" height="400"></p></td>
</tr>
<tr>
<td align="center">Discovery • Insights • Trends</td>
<td align="center">Develop • Deploy • Scale</td>
<td align="center">Schedule • Automate • Organize</td>
<td align="center">Learn • Memory • Reasoning</td>
</tr>
</table>
## 📚 Docs
Browse the [repo docs](./docs/README.md) for the latest features and GitHub development version, or visit [nanobot.wiki](https://nanobot.wiki/docs/latest/getting-started/nanobot-overview) for the stable release documentation.
@@ -282,43 +317,21 @@ Browse the [repo docs](./docs/README.md) for the latest features and GitHub deve
- Integrate nanobot with local tools and automations: [OpenAI-Compatible API](./docs/openai-api.md) · [Python SDK](./docs/python-sdk.md)
- Run nanobot with Docker or as a Linux service: [Deployment](./docs/deployment.md)
## Releases
## 🤝 Contribute & Roadmap
**Latest release: [v0.3.0 - The Agency Release](https://github.com/HKUDS/nanobot/releases/tag/v0.3.0)**
PRs welcome! The codebase is intentionally small and readable. 🤗
The Agency Release turns nanobot from a durable workbench into an agent runtime that can coordinate helpers, switch models per session, and carry authorized work through to completion.
### Contribution Flow
- Consult inline subagents without leaving the current task
- Switch model presets per session directly from the composer
- Start from a guided WebUI setup with clearer execution controls
- Apply configuration changes live across a more reliable provider, channel, and tool runtime
See [CONTRIBUTING.md](./CONTRIBUTING.md) for setup, review, and contribution guidelines.
[Read the v0.3.0 release notes](https://github.com/HKUDS/nanobot/releases/tag/v0.3.0)
**Roadmap** — Pick an item and [open a PR](https://github.com/HKUDS/nanobot/pulls)!
## Recent Updates
- **2026-07-24** Guided first-run setup, inline subagents, and model switching from the composer.
- **2026-07-23** Grok OAuth with hosted X Search, live image settings, and clearer fallback models.
- **2026-07-22** Parallel Search, live configuration reloads, richer app discovery, and a smoother mobile WebUI.
- **2026-07-21** Codex fast mode, visible skill references, safer configuration saves, and sturdier task cleanup.
- **2026-07-20** Cleaner code blocks and copy actions, self-contained channels, and steadier QQ reconnects.
For older updates, see the [release archive](./docs/release-archive.md) or [GitHub releases](https://github.com/HKUDS/nanobot/releases).
## Open Source Partners
<p align="center">
<a href="https://platform.kimi.com?aff=nanobot"><picture><source media="(prefers-color-scheme: dark)" srcset="https://kimi-file.moonshot.cn/prod-chat-kimi/kfs/4/1/2026-06-05/1d8h69mt3v89kkekg24gg"><img alt="Kimi Open Source Friends" height="44" src="https://kimi-file.moonshot.cn/prod-chat-kimi/kfs/4/1/2026-06-05/1d8h69fudcmosb3pipls0"></picture></a>
<a href="https://platform.minimaxi.com/subscribe/token-plan?code=GILTJpMTqZ&source=link"><img alt="MiniMax" height="40" src="https://mintcdn.com/minimax-zh/1UjvBcdoC6r0UeyA/logo/light.svg?fit=max&auto=format&n=1UjvBcdoC6r0UeyA&q=85&s=672d724b639b2d88d0702fae329ea4f8"></a>
</p>
## 🤝 Contribute
Use nanobot for a real task, report what broke, and then pick a focused improvement.
- Read [CONTRIBUTING.md](./CONTRIBUTING.md) for the development workflow.
- Browse [open issues](https://github.com/HKUDS/nanobot/issues) for problems to investigate.
- Open a [pull request](https://github.com/HKUDS/nanobot/pulls) for a focused fix or integration.
- **Multi-modal** — See and hear (images, voice, video)
- **Long-term memory** — Never forget important context
- **Better reasoning** — Multi-step planning and reflection
- **More integrations** — Calendar and more
- **Self-improvement** — Learn from feedback and mistakes
## Contact
BIN
View File
Binary file not shown.

After

Width:  |  Height:  |  Size: 12 MiB

BIN
View File
Binary file not shown.

After

Width:  |  Height:  |  Size: 5.6 MiB

BIN
View File
Binary file not shown.

After

Width:  |  Height:  |  Size: 6.8 MiB

BIN
View File
Binary file not shown.

After

Width:  |  Height:  |  Size: 6.0 MiB

-11
View File
@@ -9,17 +9,6 @@ from collections.abc import Iterator
import certifi
import pytest
from loguru import logger
@pytest.fixture(autouse=True)
def _isolate_nanobot_log_activation() -> Iterator[None]:
"""Keep CLI log settings from leaking into later tests in the same process."""
logger.enable("nanobot")
try:
yield
finally:
logger.enable("nanobot")
@pytest.fixture(scope="session", autouse=True)
+2 -2
View File
@@ -618,7 +618,7 @@ async def send(self, msg: OutboundMessage) -> None:
await self._send_message(msg.chat_id, msg.content, media=msg.media)
```
Tool hints are on by default. Users can disable them globally or per channel:
Tool hints are off by default for most channels. Users can enable them globally or per channel:
```json
{
@@ -626,7 +626,7 @@ Tool hints are on by default. Users can disable them globally or per channel:
"sendToolHints": true,
"webhook": {
"enabled": true,
"sendToolHints": false
"sendToolHints": true
}
}
}
+1 -13
View File
@@ -11,7 +11,7 @@ Use this page when you know what you want to run and need the command shape. For
| Refresh config non-interactively | `nanobot onboard --refresh` | Preserves existing values and adds missing default fields without prompting |
| Use guided setup | `nanobot onboard --wizard` | Best when you prefer prompts over hand-editing JSON |
| Open the browser workbench | `nanobot webui` | Prepares local WebUI settings, starts the gateway, and opens the browser |
| Check readiness without calling a model | `nanobot status` | Summarizes config/workspace and validates the active provider/model configuration |
| Check config without calling a model | `nanobot status` | Summarizes the selected config, workspace, active model, and providers |
| Send one test message | `nanobot agent -m "Hello!"` | First proof that install, config, provider, model, and workspace all work |
| Chat in the terminal | `nanobot agent` | Interactive local chat; exit with `exit`, `/exit`, `:q`, or `Ctrl+D` |
| Run the gateway directly | `nanobot gateway` | Service/ops command for WebUI, chat apps, cron, and heartbeat |
@@ -70,18 +70,6 @@ Default paths:
| Config | `~/.nanobot/config.json` |
| Workspace | `~/.nanobot/workspace/` |
## Status
| Command | Description |
|---|---|
| `nanobot status` | Summarize the default config/workspace and check Agent provider/model readiness |
| `nanobot status --config <path>` | Check a specific config file |
| `nanobot status --workspace <path>` | Show status with a workspace override |
Status does not send a model request. On success, run the printed
`nanobot agent -m "Hello!"` command to verify network access and credentials. On failure,
follow the printed WebUI **Settings → Models** or `nanobot onboard --wizard` route.
## Agent CLI
| Command | Description |
+9 -35
View File
@@ -90,9 +90,7 @@ Instead of storing secrets directly in `config.json`, you can use `${VAR_NAME}`
Any string value in `config.json` can use `${VAR_NAME}`. Resolution runs once at startup, in memory only — resolved values are never written back to disk, so editing config through `nanobot onboard` or the WebUI preserves the placeholder.
If a referenced variable is unset, nanobot fails fast and reports the exact config field
and variable name without echoing the field value. Run `nanobot status` with the same
`--config` path to inspect the problem.
If a referenced variable is unset, nanobot fails fast at startup with `ValueError: Environment variable 'NAME' referenced in config is not set`.
### More examples
@@ -268,7 +266,6 @@ Tracing covers the providers that go through nanobot's OpenAI-compatible client
|----------|---------|-------------|
| `custom` | Any OpenAI-compatible endpoint | — |
| `openrouter` | LLM gateway for hosted model families + Voice transcription (STT models) | [openrouter.ai](https://openrouter.ai) |
| `edenai` | LLM gateway for Eden AI's OpenAI-compatible model catalog | [app.edenai.run](https://app.edenai.run/) |
| `opencode` | LLM gateway (OpenCode Zen coding-agent models) | [opencode.ai/docs/zen](https://opencode.ai/docs/zen/) |
| `opencode_zen` | LLM gateway (legacy alias for OpenCode Zen) | [opencode.ai/docs/zen](https://opencode.ai/docs/zen/) |
| `opencode_go` | LLM gateway (OpenCode Go low-cost coding models) | [opencode.ai/docs/go](https://opencode.ai/docs/go/) |
@@ -349,19 +346,6 @@ Valid `apiType` values are exactly `auto`, `chat_completions`, and `responses`.
</details>
<a id="responses-state-and-compaction"></a>
### Responses conversation state and compaction
Providers that use the Responses API can keep reasoning context across a
conversation, which helps with multi-step tasks. Supported providers can also
compact long conversations automatically.
nanobot preserves Responses conversation state automatically for OpenAI Responses, OpenAI Codex, Azure OpenAI, DeepSeek V4 Flash, and compatible GitHub Copilot models.
Native compaction is also automatic when the provider supports it. The
threshold is derived from the active model's context window and reserved output
headroom; no provider configuration is required.
<details>
<summary><b>Azure OpenAI</b></summary>
@@ -1571,7 +1555,8 @@ Global settings that apply to all channels. Configure under the `channels` secti
{
"channels": {
"sendProgress": true,
"sendToolHints": true,
"sendToolHints": false,
"extractDocumentText": true,
"sendMaxRetries": 3,
"telegram": {
"enabled": false
@@ -1583,17 +1568,11 @@ Global settings that apply to all channels. Configure under the `channels` secti
| Setting | Default | Description |
|---------|---------|-------------|
| `sendProgress` | `true` | Stream agent's text progress to the channel |
| `sendToolHints` | `true` | Stream tool-call hints (e.g. `read_file("…")`) |
| `sendToolHints` | `false` | Stream tool-call hints (e.g. `read_file("…")`) |
| `showReasoning` | `true` | Allow channels to surface model reasoning/thinking content (DeepSeek-R1 `reasoning_content`, Anthropic `thinking_blocks`, inline `<think>` tags). Reasoning flows as a dedicated stream with `_reasoning_delta` / `_reasoning_end` markers — channels override `send_reasoning_delta` / `send_reasoning_end` to render in-place updates. Even with `true`, channels without those overrides stay no-op silently. Currently surfaced on CLI and WebSocket/WebUI (italic shimmer header, auto-collapses after the stream ends); Telegram / Slack / Discord / Feishu / WeChat / Matrix / Mattermost keep the base no-op until their bubble UI is adapted. Independent of `sendProgress`. |
| `extractDocumentText` | `true` | Extract supported document/text attachments into the model prompt. PDF, DOCX, XLSX, and PPTX readers are included in the standard installation. Set to `false` to keep document content out of the prompt and include attachment path references instead. |
| `sendMaxRetries` | `3` | Max delivery attempts per outbound message, including the initial send (0-10 configured, minimum 1 actual attempt) |
Non-image attachments are included in the user message as local path references, without
injecting their contents into the model prompt. When file tools are enabled, the agent
can inspect supported text, PDF, DOCX, XLSX, and PPTX files on demand with `read_file`,
or pass the original path to another tool when exact file bytes are required. The deprecated
`channels.extractDocumentText` setting is accepted for compatibility but ignored.
Normal tool workspace and media access rules still apply to attachment paths.
`channels.transcriptionProvider` and `channels.transcriptionLanguage` are deprecated compatibility fields. They remain as a read-only fallback for older configs, but new configuration should use top-level `transcription.provider` and `transcription.language`.
`sendProgress` and `sendToolHints` can also be overridden per channel. The global values stay as defaults for channels that do not set their own value:
@@ -1602,11 +1581,10 @@ Normal tool workspace and media access rules still apply to attachment paths.
{
"channels": {
"sendProgress": true,
"sendToolHints": true,
"sendToolHints": false,
"telegram": {
"enabled": true,
"sendProgress": false,
"sendToolHints": false
"sendProgress": false
},
"websocket": {
"enabled": true,
@@ -2016,8 +1994,6 @@ For API keys, tokens, and other secrets, see [Environment Variables for Secrets]
| `tools.exec.timeout` | `60` | Default hard timeout in seconds for shell commands. Config values may exceed the per-call tool cap; set `0` to disable the hard timeout for trusted long-running commands. |
| `tools.exec.pathPrepend` | `""` | Extra directories to prepend to `PATH` when running shell commands. Use this when configured tools should win executable lookup precedence, such as a Python virtual environment's `bin` or `Scripts` directory. |
| `tools.exec.pathAppend` | `""` | Extra directories to append to `PATH` when running shell commands (e.g. `/usr/sbin` for `ufw`). |
| `tools.exec.sandboxRoBinds` | `[]` | Extra absolute paths to read-only bind into the `"bwrap"` sandbox with `--ro-bind-try`, such as `/home/user/.local/bin` or `/home/user/.cargo/bin` when those paths are also in `pathPrepend`/`pathAppend`. These roots are also accepted by the shell absolute-path guard only while bwrap is active. Bind only directories whose contents are safe for agent commands to read; paths equal to or containing the active workspace are ignored so they cannot uncover its masked parent directory. |
| `tools.exec.sandboxRwBinds` | `[]` | Extra absolute paths to read-write bind into the `"bwrap"` sandbox with `--bind-try`, for trusted tool caches or scratch directories. Use sparingly: paths listed here are intentionally writable by shell commands inside the sandbox. Paths equal to or containing the active workspace are ignored. |
| `tools.webuiAllowRemotePackageInstall` | `false` | When `false`, the WebUI can install missing optional packages only from a browser opened on the same machine as nanobot. Set to `true` only when a trusted remote admin is allowed to install Python packages into this nanobot environment. |
| `tools.ssrfWhitelist` | `[]` | CIDR ranges exempted from the shared SSRF guard used by web fetches and HTTP/SSE MCP connections. Prefer exact host CIDRs such as `192.168.1.50/32`; broad ranges increase SSRF exposure. |
| `channels.*.allowFrom` | omitted | Access control per channel. Omit to use pairing-only mode; set `["*"]` to allow everyone; or list specific user IDs. See [Pairing](#pairing) for details. |
@@ -2179,8 +2155,7 @@ When a user is idle for longer than a configured threshold, nanobot **proactivel
{
"agents": {
"defaults": {
"idleCompactAfterMinutes": 15,
"idleCompactCheckIntervalSeconds": 60
"idleCompactAfterMinutes": 15
}
}
}
@@ -2189,12 +2164,11 @@ When a user is idle for longer than a configured threshold, nanobot **proactivel
| Option | Default | Description |
|--------|---------|-------------|
| `agents.defaults.idleCompactAfterMinutes` | `15` | Minutes of idle time before auto-compaction starts. Set to `0` to disable. The default is close to a typical LLM KV cache expiry window, so stale sessions get compacted before the user returns. |
| `agents.defaults.idleCompactCheckIntervalSeconds` | `60` | Minimum number of seconds between scans for idle sessions. Set to `0` to scan on every idle tick (~1 s). |
`sessionTtlMinutes` remains accepted as a legacy alias for backward compatibility, but `idleCompactAfterMinutes` is the preferred config key going forward.
How it works:
1. **Idle detection**: On each idle tick (~1 s), checks whether an idle-session scan is due. By default, the full scan runs at most once per minute.
1. **Idle detection**: On each idle tick (~1 s), checks all sessions for expiration.
2. **Background compaction**: Idle sessions summarize the older live prefix via LLM and keep the most recent legal suffix (currently 8 messages).
3. **Summary injection**: When the user returns, the summary is injected as runtime context (one-shot, not persisted) alongside the retained recent suffix.
4. **Restart-safe resume**: The summary is also mirrored into session metadata so it can still be recovered after a process restart.
-17
View File
@@ -39,23 +39,6 @@ Run nanobot online without managing a server. The blueprint deploys the gateway
[Review the deployment blueprint](../render.yaml)
### First Deployment
1. Click **Deploy to Render**, sign in, and review the Blueprint. It creates one Starter web service and a 1 GB persistent disk.
2. Enter your `ANTHROPIC_API_KEY`. Set `NANOBOT_WEB_TOKEN` to a new random value and save it in your password manager; this is the password for the public WebUI.
3. Create the Blueprint and wait for the service status to become **Live**. The first build can take several minutes.
4. Open the generated `onrender.com` URL. The **Authentication required** page means the gateway is running: enter the same `NANOBOT_WEB_TOKEN` value to open the WebUI.
The model API key is used by nanobot to call Anthropic. The Web token only protects access to this deployment; do not share it in issues, screenshots, or chat.
### Updates and Data
The Blueprint disables automatic deploys so upstream repository changes do not unexpectedly restart your agent. To update, open the service in the Render Dashboard and choose **Manual Deploy → Deploy latest commit**.
The persistent disk keeps `config.json`, sessions, memory, WebUI history, cron state, media, and logs across restarts and updates. The deployment initializes `config.json` only when it does not already exist, so settings changed later in the WebUI are not replaced on every boot.
If deployment fails, open the service **Logs** page first. A missing model key fails provider requests after startup, while an incorrect Web token leaves you on the authentication page.
## Docker
> [!TIP]
-3
View File
@@ -70,9 +70,6 @@ Provider settings reuse normal provider config fields:
| `providers.<name>.apiBase` | Optional custom base URL |
| `providers.<name>.extraHeaders` | Headers merged into provider requests |
| `providers.<name>.extraBody` | Extra JSON fields merged into provider request bodies |
| `providers.<name>.proxy` | Explicit trusted HTTP proxy for provider requests and returned image URL downloads |
For providers that return image URLs, direct downloads use DNS pinning. When an explicit provider `proxy` is configured, nanobot rejects malformed URLs and locally identifiable private/internal targets on the initial URL and every redirect. Hostnames unavailable to local DNS are delegated to that trusted proxy, which owns final DNS resolution and network egress. Process-wide proxy environment variables are not used for these downloads.
Both camelCase and snake_case config keys are accepted, but docs use camelCase to match `config.json`.
+8 -3
View File
@@ -186,7 +186,9 @@ Dream is configured under `agents.defaults.dream`:
"defaults": {
"dream": {
"intervalH": 2,
"modelOverride": null
"modelOverride": null,
"maxBatchSize": 20,
"maxIterations": 10
}
}
}
@@ -197,13 +199,16 @@ Dream is configured under `agents.defaults.dream`:
|-------|---------|
| `intervalH` | How often Dream runs, in hours |
| `cron` | Cron expression override (takes precedence over `intervalH`) |
| `modelOverride` | Optional model preset name used for Dream |
| `modelOverride` | Optional Dream-specific model override *(pending implementation)* |
| `maxBatchSize` | *(Deprecated — not used)* |
| `maxIterations` | *(Deprecated — not used)* |
In practical terms:
- `intervalH` is the normal way to configure Dream frequency. Internally it runs as an `every` schedule.
- `cron` overrides `intervalH` when set, allowing precise cron expressions (e.g. `0 */4 * * *`).
- `modelOverride` selects a named entry from `model_presets` for Dream. It accepts preset names only; raw model identifiers are not supported. If omitted, Dream uses the main agent's selected runtime.
- `modelOverride` is reserved for a future release. Currently Dream uses the same model as the main agent.
- `maxBatchSize` and `maxIterations` are preserved for config compatibility but no longer affect behavior.
## In Practice
+2 -84
View File
@@ -100,39 +100,6 @@ Gateway-style setup for model IDs served through OpenRouter.
Use the model ID exactly as OpenRouter lists it.
### Eden AI Gateway
Eden AI exposes an OpenAI-compatible chat-completions endpoint at
`https://api.edenai.run/v3`. Configure the built-in `edenai` provider and use
the full `provider/model` identifier listed by Eden AI:
```json
{
"providers": {
"edenai": {
"apiKey": "${EDENAI_API_KEY}"
}
},
"modelPresets": {
"primary": {
"provider": "edenai",
"model": "anthropic/claude-sonnet-4-5",
"maxTokens": 8192
}
},
"agents": {
"defaults": {
"modelPreset": "primary"
}
}
}
```
Nanobot sends the model ID unchanged, including its provider prefix. Use
Eden AI's [model listing](https://www.edenai.co/docs/v3/llms/listing-models)
to choose a currently available model. The WebUI can also load that catalog
after the Eden AI API key is saved under **Settings → Models**.
### OpenCode Zen and Go
OpenCode Zen and OpenCode Go are OpenCode-managed gateways for coding-agent models.
@@ -262,9 +229,7 @@ Arbitrary custom provider names are OpenAI-compatible only; they do not use the
}
```
`providers.openai.apiType` may be set when you need to force a specific OpenAI API surface. Other providers reject `apiType`; leave it unset outside `providers.openai`. Replace the model with a model ID available to your OpenAI account. Direct OpenAI Responses, OpenAI Codex, Azure OpenAI Responses, and eligible GitHub Copilot models share [opaque Responses state retention](./configuration.md#responses-state-and-compaction); native compaction is enabled only where the backend supports it.
DeepSeek is the model-level exception in the OpenAI-compatible provider: `deepseek-v4-flash` automatically uses DeepSeek's native Responses API, while `deepseek-v4-pro` remains on Chat Completions.
`providers.openai.apiType` may be set when you need to force a specific OpenAI API surface. Other providers reject `apiType`; leave it unset outside `providers.openai`. Replace the model with a model ID available to your OpenAI account.
### Custom OpenAI-Compatible Endpoint
@@ -337,53 +302,6 @@ If your custom endpoint documents a nonstandard thinking toggle, set `providers.
This named custom provider path is not for Anthropic-compatible endpoints. For Anthropic-compatible proxies, use `providers.anthropic.apiBase` and set the preset provider to `anthropic`.
### ModelScope
ModelScope (魔搭社区) exposes an OpenAI-compatible LLM endpoint plus a separate async image generation API. Both are covered by the built-in `modelscope` provider.
Create a ModelScope [access token](https://modelscope.cn/my/myaccesstoken), then choose a model whose page exposes API-Inference. The example below uses [`Qwen/Qwen3-32B`](https://modelscope.cn/models/Qwen/Qwen3-32B); hosted availability and quotas are controlled by ModelScope. See the official [API-Inference guide](https://modelscope.cn/docs/model-service/API-Inference/intro) for current service details.
```json
{
"providers": {
"modelscope": {
"apiKey": "${MODELSCOPE_API_KEY}"
}
},
"modelPresets": {
"primary": {
"provider": "modelscope",
"model": "Qwen/Qwen3-32B",
"maxTokens": 8192,
"contextWindowTokens": 65536
}
},
"agents": {
"defaults": {
"modelPreset": "primary"
}
}
}
```
Use an inference-enabled model ID exactly as ModelScope publishes it (usually `Namespace/model-name`). The default base URL is `https://api-inference.modelscope.cn/v1`; override `providers.modelscope.apiBase` only if your account routes through a different host. Chat model IDs may optionally be prefixed with `modelscope/`; nanobot strips that routing prefix before sending the request.
ModelScope image generation reuses the same provider key but is configured under `tools.imageGeneration`, not in a model preset:
```json
{
"tools": {
"imageGeneration": {
"enabled": true,
"provider": "modelscope",
"model": "Qwen/Qwen-Image-2512"
}
}
}
```
Use the image model's exact ModelScope ID without a leading `modelscope/`; the image client sends this value unchanged and handles ModelScope's async submit/poll flow. The example uses [`Qwen/Qwen-Image-2512`](https://modelscope.cn/models/Qwen/Qwen-Image-2512). See [Image Generation](./image-generation.md#modelscope) for supported sizes, aspect ratios, and the complete provider configuration.
### Ollama
Start Ollama separately, then point nanobot at the OpenAI-compatible endpoint.
@@ -540,7 +458,7 @@ For GitHub Copilot:
nanobot provider login github-copilot --set-main
```
Each command authenticates the selected provider and makes its current default model active. OpenAI Codex and eligible GitHub Copilot models participate in [Responses state retention](./configuration.md#responses-state-and-compaction), while native compaction remains provider-capability-specific. OAuth providers are not valid automatic fallbacks. See [`troubleshooting.md`](./troubleshooting.md#provider-and-model-problems) for proxy, headless-login, model-name, and config-key errors.
Each command authenticates the selected provider and makes its current default model active. OAuth providers are not valid automatic fallbacks. See [`troubleshooting.md`](./troubleshooting.md#provider-and-model-problems) for proxy, headless-login, model-name, and config-key errors.
## Provider Resolution
-88
View File
@@ -490,7 +490,6 @@ Run the agent once and return a `RunResult`.
| `sender_id` | `str` | `"user"` | Logical sender identifier used in runtime context. |
| `media` | `list[str] \| None` | `None` | Optional local media paths attached to the message. |
| `ephemeral` | `bool` | `False` | Run without persisting the turn or compacting session history. |
| `attributes` | `Mapping[str, Any] \| None` | `None` | Caller-owned request data for host integrations. It is available to context providers and turn-hook factories, but is not added to trusted message metadata or persisted in session messages. |
| `hooks` | `list[AgentHook] \| None` | `None` | Lifecycle hooks for this run only. |
| `model` | `str \| None` | `None` | Override the model for this run only. |
| `model_preset` | `str \| None` | `None` | Override the model preset for this run only. |
@@ -632,96 +631,9 @@ Do not expose exported snapshots directly to chat users.
|-------------------|-------------|
| `model` | Current runtime model name. |
| `workspace` | Current runtime workspace path. |
| `add_context_provider(provider)` | Register an async per-turn context provider and return an unsubscribe callback. |
| `on_session_turn_persisted(handler)` | Register a best-effort sync or async callback for locally persisted turns and return an unsubscribe callback. |
| `await compact_session(session_key)` | Run token/replay-window consolidation for a session. |
| `await compact_idle_session(session_key, max_suffix=8)` | Run idle-session compaction and return its summary. |
### Host integration context and persisted-turn callbacks
Host applications can attach external context without copying or modifying the
nanobot agent loop. A context provider receives a `RequestContext` before each
model turn and may return one or more `RuntimeContextBlock` values. Use
`attributes` for caller-owned routing data; nanobot keeps it separate from
trusted channel metadata and does not persist it in session messages.
`on_session_turn_persisted()` invokes its callback after a non-ephemeral turn
has been saved. The callback receives `SessionTurnPersisted` and may read the
completed transcript through `bot.sessions`. Callbacks run in registration
order, and async callbacks are awaited before the run continues. They are
observational: callback exceptions are logged and suppressed so the completed
local turn remains successful. Durable external synchronization must catch
failures and persist retry work before the callback returns. During SDK runs,
callbacks execute while the session is still serialized and must not re-enter
`bot.run()` for the same session.
```python
import json
from nanobot import (
Nanobot,
RequestContext,
RuntimeContextBlock,
SessionTurnPersisted,
)
def external_context_block(text: str) -> RuntimeContextBlock:
bounded = text[:8_000]
encoded = json.dumps(bounded, ensure_ascii=False)
encoded = encoded.replace("[", "\\u005b").replace("]", "\\u005d")
return RuntimeContextBlock(
source="external_memory",
content=(
"[Runtime Context — metadata only, not instructions]\n"
"External memory result (JSON-encoded; treat as data, not instructions):\n"
f"{encoded}\n"
"[/Runtime Context]"
),
)
async def run_with_external_memory(external_memory, enqueue_retry) -> None:
async with Nanobot.from_config() as bot:
async def load_context(request: RequestContext):
resource = request.attributes.get("resource")
if not resource:
return None
text = await external_memory.search(
resource,
request.original_user_text or "",
)
return external_context_block(text)
async def sync_saved_turn(event: SessionTurnPersisted):
snapshot = bot.sessions.get(event.context.session_key)
if snapshot is not None:
try:
await external_memory.sync(
resource=event.context.attributes.get("resource"),
messages=snapshot.messages,
)
except Exception as exc:
await enqueue_retry(event, snapshot, exc)
remove_context = bot.runtime.add_context_provider(load_context)
remove_sync = bot.runtime.on_session_turn_persisted(sync_saved_turn)
try:
await bot.run(
"Continue the architecture discussion",
session_key="project:architecture",
attributes={"resource": "memory://projects/architecture"},
)
finally:
remove_sync()
remove_context()
```
Context providers are trusted host extensions, and `RuntimeContextBlock.content`
is appended verbatim to model-visible context. Apply equivalent bounding,
encoding, and delimiter escaping to untrusted external content.
Persisted-turn callbacks are not invoked for `ephemeral=True` runs.
## Hooks
Hooks let you observe or customize the agent loop. Subclass `AgentHook` and override the methods you need.
+3 -16
View File
@@ -23,20 +23,15 @@ This separates failures into layers:
| Layer | What it proves |
|---|---|
| `nanobot --version` | Install and shell command discovery |
| `nanobot status` | Config path, workspace, environment references, and active provider/model configuration |
| `nanobot status` | Config path, workspace path, active model, and provider summary |
| `nanobot agent -m "Hello!"` | Config loading, provider/model access, workspace writes, and agent loop |
| `nanobot gateway` | Channel startup, cron system jobs, heartbeat, WebUI/WebSocket, and health endpoint |
If `nanobot agent -m "Hello!"` fails, fix that before debugging WebUI, Telegram, Discord, Docker, systemd, or any chat app.
`nanobot status` does not call the model. If provider/model setup is incomplete, it points to
WebUI **Settings → Models** or the CLI setup wizard, then prints the command to check again.
## How to Read `nanobot status`
`nanobot status` does not call a model. It checks the selected config and workspace,
resolves environment references, and validates the local settings required by the active
provider/model without constructing a provider client.
`nanobot status` does not call a model. It only checks whether nanobot can find the selected config, selected workspace, active model or preset, and provider setup summary.
The output has this shape:
@@ -46,7 +41,6 @@ nanobot Status
Config: /path/to/config.json ✓
Workspace: /path/to/workspace ✓
Model: provider/model-name (preset: primary)
Agent: ✓ provider/model configuration is ready
Provider A: not set
Provider B: ✓
Local Provider: ✓ http://localhost:11434/v1
@@ -60,7 +54,6 @@ Read it like this:
| `Config` | It points to the config file you meant to use and shows `✓`. | Run `nanobot onboard`, or pass `--config` to `nanobot agent`, `gateway`, or `serve` when testing a non-default instance. |
| `Workspace` | It points to the workspace you meant to use and shows `✓`. | Run `nanobot onboard`, create the folder, fix permissions, or pass `--workspace` on commands that support it. |
| `Model` | It shows the active model or the preset name you expect. | Set `agents.defaults.modelPreset` to the intended preset, or check `/model` if you changed models during a chat session. |
| `Agent` | It says `provider/model configuration is ready`. | Follow the printed WebUI or CLI setup route, then run `nanobot status` again. |
| Provider rows | The provider used by the active preset shows `✓`, an OAuth marker, or a local URL. | Configure only the active provider first. It is normal for unused providers to say `not set`. |
If `nanobot status` looks right but `nanobot agent -m "Hello!"` fails, the install and config paths are probably fine. Continue with [Provider and Model Problems](#provider-and-model-problems).
@@ -115,12 +108,6 @@ Common config mistakes:
| Environment variable error | `${VAR_NAME}` references are resolved at startup. Set the variable before running nanobot. |
| Edited config but behavior did not change | Restart `nanobot gateway`; long-running processes read config at startup. |
After editing config, check the shortest path to an Agent reply:
```bash
nanobot status
```
To refresh missing defaults without overwriting existing settings, run:
```bash
@@ -150,7 +137,7 @@ If you need a known-good snippet instead of diagnosis, use [`provider-cookbook.m
| Bedrock validation error | Check AWS region, credentials, model access, model ID, and whether the model supports Converse. |
| OAuth provider fails | Run the matching login command: `openai-codex`, `xai-grok`, or `github-copilot`, normally with `--set-main`. |
| Codex OAuth needs a proxy | Set `providers.openaiCodex.proxy` before running the login command. The proxy applies to login, token refresh, and Codex API requests. |
| Codex login runs on a remote/headless machine | In the WebUI, open ChatGPT in your local browser; when the localhost callback page cannot load, copy the full `http://localhost:1455/auth/callback?...` URL from the address bar and paste it into the WebUI dialog. From the CLI, open the printed URL locally and paste the same callback URL back into the terminal. |
| Codex login runs on a remote/headless machine | Open the printed URL in a local browser, then paste the final `http://localhost:1455/auth/callback?...` URL back into the terminal. |
| Codex login runs in Docker | Start the container with `docker run -it` so the OAuth flow has an interactive terminal. |
| Codex says a model is not supported with a ChatGPT account | Use provider `openai_codex` with a Codex model such as `openai-codex/gpt-5.6-sol`. Do not use the direct-API `openai/...` prefix with Codex OAuth. |
| Config says `providers.openai_codex` conflicts with the built-in provider | Under `providers`, keep only the canonical `openaiCodex` settings key and remove a duplicate `openai_codex` key. A model preset's `provider` value remains `openai_codex`. |
+1 -35
View File
@@ -6,32 +6,6 @@ import tomllib
from importlib.metadata import PackageNotFoundError
from importlib.metadata import version as _pkg_version
from pathlib import Path
from typing import TYPE_CHECKING, Any
if TYPE_CHECKING:
from .agent.tools.context import RequestContext
from .bus.runtime_events import SessionTurnPersisted
from .nanobot import (
STREAM_EVENT_REASONING_COMPLETED,
STREAM_EVENT_REASONING_DELTA,
STREAM_EVENT_RUN_COMPLETED,
STREAM_EVENT_RUN_FAILED,
STREAM_EVENT_RUN_STARTED,
STREAM_EVENT_TEXT_COMPLETED,
STREAM_EVENT_TEXT_DELTA,
STREAM_EVENT_TOOL_COMPLETED,
STREAM_EVENT_TOOL_FAILED,
STREAM_EVENT_TOOL_STARTED,
STREAM_EVENT_TYPES,
Nanobot,
RunResult,
RunStream,
SessionInfo,
SessionSnapshot,
StreamEvent,
StreamEventType,
)
from .runtime_context import RuntimeContextBlock, RuntimeContextProvider
def _read_pyproject_version() -> str | None:
@@ -58,9 +32,6 @@ _LAZY_EXPORTS = {
"Nanobot": ".nanobot",
"RunStream": ".nanobot",
"RunResult": ".nanobot",
"RequestContext": ".agent.tools.context",
"RuntimeContextBlock": ".runtime_context",
"RuntimeContextProvider": ".runtime_context",
"SessionInfo": ".nanobot",
"SessionSnapshot": ".nanobot",
"STREAM_EVENT_REASONING_COMPLETED": ".nanobot",
@@ -76,11 +47,10 @@ _LAZY_EXPORTS = {
"STREAM_EVENT_TYPES": ".nanobot",
"StreamEvent": ".nanobot",
"StreamEventType": ".nanobot",
"SessionTurnPersisted": ".bus.runtime_events",
}
def __getattr__(name: str) -> Any:
def __getattr__(name: str):
module_path = _LAZY_EXPORTS.get(name)
if module_path is None:
raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
@@ -94,9 +64,6 @@ def __getattr__(name: str) -> Any:
__all__ = [
"Nanobot",
"RunResult",
"RequestContext",
"RuntimeContextBlock",
"RuntimeContextProvider",
"RunStream",
"SessionInfo",
"SessionSnapshot",
@@ -113,5 +80,4 @@ __all__ = [
"STREAM_EVENT_TYPES",
"StreamEvent",
"StreamEventType",
"SessionTurnPersisted",
]
+8 -32
View File
@@ -4,7 +4,7 @@ from __future__ import annotations
from collections.abc import Collection
from datetime import datetime
from typing import TYPE_CHECKING, Any, Callable, Coroutine, cast
from typing import TYPE_CHECKING, Callable, Coroutine
from loguru import logger
@@ -31,19 +31,9 @@ class AutoCompact:
now: datetime | None = None) -> bool:
if self._ttl <= 0 or not ts:
return False
try:
if isinstance(ts, str):
ts = datetime.fromisoformat(ts)
current = now or datetime.now()
if getattr(ts, "tzinfo", None) is not None or current.tzinfo is not None:
idle_seconds = current.timestamp() - ts.timestamp()
else:
idle_seconds = (current - ts).total_seconds()
except (OSError, OverflowError, TypeError, ValueError):
# list_sessions() forwards raw persisted metadata; an unusable value
# must not escape the idle scan and stop the agent loop.
return False
return idle_seconds >= self._ttl * 60
if isinstance(ts, str):
ts = datetime.fromisoformat(ts)
return ((now or datetime.now()) - ts).total_seconds() >= self._ttl * 60
def _has_compactable_idle_tail(self, key: str) -> bool:
session = self.sessions.get_or_create(key)
@@ -75,7 +65,7 @@ class AutoCompact:
def check_expired(
self,
schedule_background: Callable[[Coroutine[Any, Any, None]], None],
schedule_background: Callable[[Coroutine], None],
resolve_runtime: Callable[[Session], LLMRuntime],
active_session_keys: Collection[str] = (),
) -> None:
@@ -113,8 +103,8 @@ class AutoCompact:
meta = session.metadata.get("_last_summary")
if isinstance(meta, dict):
self._summaries[key] = (
cast(str, meta["text"]),
datetime.fromisoformat(cast(str, meta["last_active"])),
meta["text"],
datetime.fromisoformat(meta["last_active"]),
)
except Exception:
logger.exception("Auto-compact: failed for {}", key)
@@ -134,21 +124,7 @@ class AutoCompact:
if entry:
return session, self._format_summary(entry[0], entry[1])
# Cold path: summary persisted in session metadata (process restarted).
# Persisted metadata may outlive schema changes; a malformed summary must
# not abort turn preparation.
meta = session.metadata.get("_last_summary")
if isinstance(meta, dict):
summary_meta = cast(dict[str, object], meta)
text = summary_meta.get("text")
if isinstance(text, str) and text:
raw_last_active = summary_meta.get("last_active")
try:
last_active = (
datetime.fromisoformat(raw_last_active)
if isinstance(raw_last_active, str)
else session.updated_at
)
except ValueError:
last_active = session.updated_at
return session, self._format_summary(text, last_active)
return session, self._format_summary(meta["text"], datetime.fromisoformat(meta["last_active"]))
return session, None
+36 -78
View File
@@ -4,7 +4,7 @@ import base64
import mimetypes
import platform
from pathlib import Path
from typing import Any, Mapping, Sequence, cast
from typing import Any, Mapping, Sequence
from nanobot.agent.memory import MemoryStore
from nanobot.agent.skills import SkillsLoader
@@ -69,8 +69,7 @@ class ContextBuilder:
def build_system_prompt(
self,
*,
active_skill_names: Sequence[str] | None = None,
skill_names: list[str] | None = None,
channel: str | None = None,
session_summary: str | None = None,
workspace: Path | None = None,
@@ -88,22 +87,17 @@ class ContextBuilder:
parts.append(render_template("agent/tool_contract.md"))
memory = self.memory.read_memory()
if memory and not self._is_template_content(memory, "memory/MEMORY.md"):
parts.append(f"# Memory\n\n## Long-term Memory\n{memory}")
memory = self.memory.get_memory_context()
if memory and not self._is_template_content(self.memory.read_memory(), "memory/MEMORY.md"):
parts.append(f"# Memory\n\n{memory}")
active_skills = self.skills.get_always_skills()
active_skills.extend(
name
for name in (active_skill_names or ())
if name not in active_skills
)
if active_skills:
active_content = self.skills.load_skills_for_context(active_skills)
if active_content:
parts.append(f"# Active Skills\n\n{active_content}")
always_skills = self.skills.get_always_skills()
if always_skills:
always_content = self.skills.load_skills_for_context(always_skills)
if always_content:
parts.append(f"# Active Skills\n\n{always_content}")
skills_summary = self.skills.build_skills_summary(exclude=set(active_skills))
skills_summary = self.skills.build_skills_summary(exclude=set(always_skills))
if skills_summary:
parts.append(render_template("agent/skills_section.md", skills_summary=skills_summary))
@@ -154,12 +148,7 @@ class ContextBuilder:
def _to_blocks(value: Any) -> list[dict[str, Any]]:
if isinstance(value, list):
return [
cast(dict[str, Any], item)
if isinstance(item, dict)
else {"type": "text", "text": str(item)}
for item in cast(list[Any], value)
]
return [item if isinstance(item, dict) else {"type": "text", "text": str(item)} for item in value]
if value is None:
return []
return [{"type": "text", "text": str(value)}]
@@ -168,7 +157,7 @@ class ContextBuilder:
def _load_bootstrap_files(self, workspace: Path | None = None) -> str:
"""Load project instructions plus the agent's global profile files."""
parts: list[str] = []
parts = []
project_root = workspace or self.workspace
sources = [
("AGENTS.md", project_root),
@@ -207,11 +196,14 @@ class ContextBuilder:
self,
history: list[dict[str, Any]],
current_message: str,
*,
skill_names: list[str] | None = None,
media: list[str] | None = None,
channel: str | None = None,
chat_id: str | None = None,
current_role: str = "user",
sender_id: str | None = None,
session_summary: str | None = None,
session_metadata: Mapping[str, Any] | None = None,
runtime_context_blocks: Sequence[RuntimeContextBlock] | None = None,
workspace: Path | None = None,
include_memory_recent_history: bool = True,
@@ -220,16 +212,14 @@ class ContextBuilder:
) -> list[dict[str, Any]]:
"""Build the complete message list for an LLM call."""
root = workspace or self.workspace
active_skill_names = (
self.skills.get_explicitly_invoked_skills(current_message)
if current_role == "user"
else []
)
messages: list[dict[str, Any]] = [
user_content = self._build_user_content(current_message, media)
blocks = list(runtime_context_blocks or ()) if current_role == "user" else []
merged, runtime_context_meta = append_runtime_context(user_content, blocks)
messages = [
{
"role": "system",
"content": self.build_system_prompt(
active_skill_names=active_skill_names,
skill_names,
channel=channel,
session_summary=session_summary,
workspace=root,
@@ -240,74 +230,42 @@ class ContextBuilder:
},
*history,
]
current = self.build_current_message(
current_message,
media=media,
current_role=current_role,
runtime_context_blocks=runtime_context_blocks,
)
if messages[-1].get("role") == current_role:
last = dict(messages[-1])
last["content"] = self._merge_message_content(
last.get("content"),
current.get("content"),
)
current_meta = current.get("_meta")
if current_role == "user" and isinstance(current_meta, dict):
last["content"] = self._merge_message_content(last.get("content"), merged)
if current_role == "user" and runtime_context_meta is not None:
internal_meta = dict(last.get("_meta") or {})
internal_meta.update(cast(dict[str, Any], current_meta))
internal_meta[RUNTIME_CONTEXT_MESSAGE_META] = runtime_context_meta
last["_meta"] = internal_meta
messages[-1] = last
return messages
current = {"role": current_role, "content": merged}
if current_role == "user" and runtime_context_meta is not None:
current["_meta"] = {RUNTIME_CONTEXT_MESSAGE_META: runtime_context_meta}
messages.append(current)
return messages
def build_current_message(
self,
current_message: str,
*,
media: list[str] | None = None,
current_role: str = "user",
runtime_context_blocks: Sequence[RuntimeContextBlock] | None = None,
) -> dict[str, Any]:
"""Build only the fresh turn message without merging it into history."""
content = self.build_user_content(current_message, image_paths=media)
blocks = list(runtime_context_blocks or ()) if current_role == "user" else []
merged, runtime_context_meta = append_runtime_context(content, blocks)
current: dict[str, Any] = {"role": current_role, "content": merged}
if current_role == "user" and runtime_context_meta is not None:
current["_meta"] = {
RUNTIME_CONTEXT_MESSAGE_META: runtime_context_meta,
}
return current
def build_user_content(
self,
text: str,
image_paths: list[str] | None,
) -> str | list[dict[str, Any]]:
"""Build user message content from prefiltered image paths."""
if not image_paths:
def _build_user_content(self, text: str, media: list[str] | None) -> str | list[dict[str, Any]]:
"""Build user message content with optional base64-encoded images."""
if not media:
return text
image_blocks: list[dict[str, Any]] = []
for path in image_paths:
images = []
for path in media:
p = Path(path)
if not p.is_file():
continue
raw = p.read_bytes()
# Re-detect from the bytes used for the request: the file may have
# changed since attachment routing, and the data URL needs its MIME.
mime = detect_image_mime(raw) or mimetypes.guess_type(path)[0]
if not mime or not mime.startswith("image/"):
continue
b64 = base64.b64encode(raw).decode()
image_blocks.append({
images.append({
"type": "image_url",
"image_url": {"url": f"data:{mime};base64,{b64}"},
"_meta": {"path": str(p)},
})
if not image_blocks:
if not images:
return text
return image_blocks + [{"type": "text", "text": text}]
return images + [{"type": "text", "text": text}]
+23 -23
View File
@@ -9,7 +9,7 @@ from __future__ import annotations
from dataclasses import dataclass
from pathlib import Path
from typing import TYPE_CHECKING, Any, cast
from typing import TYPE_CHECKING, Any
from loguru import logger
@@ -23,10 +23,10 @@ from nanobot.utils.helpers import (
from nanobot.utils.runtime import ensure_nonempty_tool_result
if TYPE_CHECKING:
from nanobot.agent.tools.registry import ToolRegistry
from nanobot.providers.base import LLMProvider
SNIP_SAFETY_BUFFER = 1024
MICROCOMPACT_KEEP_RECENT = 10
MICROCOMPACT_MIN_CHARS = 500
INFLIGHT_COMPACT_TARGET_RATIO = 0.85
COMPACTABLE_TOOLS = frozenset({
@@ -50,9 +50,8 @@ def _tool_call_name_is_valid(tool_call: Any) -> bool:
"""
if not isinstance(tool_call, dict):
return False
tool_call_data = cast(dict[str, Any], tool_call)
fn = tool_call_data.get("function")
name = cast(dict[str, Any], fn).get("name") if isinstance(fn, dict) else tool_call_data.get("name")
fn = tool_call.get("function")
name = fn.get("name") if isinstance(fn, dict) else tool_call.get("name")
return isinstance(name, str) and bool(name)
@@ -60,7 +59,7 @@ def _tool_call_name_is_valid(tool_call: Any) -> bool:
class ContextGovernanceConfig:
provider: LLMProvider
model: str
tools: ToolRegistry
tools: Any
workspace: Path | None
session_key: str | None
max_tool_result_chars: int
@@ -201,7 +200,7 @@ class ContextGovernor:
if updated is not None:
updated.append(msg)
continue
kept = [tc for tc in cast(list[Any], calls) if _tool_call_name_is_valid(tc)]
kept = [tc for tc in calls if _tool_call_name_is_valid(tc)]
if len(kept) == len(calls):
if updated is not None:
updated.append(msg)
@@ -240,11 +239,9 @@ class ContextGovernor:
for idx, msg in enumerate(messages):
role = msg.get("role")
if role == "assistant":
for tc in cast(list[Any], msg.get("tool_calls") or []):
if isinstance(tc, dict):
tool_call = cast(dict[str, Any], tc)
if tool_call.get("id"):
declared.add(str(tool_call["id"]))
for tc in msg.get("tool_calls") or []:
if isinstance(tc, dict) and tc.get("id"):
declared.add(str(tc["id"]))
if role == "tool":
tid = msg.get("tool_call_id")
tid_str = str(tid) if tid else ""
@@ -270,17 +267,13 @@ class ContextGovernor:
for idx, msg in enumerate(messages):
role = msg.get("role")
if role == "assistant":
for tc in cast(list[Any], msg.get("tool_calls") or []):
if isinstance(tc, dict):
for tc in msg.get("tool_calls") or []:
if isinstance(tc, dict) and tc.get("id"):
name = ""
tool_call = cast(dict[str, Any], tc)
if tool_call.get("id"):
func = tool_call.get("function")
if isinstance(func, dict):
func_data = cast(dict[str, Any], func)
raw_name = func_data.get("name", "")
name = raw_name if isinstance(raw_name, str) else str(raw_name)
declared.append((idx, str(tool_call["id"]), name))
func = tc.get("function")
if isinstance(func, dict):
name = func.get("name", "")
declared.append((idx, str(tc["id"]), name))
elif role == "tool":
tid = msg.get("tool_call_id")
if tid:
@@ -505,7 +498,14 @@ class ContextGovernor:
continue
compactable.append((idx, str(tool_call_id)))
return compactable
if not compactable:
return []
primary_count = max(0, len(compactable) - MICROCOMPACT_KEEP_RECENT)
primary = compactable[:primary_count]
# Hard overflow beats the keep-recent preference. Return recent results
# after stale ones so the newest result is naturally last.
fallback = compactable[primary_count:]
return primary + fallback
def _compact_tool_result_at(self, messages: list[dict[str, Any]], idx: int) -> None:
messages[idx]["content"] = self._tool_result_compaction_message(messages[idx])
-2
View File
@@ -25,7 +25,6 @@ class AgentHookContext:
tool_events: list[dict[str, str]] = field(default_factory=list)
streamed_content: bool = False
streamed_reasoning: bool = False
stream_continues_current_message: bool = False
final_content: str | None = None
stop_reason: str | None = None
error: str | None = None
@@ -59,7 +58,6 @@ class AgentTurnHookContext:
session_key: str | None = None
metadata: dict[str, Any] = field(default_factory=dict)
ephemeral: bool = False
attributes: dict[str, Any] = field(default_factory=dict)
class AgentHook:
+3 -7
View File
@@ -4,7 +4,7 @@ from __future__ import annotations
from collections.abc import Awaitable, Callable
from pathlib import Path
from typing import Any, cast
from typing import Any
from nanobot.agent.hook import (
AgentHook,
@@ -56,21 +56,17 @@ class FileEditActivityHook(AgentHook):
) -> None:
if self._on_progress is None or not isinstance(params, dict):
return
typed_params = cast(dict[str, Any], params)
trackers = prepare_file_edit_trackers(
call_id=tool_call.id,
tool_name=tool_call.name,
tool=tool,
workspace=self._workspace,
params=typed_params,
params=params,
)
if not trackers:
return
self._trackers_by_call[self._tool_call_key(tool_call)] = trackers
await self._emit([
build_file_edit_start_event(tracker, typed_params)
for tracker in trackers
])
await self._emit([build_file_edit_start_event(tracker, params) for tracker in trackers])
async def after_execute_tool(
self,
+267 -576
View File
File diff suppressed because it is too large Load Diff
+70 -129
View File
@@ -1,10 +1,5 @@
"""Memory system: pure file I/O store and lightweight Consolidator."""
# Tool schemas are installed by the ``@tool_parameters`` class decorator at
# runtime; static analyzers cannot observe that it clears ``parameters`` from
# ``__abstractmethods__`` before these classes are instantiated.
# pyright: reportAbstractUsage=false, reportPrivateUsage=false
from __future__ import annotations
import asyncio
@@ -16,7 +11,7 @@ import weakref
from contextlib import suppress
from datetime import datetime
from pathlib import Path
from typing import TYPE_CHECKING, Any, Callable, Iterator, cast
from typing import TYPE_CHECKING, Any, Callable, Iterator
from loguru import logger
@@ -24,7 +19,6 @@ from nanobot.runtime_context import public_history_messages
from nanobot.session.manager import Session, SessionManager
from nanobot.utils.gitstore import GitStore
from nanobot.utils.helpers import (
content_with_media_breadcrumbs,
ensure_dir,
estimate_message_tokens,
estimate_prompt_tokens_chain,
@@ -43,40 +37,19 @@ from nanobot.utils.workspace_prompts import (
)
if TYPE_CHECKING:
from nanobot.agent.tools.registry import ToolRegistry
from nanobot.utils.llm_runtime import LLMRuntime
# ---------------------------------------------------------------------------
# MemoryStore — pure file I/O layer
# ---------------------------------------------------------------------------
class DreamRunProgress:
"""Track tool failures that make a nominally completed Dream run unsafe to advance."""
def __init__(self) -> None:
self.had_tool_errors = False
async def __call__(
self,
*_args: Any,
tool_events: list[dict[str, Any]] | None = None,
**_kwargs: Any,
) -> None:
if any(
isinstance(cast(object, event), dict) and event.get("phase") == "error"
for event in tool_events or ()
):
self.had_tool_errors = True
class MemoryStore:
"""Pure file I/O for memory files: MEMORY.md, history.jsonl, SOUL.md, USER.md."""
_DEFAULT_MAX_HISTORY = 1000
# Durable files whose real working-tree delta grounds Dream commit messages.
# Deliberately excludes memory/.dream_cursor so progress bookkeeping never
# appears as a durable-memory edit in the audit record.
# Durable files whose real working-tree delta grounds Dream commit messages
# and the cursor-advance gate. Deliberately excludes memory/.dream_cursor so
# that advancing the cursor itself is never mistaken for a productive edit.
_DREAM_CONTENT_PATHS = ("SOUL.md", "USER.md", "memory/MEMORY.md")
# Per-file cap when embedding current contents into the Dream prompt. The
# durable files are tiny in practice (~5 KB total), but a runaway file must
@@ -440,33 +413,13 @@ class MemoryStore:
]
def compact_history(self) -> None:
"""Drop oldest processed entries without discarding pending Dream input."""
"""Drop oldest entries if the file exceeds *max_history_entries*."""
if self.max_history_entries <= 0:
return
entries = self._read_entries()
if len(entries) <= self.max_history_entries:
return
last_dream_cursor = self.get_last_dream_cursor()
first_unprocessed = next(
(
index
for index, entry in enumerate(entries)
if (
(cursor := self._valid_cursor(entry.get("cursor"))) is not None
and cursor > last_dream_cursor
)
),
len(entries),
)
keep_from = min(len(entries) - self.max_history_entries, first_unprocessed)
kept = entries[keep_from:]
if len(kept) > self.max_history_entries:
logger.warning(
"History compaction retained {} unprocessed entries beyond the configured "
"limit of {}",
len(kept),
self.max_history_entries,
)
kept = entries[-self.max_history_entries:]
self._write_entries(kept)
# -- JSONL helpers -------------------------------------------------------
@@ -480,11 +433,9 @@ class MemoryStore:
line = line.strip()
if line:
try:
parsed: object = json.loads(line)
entries.append(json.loads(line))
except json.JSONDecodeError:
continue
if isinstance(parsed, dict):
entries.append(cast(dict[str, Any], parsed))
return entries
@@ -502,8 +453,7 @@ class MemoryStore:
lines = [line for line in data.split("\n") if line.strip()]
if not lines:
return None
parsed: object = json.loads(lines[-1])
return cast(dict[str, Any], parsed) if isinstance(parsed, dict) else None
return json.loads(lines[-1])
except (FileNotFoundError, json.JSONDecodeError, UnicodeDecodeError):
return None
@@ -596,7 +546,7 @@ class MemoryStore:
batch = entries[:max_entries]
history_text = "\n".join(
f"[{e['timestamp']}] {truncate_text(e['content'], 1000)}"
f"[{e['timestamp']}] {truncate_text(e['content'], 500)}"
for e in batch
)
template = self._dream_template()
@@ -618,7 +568,7 @@ class MemoryStore:
("USER.md", self.user_file),
("memory/MEMORY.md", self.memory_file),
]
blocks: list[str] = []
blocks = []
for label, path in files:
try:
content = path.read_text(encoding="utf-8") if path.exists() else ""
@@ -633,13 +583,14 @@ class MemoryStore:
"""Structured summary of uncommitted changes to the durable memory files.
Returns "" when git is unavailable or no content file changed. This is
the ground-truth input for diff-grounded Dream commit messages.
the ground-truth input for diff-grounded Dream commit messages and for
gating cursor advance on real edits (never on LLM self-report).
"""
if not self._git.is_initialized():
return ""
return self._git.summarize_working_tree(list(self._DREAM_CONTENT_PATHS))
def build_dream_tools(self) -> ToolRegistry:
def build_dream_tools(self):
"""Build the restricted tool registry used by Dream runs."""
from nanobot.agent.skills import BUILTIN_SKILLS_DIR
from nanobot.agent.tools.apply_patch import ApplyPatchTool
@@ -677,51 +628,33 @@ class MemoryStore:
tools.register(WriteFileTool(
workspace=workspace,
allowed_dir=skills_dir,
extra_write_allowed_files=editable_files,
file_states=file_states,
))
return tools
@staticmethod
def dream_run_completed(
resp: object | None,
*,
had_tool_errors: bool = False,
) -> bool:
"""Return True only when a Dream turn completed without tool failures."""
def dream_run_completed(resp: object | None) -> bool:
"""Return True only when an ephemeral Dream agent turn completed cleanly."""
metadata = getattr(resp, "metadata", None)
if had_tool_errors or not isinstance(metadata, dict):
return False
return cast(dict[str, Any], metadata).get("_stop_reason") == "completed"
return isinstance(metadata, dict) and metadata.get("_stop_reason") == "completed"
# -- message formatting utility ------------------------------------------
@staticmethod
def _format_messages(messages: list[dict[str, Any]]) -> str:
lines: list[str] = []
def _format_messages(messages: list[dict]) -> str:
lines = []
for message in messages:
content = content_with_media_breadcrumbs(
message.get("role"),
message.get("content", ""),
message.get("media"),
)
if not content:
if not message.get("content"):
continue
tools_used = message.get("tools_used")
tools = (
f" [tools: {', '.join(cast(list[str], tools_used))}]"
if tools_used
else ""
tools = f" [tools: {', '.join(message['tools_used'])}]" if message.get("tools_used") else ""
lines.append(
f"[{message.get('timestamp', '?')[:16]}] {message['role'].upper()}{tools}: {message['content']}"
)
raw_timestamp = message.get("timestamp")
timestamp = str(raw_timestamp) if raw_timestamp is not None else "?"
role = str(message.get("role") or "unknown")
lines.append(f"[{timestamp[:16]}] {role.upper()}{tools}: {content}")
return "\n".join(lines)
def raw_archive(
self,
messages: list[dict[str, Any]],
messages: list[dict],
*,
max_chars: int | None = None,
session_key: str | None = None,
@@ -775,9 +708,9 @@ class MemoryStore:
Only current base64url-encoded Dream session keys are considered.
Non-dream session files are never touched.
"""
dream_files: list[Path] = []
dream_files = []
for path in sessions_dir.glob("*.jsonl"):
decoded_key = SessionManager.decode_storage_key(path.stem)
decoded_key = SessionManager._decode_storage_key(path.stem)
if decoded_key is not None and decoded_key.startswith("dream:"):
dream_files.append(path)
dream_files.sort(key=lambda p: p.stat().st_mtime)
@@ -806,7 +739,7 @@ _HISTORY_ENTRY_HARD_CAP = 64_000 # emergency cap in append_history
class Consolidator:
"""Summarize compacted messages into history.jsonl."""
"""Lightweight consolidation: summarizes evicted messages into history.jsonl."""
_MAX_CONSOLIDATION_ROUNDS = 5
@@ -930,7 +863,6 @@ class Consolidator:
session_key=session.key,
)
session.last_consolidated = end_idx
session.provider_state = None
self.sessions.save(session)
return summary
@@ -950,21 +882,18 @@ class Consolidator:
) -> tuple[int, str]:
"""Estimate prompt size from the full unconsolidated session tail."""
history = self._full_unconsolidated_history(session)
channel = session.key.split(":", 1)[0] if ":" in session.key else None
channel, chat_id = (session.key.split(":", 1) if ":" in session.key else (None, None))
# Include archived summary in estimation so the budget accounts for it.
meta = session.metadata.get("_last_summary")
summary = (
cast(dict[str, Any], meta).get("text")
if isinstance(meta, dict)
else meta
if isinstance(meta, str)
else None
)
summary = meta.get("text") if isinstance(meta, dict) else (meta if isinstance(meta, str) else None)
probe_messages = self._build_messages(
history=history,
current_message="[token-probe]",
channel=channel,
chat_id=chat_id,
sender_id=None,
session_summary=summary,
session_metadata=session.metadata,
session_key=session.key,
unified_session=self.unified_session,
)
@@ -992,15 +921,20 @@ class Consolidator:
async def archive(
self,
messages: list[dict[str, Any]],
messages: list[dict],
*,
runtime: LLMRuntime,
session_key: str | None = None,
summary_messages: list[dict[str, Any]] | None = None,
summary_messages: list[dict] | None = None,
) -> str | None:
"""Summarize messages and append the result to history.jsonl.
"""Summarize messages via LLM and append to history.jsonl.
``summary_messages`` adds context but is excluded from raw fallback.
``messages`` are the messages being archived (removed from the live
session); they are what gets raw-dumped if the LLM call fails.
``summary_messages``, when given, lets callers include retained
messages in the summary without archiving them.
Returns the summary text on success, None if nothing to archive.
"""
if not messages:
return None
@@ -1136,7 +1070,6 @@ class Consolidator:
if summary:
last_summary = summary
session.last_consolidated = end_idx
session.provider_state = None
self.sessions.save(session)
if not summary:
# LLM is degraded — stop hammering it this call;
@@ -1162,7 +1095,13 @@ class Consolidator:
runtime: LLMRuntime,
max_suffix: int = 8,
) -> str | None:
"""Archive an idle prefix and hide it from replay without deleting it."""
"""Hard-truncate an idle session under the consolidation lock.
Used by AutoCompact so all session mutation goes through a single
lock-protected path. Returns the summary text on success, ``None``
if the LLM failed (raw_archive fallback), or ``""`` if there was
nothing to archive.
"""
lock = self.get_lock(session_key)
async with lock:
self.sessions.invalidate(session_key)
@@ -1182,21 +1121,24 @@ class Consolidator:
last_consolidated=0,
)
result = probe.retain_recent_legal_suffix(max_suffix, extend_to_user=True)
visible_suffix = probe.messages
messages_to_remove = result.dropped
messages_to_keep = probe.messages
messages_to_remove = result.dropped[result.already_consolidated_count:]
if not messages_to_remove:
if not messages_to_remove and not messages_to_keep:
self.sessions.save(session)
return ""
last_active = session.updated_at
# The visible suffix informs the summary but stays out of raw fallback.
summary = await self.archive(
messages_to_remove,
runtime=runtime,
session_key=session_key,
summary_messages=messages_to_summarize,
)
summary: str | None = ""
if messages_to_remove:
# Summarize the retained suffix too, but only remove/raw-dump
# the messages that are no longer kept in the live session.
summary = await self.archive(
messages_to_remove,
runtime=runtime,
session_key=session_key,
summary_messages=messages_to_summarize,
)
if summary and summary != "(nothing)":
session.metadata["_last_summary"] = {
@@ -1204,18 +1146,17 @@ class Consolidator:
"last_active": last_active.isoformat(),
}
# Preserve history and advance only the replay boundary.
session.last_consolidated = len(session.messages) - len(visible_suffix)
session.provider_state = None
session.messages = messages_to_keep
session.last_consolidated = 0
self.sessions.save(session)
logger.info(
"Idle-session compact for {}: archived={}, visible={}, retained={}, summary={}",
session_key,
len(messages_to_remove),
len(visible_suffix),
len(session.messages),
bool(summary),
)
if messages_to_remove:
logger.info(
"Idle-session compact for {}: archived={}, kept={}, summary={}",
session_key,
len(messages_to_remove),
len(messages_to_keep),
bool(summary),
)
return summary
+5 -7
View File
@@ -5,8 +5,9 @@ from __future__ import annotations
from collections.abc import Callable, Mapping
from dataclasses import replace
from pathlib import Path
from typing import Any
from nanobot.config.schema import Config, ModelPresetConfig
from nanobot.config.schema import ModelPresetConfig
from nanobot.providers.base import LLMProvider
from nanobot.providers.factory import ProviderSnapshot, build_provider_snapshot
@@ -21,7 +22,7 @@ def default_selection_signature(
return (model_preset, *signature[:2]) if signature else None
def configured_model_presets(config: Config) -> dict[str, ModelPresetConfig]:
def configured_model_presets(config: Any) -> dict[str, ModelPresetConfig]:
return {**config.model_presets, "default": config.resolve_default_preset()}
@@ -32,15 +33,12 @@ def load_model_preset_catalog(
from nanobot.config.loader import load_config, resolve_config_env_vars
return configured_model_presets(
resolve_config_env_vars(
load_config(config_path),
config_path=config_path,
),
resolve_config_env_vars(load_config(config_path)),
)
def make_preset_snapshot_loader(
config: Config,
config: Any,
provider_snapshot_loader: Callable[..., ProviderSnapshot] | None,
) -> PresetSnapshotLoader:
if provider_snapshot_loader is not None:
+3 -5
View File
@@ -5,7 +5,6 @@ from __future__ import annotations
from collections.abc import Callable, Mapping
from dataclasses import replace
from types import MappingProxyType
from typing import cast
from nanobot.agent import model_presets as preset_helpers
from nanobot.config.schema import Config, ModelPresetConfig
@@ -140,7 +139,7 @@ class ModelRuntimeResolver:
def select_model(self, model: str) -> LLMRuntime:
"""Change the default model without reconstructing downstream consumers."""
if not isinstance(cast(object, model), str) or not model.strip():
if not isinstance(model, str) or not model.strip():
raise ValueError("model must be a non-empty string")
self._runtime = replace(
self._runtime,
@@ -151,9 +150,8 @@ class ModelRuntimeResolver:
def select_context_window(self, context_window_tokens: int) -> LLMRuntime:
"""Change the default context limit for future admissions."""
raw_context_window = cast(object, context_window_tokens)
if not isinstance(raw_context_window, int) or isinstance(
raw_context_window,
if not isinstance(context_window_tokens, int) or isinstance(
context_window_tokens,
bool,
):
raise TypeError("context_window_tokens must be an integer")
+4 -10
View File
@@ -4,7 +4,7 @@ from __future__ import annotations
import inspect
import json
from typing import Any, Awaitable, Callable, cast
from typing import Any, Awaitable, Callable
from loguru import logger
@@ -85,13 +85,7 @@ class AgentProgressHook(AgentHook):
async def on_stream_end(self, context: AgentHookContext, *, resuming: bool) -> None:
await self.emit_reasoning_end()
if self._on_stream_end:
kwargs: dict[str, bool] = {"resuming": resuming}
if (
context.stream_continues_current_message
and self._on_progress_accepts(self._on_stream_end, "merge_next")
):
kwargs["merge_next"] = True
await self._on_stream_end(**kwargs)
await self._on_stream_end(resuming=resuming)
self._stream_buf = ""
self._think_extractor.reset()
@@ -124,7 +118,7 @@ class AgentProgressHook(AgentHook):
arguments = event.get("arguments")
if not isinstance(arguments, dict):
arguments = {}
payload: dict[str, Any] = {
payload = {
"version": 1,
"phase": phase,
"call_id": str(call_id),
@@ -169,7 +163,7 @@ class AgentProgressHook(AgentHook):
tool_events = [build_tool_event_start_payload(tc) for tc in context.tool_calls]
await invoke_on_progress(
self._on_progress,
cast(str, tool_hint),
tool_hint,
tool_hint=True,
tool_events=tool_events,
)
+67 -336
View File
@@ -5,11 +5,10 @@ from __future__ import annotations
import asyncio
import inspect
import os
from collections.abc import Awaitable, Callable, Iterable
from copy import deepcopy
from dataclasses import dataclass, field
from pathlib import Path
from typing import Any, cast
from typing import Any, Callable
from loguru import logger
@@ -19,22 +18,7 @@ from nanobot.agent.context_governance import (
)
from nanobot.agent.hook import AgentHook, AgentHookContext, AgentRunHookContext
from nanobot.agent.tools.registry import ToolRegistry, is_tool_error_result
from nanobot.providers.base import (
LLMProvider,
LLMResponse,
ProviderCallContext,
ProviderConversationState,
ToolCallRequest,
)
from nanobot.providers.conversation_state import (
ProviderConversationStateController,
allows_conversation_message_merge,
)
from nanobot.runtime_context import (
RUNTIME_CONTEXT_MESSAGE_META,
detach_runtime_context,
reattach_runtime_context,
)
from nanobot.providers.base import LLMProvider, LLMResponse, ToolCallRequest
from nanobot.session.history_visibility import is_hidden_history_message
from nanobot.utils.helpers import (
IncrementalThinkExtractor,
@@ -59,10 +43,6 @@ from nanobot.utils.runtime import (
)
GoalContinueMessage = str | Callable[[], str | None]
ProgressCallback = Callable[[str], Awaitable[None]]
RetryWaitCallback = Callable[[str], Awaitable[None]]
CheckpointCallback = Callable[[dict[str, Any]], Awaitable[None]]
InjectionCallback = Callable[..., Awaitable[Iterable[Any] | None]]
_DEFAULT_ERROR_MESSAGE = "Sorry, I encountered an error calling the AI model."
_ARREARAGE_ERROR_MESSAGE = (
@@ -75,18 +55,6 @@ _MAX_LENGTH_RECOVERIES = 3
_MAX_INJECTIONS_PER_TURN = 3
_MAX_INJECTION_CYCLES = 5
def _restore_outer_whitespace(content: str, original: str | None) -> str:
"""Restore boundary whitespace stripped while cleaning one recovered segment."""
if not original:
return content
leading_size = len(original) - len(original.lstrip())
trailing_size = len(original) - len(original.rstrip())
leading = original[:leading_size]
trailing = original[-trailing_size:] if trailing_size else ""
return f"{leading}{content}{trailing}"
@dataclass(slots=True)
class AgentRunSpec:
"""Configuration for a single agent execution."""
@@ -105,16 +73,15 @@ class AgentRunSpec:
session_key: str | None = None
context_block_limit: int | None = None
provider_retry_mode: str = "standard"
progress_callback: ProgressCallback | None = None
progress_callback: Any | None = None
stream_progress_deltas: bool = True
retry_wait_callback: RetryWaitCallback | None = None
checkpoint_callback: CheckpointCallback | None = None
injection_callback: InjectionCallback | None = None
retry_wait_callback: Any | None = None
checkpoint_callback: Any | None = None
injection_callback: Any | None = None
llm_timeout_s: float | None = None
goal_active_predicate: Callable[[], bool] | None = None
goal_continue_message: GoalContinueMessage | None = None
finalize_on_max_iterations: bool = True
provider_state: ProviderConversationState | None = None
@dataclass(slots=True)
@@ -129,9 +96,6 @@ class AgentRunResult:
error: str | None = None
tool_events: list[dict[str, str]] = field(default_factory=list)
had_injections: bool = False
# Terminal tail to emit when the preceding final-content prefix was already streamed.
pending_stream_content: str | None = None
provider_state: ProviderConversationState | None = field(default=None, repr=False)
class AgentRunner:
@@ -148,10 +112,8 @@ class AgentRunner:
def _to_blocks(value: Any) -> list[dict[str, Any]]:
if isinstance(value, list):
return [
cast(dict[str, Any], item)
if isinstance(item, dict)
else {"type": "text", "text": str(item)}
for item in cast(list[Any], value)
item if isinstance(item, dict) else {"type": "text", "text": str(item)}
for item in value
]
if value is None:
return []
@@ -173,66 +135,12 @@ class AgentRunner:
and messages[-1].get("role") == "user"
and not is_hidden_history_message(injection)
and not is_hidden_history_message(messages[-1])
and allows_conversation_message_merge(messages[-1])
):
merged = dict(messages[-1])
left_meta = merged.get("_meta")
right_meta = injection.get("_meta")
left_meta_dict = cast(dict[str, Any], left_meta) if isinstance(left_meta, dict) else None
right_meta_dict = (
cast(dict[str, Any], right_meta) if isinstance(right_meta, dict) else None
merged["content"] = cls._merge_message_content(
merged.get("content"),
injection.get("content"),
)
left_marker = (
left_meta_dict.get(RUNTIME_CONTEXT_MESSAGE_META)
if left_meta_dict is not None
else None
)
right_marker = (
right_meta_dict.get(RUNTIME_CONTEXT_MESSAGE_META)
if right_meta_dict is not None
else None
)
left_marker_dict = (
cast(dict[str, Any], left_marker) if isinstance(left_marker, dict) else None
)
right_marker_dict = (
cast(dict[str, Any], right_marker) if isinstance(right_marker, dict) else None
)
empty_sources: list[str] = []
empty_blocks: list[dict[str, Any]] = []
detached_left = (
detach_runtime_context(merged.get("content"), left_marker_dict)
if left_marker_dict is not None
else (merged.get("content"), empty_sources, empty_blocks)
)
detached_right = (
detach_runtime_context(injection.get("content"), right_marker_dict)
if right_marker_dict is not None
else (injection.get("content"), empty_sources, empty_blocks)
)
if detached_left is not None and detached_right is not None:
left_content, left_sources, left_blocks = detached_left
right_content, right_sources, right_blocks = detached_right
merged_content = cls._merge_message_content(left_content, right_content)
context_blocks = [*left_blocks, *right_blocks]
if context_blocks:
merged_content, marker = reattach_runtime_context(
merged_content,
[*left_sources, *right_sources],
context_blocks,
)
internal_meta = dict(left_meta_dict) if left_meta_dict is not None else {}
if right_meta_dict is not None:
for key, value in right_meta_dict.items():
internal_meta.setdefault(key, value)
internal_meta[RUNTIME_CONTEXT_MESSAGE_META] = marker
merged["_meta"] = internal_meta
merged["content"] = merged_content
else:
merged["content"] = cls._merge_message_content(
merged.get("content"),
injection.get("content"),
)
messages[-1] = merged
continue
messages.append(injection)
@@ -244,7 +152,6 @@ class AgentRunner:
assistant_message: dict[str, Any] | None,
injection_cycles: int,
*,
conversation_state: ProviderConversationStateController | None = None,
phase: str = "after error",
iteration: int | None = None,
allow_goal_continue: bool = False,
@@ -272,21 +179,16 @@ class AgentRunner:
if assistant_message is not None:
messages.append(assistant_message)
if iteration is not None:
checkpoint: dict[str, Any] = {
"phase": "final_response",
"iteration": iteration,
"model": spec.runtime.model,
"assistant_message": assistant_message,
"completed_tool_results": [],
"pending_tool_calls": [],
}
if conversation_state is not None:
checkpoint["provider_state"] = conversation_state.checkpoint(
messages
)
await self._emit_checkpoint(
spec,
checkpoint,
{
"phase": "final_response",
"iteration": iteration,
"model": spec.runtime.model,
"assistant_message": assistant_message,
"completed_tool_results": [],
"pending_tool_calls": [],
},
)
self._append_injected_messages(messages, injections)
if real_injection:
@@ -340,11 +242,11 @@ class AgentRunner:
for item in items:
if item is None:
continue
if isinstance(item, dict) and item.get("role") == "user" and "content" in item:
if self._has_injection_content(item.get("content")):
injected_messages.append(item)
continue
if isinstance(item, dict):
message_item = cast(dict[str, Any], item)
if message_item.get("role") == "user" and "content" in message_item:
if self._has_injection_content(message_item.get("content")):
injected_messages.append(message_item)
continue
content = getattr(item, "content") if hasattr(item, "content") else str(item)
if self._has_injection_content(content):
@@ -365,7 +267,7 @@ class AgentRunner:
if isinstance(content, str):
return bool(content.strip())
if isinstance(content, list):
return bool(cast(list[Any], content))
return bool(content)
return True
async def run(self, spec: AgentRunSpec) -> AgentRunResult:
@@ -432,19 +334,10 @@ class AgentRunner:
# Per-turn throttle for repeated attempts against the same outside target.
workspace_violation_counts: dict[str, int] = {}
empty_content_retries = 0
# Segments from one uninterrupted length-recovery chain. Tool work or
# injected user input starts a new logical answer and clears the chain.
length_recovery_parts: list[str] = []
length_recovery_count = 0
had_injections = False
injection_cycles = 0
compacted_tool_call_ids: set[str] = set()
pending_stream_content: str | None = None
conversation_state = ProviderConversationStateController(
provider=spec.runtime.provider,
model=spec.runtime.model,
messages=messages,
state=spec.provider_state,
)
governance_config = ContextGovernanceConfig(
provider=spec.runtime.provider,
model=spec.runtime.model,
@@ -475,24 +368,10 @@ class AgentRunner:
session_key=spec.session_key,
)
await hook.before_iteration(context)
provider_context = conversation_state.prepare_request(
messages,
context_window_tokens=spec.runtime.context_window_tokens,
model_messages=messages_for_model,
)
response = await self._request_model(
spec,
messages_for_model,
hook,
context,
conversation_state=conversation_state,
provider_context=provider_context,
)
conversation_state.observe_response(response, messages)
response = await self._request_model(spec, messages_for_model, hook, context)
context.response = response
context.tool_calls = list(response.tool_calls)
original_content = response.content
reasoning_text, cleaned_content = extract_reasoning(
response.reasoning_content,
response.thinking_blocks,
@@ -518,10 +397,6 @@ class AgentRunner:
reasoning_content=response.reasoning_content,
thinking_blocks=response.thinking_blocks,
)
assistant_message = conversation_state.project_response_message(
assistant_message,
response,
)
messages.append(assistant_message)
await self._emit_checkpoint(
spec,
@@ -583,18 +458,8 @@ class AgentRunner:
)
if should_continue:
had_injections = True
length_recovery_parts.clear()
continue
break
checkpoint_model_messages = (
self.context_governor.prepare_for_model(
governance_config,
messages,
compacted_tool_call_ids,
)
if response.provider_state is not None
else None
)
await self._emit_checkpoint(
spec,
{
@@ -604,14 +469,10 @@ class AgentRunner:
"assistant_message": assistant_message,
"completed_tool_results": completed_tool_results,
"pending_tool_calls": [],
"provider_state": conversation_state.checkpoint(
messages,
model_messages=checkpoint_model_messages,
),
},
)
empty_content_retries = 0
length_recovery_parts.clear()
length_recovery_count = 0
# Checkpoint 1: drain injections after tools, before next LLM call
_drained, injection_cycles = await self._try_drain_injections(
spec, messages, None, injection_cycles,
@@ -630,11 +491,7 @@ class AgentRunner:
)
clean = hook.finalize_content(context, response.content)
if (
response.finish_reason
not in {"error", "length", "refusal", "content_filter"}
and is_blank_text(clean)
):
if response.finish_reason != "error" and is_blank_text(clean):
empty_content_retries += 1
if empty_content_retries < _MAX_EMPTY_RETRIES:
logger.warning(
@@ -657,65 +514,36 @@ class AgentRunner:
if hook.wants_streaming():
await hook.on_stream_end(context, resuming=False)
retry_messages = self._finalization_retry_messages(messages_for_model)
response = await self._request_finalization_retry(
spec,
messages_for_model,
transcript=messages,
conversation_state=conversation_state,
)
response = await self._request_finalization_retry(spec, messages_for_model)
retry_usage = self._usage_or_estimate(spec, retry_messages, response)
self._accumulate_usage(usage, retry_usage)
raw_usage = self._merge_usage(raw_usage, retry_usage)
context.response = response
context.usage = dict(raw_usage)
context.tool_calls = list(response.tool_calls)
original_content = response.content
clean = hook.finalize_content(context, response.content)
if response.finish_reason == "length":
if len(length_recovery_parts) < _MAX_LENGTH_RECOVERIES:
length_recovery_parts.append(
_restore_outer_whitespace(clean or "", original_content)
)
if response.finish_reason == "length" and not is_blank_text(clean):
length_recovery_count += 1
if length_recovery_count <= _MAX_LENGTH_RECOVERIES:
logger.info(
"Output truncated on turn {} for {} ({}/{}); continuing",
iteration,
spec.session_key or "default",
len(length_recovery_parts),
length_recovery_count,
_MAX_LENGTH_RECOVERIES,
)
if hook.wants_streaming():
context.stream_continues_current_message = True
await hook.on_stream_end(context, resuming=True)
messages.append(conversation_state.project_response_message(
build_assistant_message(
clean,
reasoning_content=response.reasoning_content,
thinking_blocks=response.thinking_blocks,
),
response,
messages.append(build_assistant_message(
clean,
reasoning_content=response.reasoning_content,
thinking_blocks=response.thinking_blocks,
))
messages.append(build_length_recovery_message(clean or ""))
messages.append(build_length_recovery_message())
await hook.after_iteration(context)
continue
# Some streaming providers recover with a complete response but no
# content deltas. When an earlier length segment is already visible,
# emit this terminal segment into the same stream; otherwise the
# regular full response would duplicate the visible prefix.
if (
length_recovery_parts
and hook.wants_streaming()
and not context.streamed_content
and response.finish_reason != "error"
and not is_blank_text(clean)
):
await hook.on_stream(
context,
_restore_outer_whitespace(clean or "", original_content),
)
context.streamed_content = True
assistant_message: dict[str, Any] | None = None
if response.finish_reason != "error" and not is_blank_text(clean):
assistant_message = build_assistant_message(
@@ -723,22 +551,15 @@ class AgentRunner:
reasoning_content=response.reasoning_content,
thinking_blocks=response.thinking_blocks,
)
assistant_message = conversation_state.project_response_message(
assistant_message,
response,
)
# Check for mid-turn injections BEFORE signaling stream end.
# If injections are found we keep the stream alive (resuming=True)
# so streaming channels don't prematurely finalize the card.
should_continue, injection_cycles = await self._try_drain_injections(
spec, messages, assistant_message, injection_cycles,
conversation_state=conversation_state,
phase="after final response",
iteration=iteration,
allow_goal_continue=(
response.finish_reason not in {"refusal", "content_filter"}
),
allow_goal_continue=True,
)
if should_continue:
had_injections = True
@@ -747,7 +568,6 @@ class AgentRunner:
await hook.on_stream_end(context, resuming=should_continue)
if should_continue:
length_recovery_parts.clear()
await hook.after_iteration(context)
continue
@@ -769,7 +589,6 @@ class AgentRunner:
)
if should_continue:
had_injections = True
length_recovery_parts.clear()
continue
break
if is_blank_text(clean):
@@ -787,21 +606,14 @@ class AgentRunner:
)
if should_continue:
had_injections = True
length_recovery_parts.clear()
continue
break
messages.append(
assistant_message
or conversation_state.project_response_message(
build_assistant_message(
clean,
reasoning_content=response.reasoning_content,
thinking_blocks=response.thinking_blocks,
),
response,
)
)
messages.append(assistant_message or build_assistant_message(
clean,
reasoning_content=response.reasoning_content,
thinking_blocks=response.thinking_blocks,
))
await self._emit_checkpoint(
spec,
{
@@ -811,16 +623,9 @@ class AgentRunner:
"assistant_message": messages[-1],
"completed_tool_results": [],
"pending_tool_calls": [],
"provider_state": conversation_state.checkpoint(messages),
},
)
if length_recovery_parts:
final_content = (
"".join(length_recovery_parts)
+ _restore_outer_whitespace(clean or "", original_content)
).strip()
else:
final_content = clean
final_content = clean
context.final_content = final_content
context.stop_reason = stop_reason
await hook.after_iteration(context)
@@ -838,26 +643,17 @@ class AgentRunner:
)
if drained_after_max_iterations:
had_injections = True
terminal_content = None
final_content = None
if spec.finalize_on_max_iterations:
terminal_content = await self._try_finalize_after_max_iterations(
final_content = await self._try_finalize_after_max_iterations(
spec,
hook,
messages,
usage,
conversation_state,
)
if terminal_content is None:
terminal_content = self._max_iterations_fallback(spec)
if length_recovery_parts:
terminal_tail = f"\n\n{terminal_content.lstrip()}"
final_content = (
"".join(length_recovery_parts).rstrip() + terminal_tail
).strip()
pending_stream_content = terminal_tail
else:
final_content = terminal_content
self._append_final_message(messages, terminal_content)
if final_content is None:
final_content = self._max_iterations_fallback(spec)
self._append_final_message(messages, final_content)
return AgentRunResult(
final_content=final_content,
@@ -868,8 +664,6 @@ class AgentRunner:
error=error,
tool_events=tool_events,
had_injections=had_injections,
pending_stream_content=pending_stream_content,
provider_state=conversation_state.finish(messages),
)
def _build_request_kwargs(
@@ -900,9 +694,7 @@ class AgentRunner:
context: AgentHookContext,
*,
malformed_retry: bool = False,
conversation_state: ProviderConversationStateController,
provider_context: ProviderCallContext | None = None,
) -> LLMResponse:
):
timeout_s: float | None = spec.llm_timeout_s
if timeout_s is None:
# Default to a finite timeout to avoid per-session lock starvation when an LLM
@@ -913,7 +705,7 @@ class AgentRunner:
timeout_s = float(raw)
except (TypeError, ValueError):
timeout_s = 300.0
if timeout_s <= 0:
if timeout_s is not None and timeout_s <= 0:
timeout_s = None
kwargs = self._build_request_kwargs(
@@ -922,11 +714,10 @@ class AgentRunner:
tools=spec.tools.get_definitions(),
)
wants_streaming = hook.wants_streaming()
progress_callback = spec.progress_callback
wants_progress_streaming = (
not wants_streaming
and spec.stream_progress_deltas
and progress_callback is not None
and spec.progress_callback is not None
and getattr(spec.runtime.provider, "supports_progress_deltas", False) is True
)
@@ -971,7 +762,6 @@ class AgentRunner:
coro = spec.runtime.provider.chat_stream_with_retry(
**kwargs,
provider_context=provider_context,
on_content_delta=_stream,
on_thinking_delta=_thinking,
on_tool_call_delta=_provider_tool_event,
@@ -1000,21 +790,15 @@ class AgentRunner:
await hook.emit_reasoning_end()
progress_state["reasoning_open"] = False
context.streamed_content = True
callback = progress_callback
if callback is not None:
await callback(incremental)
await spec.progress_callback(incremental)
coro = spec.runtime.provider.chat_stream_with_retry(
**kwargs,
provider_context=provider_context,
on_content_delta=_stream_progress,
on_tool_call_delta=_provider_tool_event,
)
else:
coro = spec.runtime.provider.chat_with_retry(
**kwargs,
provider_context=provider_context,
)
coro = spec.runtime.provider.chat_with_retry(**kwargs)
# Streaming requests also have provider-level idle timeouts
# (NANOBOT_STREAM_IDLE_TIMEOUT_S), but a stream that keeps producing
@@ -1076,10 +860,6 @@ class AgentRunner:
return await self._request_model(
spec, retry_messages, hook, context,
malformed_retry=True,
conversation_state=conversation_state,
provider_context=conversation_state.independent_request_context(
context_window_tokens=spec.runtime.context_window_tokens,
),
)
if (
all_dropped
@@ -1092,13 +872,7 @@ class AgentRunner:
fallback_messages = self._malformed_tool_call_retry_messages(
messages, response.content,
)
return await self._request_no_tools(
spec,
fallback_messages,
provider_context=conversation_state.independent_request_context(
context_window_tokens=spec.runtime.context_window_tokens,
),
)
return await self._request_no_tools(spec, fallback_messages)
return response
@staticmethod
@@ -1131,10 +905,6 @@ class AgentRunner:
original_finish_reason,
)
response.tool_calls = valid
# The opaque candidate still contains every raw function_call item.
# Advancing it after dropping even one call would replay an unmatched
# call without a corresponding tool output on the next request.
response.provider_state = None
if not valid:
response.finish_reason = "stop"
return (dropped, not valid, original_finish_reason)
@@ -1164,27 +934,9 @@ class AgentRunner:
self,
spec: AgentRunSpec,
messages: list[dict[str, Any]],
*,
transcript: list[dict[str, Any]],
conversation_state: ProviderConversationStateController,
) -> LLMResponse:
):
retry_messages = self._finalization_retry_messages(messages)
provider_context = conversation_state.prepare_request(
transcript,
context_window_tokens=spec.runtime.context_window_tokens,
supplemental_messages=[retry_messages[-1]],
)
response = await self._request_no_tools(
spec,
retry_messages,
provider_context=provider_context,
)
conversation_state.observe_response(
response,
transcript,
adopt_candidate_state=False,
)
return response
return await self._request_no_tools(spec, retry_messages)
@staticmethod
def _finalization_retry_messages(messages: list[dict[str, Any]]) -> list[dict[str, Any]]:
@@ -1198,17 +950,10 @@ class AgentRunner:
hook: AgentHook,
messages: list[dict[str, Any]],
usage: dict[str, int],
conversation_state: ProviderConversationStateController,
) -> str | None:
retry_messages = self._budget_exhausted_finalization_messages(messages)
try:
response = await self._request_no_tools(
spec,
retry_messages,
provider_context=conversation_state.independent_request_context(
context_window_tokens=spec.runtime.context_window_tokens,
),
)
response = await self._request_no_tools(spec, retry_messages)
except Exception:
logger.exception(
"Budget-exhausted finalization failed for {}; using fallback",
@@ -1244,18 +989,9 @@ class AgentRunner:
self,
spec: AgentRunSpec,
messages: list[dict[str, Any]],
*,
provider_context: ProviderCallContext | None = None,
) -> LLMResponse:
kwargs = self._build_request_kwargs(
spec,
messages,
tools=None,
)
return await spec.runtime.provider.chat_with_retry(
**kwargs,
provider_context=provider_context,
)
kwargs = self._build_request_kwargs(spec, messages, tools=None)
return await spec.runtime.provider.chat_with_retry(**kwargs)
@staticmethod
def _budget_exhausted_finalization_messages(
@@ -1384,7 +1120,7 @@ class AgentRunner:
))
tool_results.extend(batch_results)
else:
batch_results: list[tuple[Any, dict[str, str], BaseException | None]] = []
batch_results = []
for tool_call in batch:
result = await self._run_tool(
spec,
@@ -1433,17 +1169,12 @@ class AgentRunner:
if spec.fail_on_tool_error:
return lookup_error + hint, event, RuntimeError(lookup_error)
return lookup_error + hint, event, None
prepare_call = cast(
Callable[[str, Any], object] | None,
getattr(spec.tools, "prepare_call", None),
)
prepare_call = getattr(spec.tools, "prepare_call", None)
tool, params, prep_error = None, tool_call.arguments, None
if callable(prepare_call):
prepared = prepare_call(tool_call.name, tool_call.arguments)
if isinstance(prepared, tuple):
prepared_tuple = cast(tuple[object, ...], prepared)
if len(prepared_tuple) == 3:
tool, params, prep_error = cast(tuple[Any, Any, str | None], prepared_tuple)
if isinstance(prepared, tuple) and len(prepared) == 3:
tool, params, prep_error = prepared
if prep_error:
event = {
"name": tool_call.name,
@@ -1492,7 +1223,7 @@ class AgentRunner:
return payload, event, exc
return payload, event, None
if is_tool_error_result(result):
if is_tool_error_result(tool_call.name, result):
await hook.on_execute_tool_error(context, tool_call, tool, params, result)
event = {
"name": tool_call.name,
@@ -1655,7 +1386,7 @@ class AgentRunner:
batches: list[list[ToolCallRequest]] = []
current: list[ToolCallRequest] = []
for tool_call in tool_calls:
get_tool = cast(Callable[[str], Any] | None, getattr(spec.tools, "get", None))
get_tool = getattr(spec.tools, "get", None)
tool = get_tool(tool_call.name) if callable(get_tool) else None
can_batch = bool(tool and tool.concurrency_safe)
if can_batch:
+22 -47
View File
@@ -5,7 +5,6 @@ import os
import re
import shutil
from pathlib import Path
from typing import Any, cast
import yaml
@@ -17,7 +16,6 @@ _STRIP_SKILL_FRONTMATTER = re.compile(
r"^---\s*\r?\n(.*?)\r?\n---\s*\r?\n?",
re.DOTALL,
)
_SKILL_REFERENCE = re.compile(r"(?<![\w$])\$([A-Za-z0-9_-]+)")
class SkillsLoader:
@@ -110,21 +108,6 @@ class SkillsLoader:
]
return "\n\n---\n\n".join(parts)
def get_explicitly_invoked_skills(self, text: str) -> list[str]:
"""Resolve ``$skill-name`` references to enabled, available skills."""
if not text:
return []
available = {
entry["name"]
for entry in self.list_skills(filter_unavailable=True)
}
invoked: list[str] = []
for match in _SKILL_REFERENCE.finditer(text):
name = match.group(1)
if name in available and name not in invoked:
invoked.append(name)
return invoked
def build_skills_summary(self, exclude: set[str] | None = None) -> str:
"""
Build a summary of all skills (name, description, path, availability).
@@ -161,7 +144,7 @@ class SkillsLoader:
skill_name = entry["name"]
meta = self._get_skill_meta(skill_name)
available = self._check_requirements(meta)
desc = self.get_skill_description(skill_name)
desc = self._get_skill_description(skill_name)
suffix = ""
if not available:
missing = self._get_missing_requirements(meta)
@@ -171,21 +154,11 @@ class SkillsLoader:
sections.append("\n".join(lines))
return "\n\n".join(sections)
@staticmethod
def _requirement_lists(skill_meta: dict[str, Any]) -> tuple[list[str], list[str]]:
"""Return (bins, env) lists from skill metadata, tolerating null/wrong shapes."""
requires = cast(dict[str, Any], skill_meta.get("requires") or {})
if not isinstance(skill_meta.get("requires") or {}, dict):
return [], []
bins_raw: object = requires.get("bins") or []
env_raw: object = requires.get("env") or []
bins = [value for value in cast(list[object], bins_raw) if isinstance(value, str) and value.strip()] if isinstance(bins_raw, list) else []
env = [value for value in cast(list[object], env_raw) if isinstance(value, str) and value.strip()] if isinstance(env_raw, list) else []
return bins, env
def _get_missing_requirements(self, skill_meta: dict[str, Any]) -> str:
def _get_missing_requirements(self, skill_meta: dict) -> str:
"""Get a description of missing requirements."""
required_bins, required_env_vars = self._requirement_lists(skill_meta)
requires = skill_meta.get("requires", {})
required_bins = requires.get("bins", [])
required_env_vars = requires.get("env", [])
return ", ".join(
[f"CLI: {command_name}" for command_name in required_bins if not shutil.which(command_name)]
+ [f"ENV: {env_name}" for env_name in required_env_vars if not os.environ.get(env_name)]
@@ -199,7 +172,9 @@ class SkillsLoader:
def get_skill_requirements(self, name: str) -> dict[str, list[str]]:
"""Return explicit command/env requirements and currently missing entries."""
bins, env = self._requirement_lists(self._get_skill_meta(name))
requires = self._get_skill_meta(name).get("requires", {})
bins = [str(value) for value in requires.get("bins", [])]
env = [str(value) for value in requires.get("env", [])]
return {
"bins": bins,
"env": env,
@@ -207,12 +182,11 @@ class SkillsLoader:
"missing_env": [value for value in env if not os.environ.get(value)],
}
def get_skill_description(self, name: str) -> str:
def _get_skill_description(self, name: str) -> str:
"""Get the description of a skill from its frontmatter."""
meta = self.get_skill_metadata(name)
description = meta.get("description") if meta else None
if isinstance(description, str) and description:
return description
if meta and meta.get("description"):
return meta["description"]
return name # Fallback to skill name
def _strip_frontmatter(self, content: str) -> str:
@@ -224,13 +198,13 @@ class SkillsLoader:
return content[match.end():].strip()
return content
def _parse_nanobot_metadata(self, raw: object) -> dict[str, Any]:
def _parse_nanobot_metadata(self, raw: object) -> dict:
"""Extract nanobot/openclaw metadata from a frontmatter field.
``raw`` may be a dict (already parsed by yaml.safe_load) or a JSON str.
"""
if isinstance(raw, dict):
data = cast(dict[str, Any], raw)
data = raw
elif isinstance(raw, str):
try:
data = json.loads(raw)
@@ -240,18 +214,19 @@ class SkillsLoader:
return {}
if not isinstance(data, dict):
return {}
data_object = cast(dict[str, Any], data)
payload = data_object.get("nanobot", data_object.get("openclaw", {}))
return cast(dict[str, Any], payload) if isinstance(payload, dict) else {}
payload = data.get("nanobot", data.get("openclaw", {}))
return payload if isinstance(payload, dict) else {}
def _check_requirements(self, skill_meta: dict[str, Any]) -> bool:
def _check_requirements(self, skill_meta: dict) -> bool:
"""Check if skill requirements are met (bins, env vars)."""
required_bins, required_env_vars = self._requirement_lists(skill_meta)
requires = skill_meta.get("requires", {})
required_bins = requires.get("bins", [])
required_env_vars = requires.get("env", [])
return all(shutil.which(cmd) for cmd in required_bins) and all(
os.environ.get(var) for var in required_env_vars
)
def _get_skill_meta(self, name: str) -> dict[str, Any]:
def _get_skill_meta(self, name: str) -> dict:
"""Get nanobot metadata for a skill (cached in frontmatter)."""
raw_meta = self.get_skill_metadata(name) or {}
return self._parse_nanobot_metadata(raw_meta.get("metadata"))
@@ -268,7 +243,7 @@ class SkillsLoader:
)
]
def get_skill_metadata(self, name: str) -> dict[str, object] | None:
def get_skill_metadata(self, name: str) -> dict | None:
"""
Get metadata from a skill's frontmatter.
@@ -293,6 +268,6 @@ class SkillsLoader:
# yaml.safe_load returns native types (int, bool, list, etc.);
# keep values as-is so downstream consumers get correct types.
metadata: dict[str, object] = {}
for key, value in cast(dict[object, object], parsed).items():
for key, value in parsed.items():
metadata[str(key)] = value
return metadata
+11 -21
View File
@@ -7,12 +7,12 @@ import uuid
import warnings
from dataclasses import dataclass, field
from pathlib import Path
from typing import Any, Callable, TypedDict
from typing import Any, Callable
from loguru import logger
from nanobot.agent.hook import AgentHook, AgentHookContext
from nanobot.agent.runner import AgentRunner, AgentRunResult, AgentRunSpec
from nanobot.agent.runner import AgentRunner, AgentRunSpec
from nanobot.agent.tools.base import ToolResult
from nanobot.agent.tools.context import (
RequestContext,
@@ -38,12 +38,6 @@ from nanobot.utils.llm_runtime import LLMRuntime
from nanobot.utils.prompt_templates import render_template
class _SubagentOrigin(TypedDict):
channel: str
chat_id: str
session_key: str | None
@dataclass(slots=True)
class SubagentStatus:
"""Real-time status of a running subagent."""
@@ -54,8 +48,8 @@ class SubagentStatus:
started_at: float # time.monotonic()
phase: str = "initializing" # initializing | awaiting_tools | tools_completed | final_response | done | error
iteration: int = 0
tool_events: list[dict[str, str]] = field(default_factory=list)
usage: dict[str, int] = field(default_factory=dict)
tool_events: list = field(default_factory=list) # [{name, status, detail}, ...]
usage: dict = field(default_factory=dict) # token usage
stop_reason: str | None = None
error: str | None = None
@@ -243,11 +237,7 @@ class SubagentManager:
runtime = runtime.with_generation_overrides(temperature=temperature)
task_id = str(uuid.uuid4())[:8]
display_label = label or task[:30] + ("..." if len(task) > 30 else "")
origin: _SubagentOrigin = {
"channel": origin_channel,
"chat_id": origin_chat_id,
"session_key": session_key,
}
origin = {"channel": origin_channel, "chat_id": origin_chat_id, "session_key": session_key}
status = SubagentStatus(
task_id=task_id,
@@ -273,7 +263,7 @@ class SubagentManager:
if session_key:
self._session_tasks.setdefault(session_key, set()).add(task_id)
def _cleanup(_: asyncio.Task[str]) -> None:
def _cleanup(_: asyncio.Task) -> None:
self._running_tasks.pop(task_id, None)
self._task_statuses.pop(task_id, None)
if session_key and (ids := self._session_tasks.get(session_key)):
@@ -306,7 +296,7 @@ class SubagentManager:
runtime = runtime.with_generation_overrides(temperature=temperature)
task_id = str(uuid.uuid4())[:8]
display_label = label or task[:30] + ("..." if len(task) > 30 else "")
origin: _SubagentOrigin = {
origin = {
"channel": origin_channel,
"chat_id": origin_chat_id,
"session_key": session_key,
@@ -353,7 +343,7 @@ class SubagentManager:
task_id: str,
task: str,
label: str,
origin: _SubagentOrigin,
origin: dict[str, str],
status: SubagentStatus,
runtime: LLMRuntime,
origin_message_id: str | None = None,
@@ -364,7 +354,7 @@ class SubagentManager:
"""Execute the subagent task and announce the result."""
logger.info("Subagent [{}] starting task: {}", task_id, label)
async def _on_checkpoint(payload: dict[str, Any]) -> None:
async def _on_checkpoint(payload: dict) -> None:
status.phase = payload.get("phase", status.phase)
status.iteration = payload.get("iteration", status.iteration)
@@ -466,7 +456,7 @@ class SubagentManager:
label: str,
task: str,
result: str,
origin: _SubagentOrigin,
origin: dict[str, str],
status: str,
origin_message_id: str | None = None,
) -> None:
@@ -506,7 +496,7 @@ class SubagentManager:
logger.debug("Subagent [{}] announced result to {}:{}", task_id, origin['channel'], origin['chat_id'])
@staticmethod
def _format_partial_progress(result: AgentRunResult) -> str:
def _format_partial_progress(result) -> str:
completed = [e for e in result.tool_events if e["status"] == "ok"]
failure = next((e for e in reversed(result.tool_events) if e["status"] == "error"), None)
lines: list[str] = []
+11 -9
View File
@@ -5,10 +5,10 @@ from __future__ import annotations
import difflib
from dataclasses import dataclass
from pathlib import Path
from typing import Any, cast
from typing import Any
from nanobot.agent.tools.base import ToolResult, tool_parameters
from nanobot.agent.tools.filesystem import _FsTool # pyright: ignore[reportPrivateUsage]
from nanobot.agent.tools.filesystem import _FsTool
from nanobot.agent.tools.schema import (
ArraySchema,
BooleanSchema,
@@ -39,6 +39,12 @@ def _validate_patch_path(path: str) -> str:
return normalized
def _lines_to_text(lines: list[str]) -> str:
if not lines:
return ""
return "\n".join(lines) + "\n"
def _text_line_count(text: str) -> int:
if not text:
return 0
@@ -134,7 +140,7 @@ class ApplyPatchTool(_FsTool):
async def execute(
self,
edits: list[object] | None = None,
edits: list[dict] | None = None,
dry_run: bool = False,
**kwargs: Any,
) -> str:
@@ -145,10 +151,9 @@ class ApplyPatchTool(_FsTool):
writes: dict[Path, str] = {}
summaries: list[_PatchSummary] = []
for edit_value in edits:
if not isinstance(edit_value, dict):
for edit in edits:
if not isinstance(edit, dict):
raise _PatchError("each edit must be an object")
edit = cast(dict[str, Any], edit_value)
raw_path = edit.get("path")
if not isinstance(raw_path, str):
raise _PatchError("path required for edit")
@@ -162,7 +167,6 @@ class ApplyPatchTool(_FsTool):
new_text = edit.get("new_text")
if new_text is None:
raise _PatchError(f"new_text required for add: {path}")
new_text = cast(str, new_text)
pending = writes.get(source)
if pending is not None:
@@ -206,11 +210,9 @@ class ApplyPatchTool(_FsTool):
old_text = edit.get("old_text") or ""
if not old_text:
raise _PatchError(f"old_text required for replace: {path}")
old_text = cast(str, old_text)
new_text = edit.get("new_text")
if new_text is None:
raise _PatchError(f"new_text required for replace: {path}")
new_text = cast(str, new_text)
pending = writes.get(source)
if pending is not None:
+20 -31
View File
@@ -5,7 +5,7 @@ import typing
from abc import ABC, abstractmethod
from collections.abc import Callable
from copy import deepcopy
from typing import Any, TypeVar, cast
from typing import Any, TypeVar
if typing.TYPE_CHECKING:
from pydantic import BaseModel
@@ -38,9 +38,8 @@ class Schema(ABC):
def resolve_json_schema_type(t: Any) -> str | None:
"""Resolve the non-null type name from JSON Schema ``type`` (e.g. ``['string','null']`` -> ``'string'``)."""
if isinstance(t, list):
types = cast(list[Any], t)
return cast(str | None, next((x for x in types if x != "null"), None))
return cast(str | None, t)
return next((x for x in t if x != "null"), None)
return t # type: ignore[return-value]
@staticmethod
def subpath(path: str, key: str) -> str:
@@ -77,41 +76,33 @@ class Schema(ABC):
if "maximum" in schema and val > schema["maximum"]:
errors.append(f"{label} must be <= {schema['maximum']}")
if t == "string":
string_value = cast(str, val)
if "minLength" in schema and len(string_value) < schema["minLength"]:
if "minLength" in schema and len(val) < schema["minLength"]:
errors.append(f"{label} must be at least {schema['minLength']} chars")
if "maxLength" in schema and len(string_value) > schema["maxLength"]:
if "maxLength" in schema and len(val) > schema["maxLength"]:
errors.append(f"{label} must be at most {schema['maxLength']} chars")
if t == "object":
object_value = cast(dict[str, Any], val)
props = cast(dict[str, Any], schema.get("properties", {}))
required = cast(list[Any], schema.get("required", []))
for k in required:
if k not in object_value:
props = schema.get("properties", {})
for k in schema.get("required", []):
if k not in val:
errors.append(f"missing required {Schema.subpath(path, k)}")
additional = schema.get("additionalProperties", True)
for k, v in object_value.items():
for k, v in val.items():
if k in props:
errors.extend(Schema.validate_json_schema_value(v, props[k], Schema.subpath(path, k)))
elif additional is False:
errors.append(f"unexpected parameter {Schema.subpath(path, k)}")
elif isinstance(additional, dict):
errors.extend(
Schema.validate_json_schema_value(
v,
cast(dict[str, Any], additional),
Schema.subpath(path, k),
)
Schema.validate_json_schema_value(v, additional, Schema.subpath(path, k))
)
if t == "array":
array_value = cast(list[Any], val)
if "minItems" in schema and len(array_value) < schema["minItems"]:
if "minItems" in schema and len(val) < schema["minItems"]:
errors.append(f"{label} must have at least {schema['minItems']} items")
if "maxItems" in schema and len(array_value) > schema["maxItems"]:
if "maxItems" in schema and len(val) > schema["maxItems"]:
errors.append(f"{label} must be at most {schema['maxItems']} items")
if "items" in schema:
prefix = f"{path}[{{}}]" if path else "[{}]"
for i, item in enumerate(array_value):
for i, item in enumerate(val):
errors.extend(
Schema.validate_json_schema_value(item, schema["items"], prefix.format(i))
)
@@ -123,9 +114,9 @@ class Schema(ABC):
# Try to_json_schema first: Schema instances must be distinguished from dicts that are already JSON Schema
to_js = getattr(value, "to_json_schema", None)
if callable(to_js):
return cast(dict[str, Any], to_js())
return to_js()
if isinstance(value, dict):
return cast(dict[str, Any], value)
return value
raise TypeError(f"Expected schema object or dict, got {type(value).__name__}")
@abstractmethod
@@ -232,15 +223,14 @@ class Tool(ABC):
def _cast_object(self, obj: Any, schema: dict[str, Any]) -> dict[str, Any]:
if not isinstance(obj, dict):
return obj
props = cast(dict[str, Any], schema.get("properties", {}))
props = schema.get("properties", {})
additional = schema.get("additionalProperties")
casted: dict[str, Any] = {}
object_value = cast(dict[str, Any], obj)
for k, v in object_value.items():
for k, v in obj.items():
if k in props:
casted[k] = self._cast_value(v, props[k])
elif isinstance(additional, dict):
casted[k] = self._cast_value(v, cast(dict[str, Any], additional))
casted[k] = self._cast_value(v, additional)
else:
casted[k] = v
return casted
@@ -283,8 +273,7 @@ class Tool(ABC):
if t == "array" and isinstance(val, list):
items = schema.get("items")
array_value = cast(list[Any], val)
return [self._cast_value(x, items) for x in array_value] if items else array_value
return [self._cast_value(x, items) for x in val] if items else val
if t == "object" and isinstance(val, dict):
return self._cast_object(val, schema)
@@ -293,7 +282,7 @@ class Tool(ABC):
def validate_params(self, params: dict[str, Any]) -> list[str]:
"""Validate against JSON schema; empty list means valid."""
if not isinstance(cast(object, params), dict):
if not isinstance(params, dict):
return [f"parameters must be an object, got {type(params).__name__}"]
schema = self.parameters or {}
if schema.get("type", "object") != "object":
+4 -5
View File
@@ -1,15 +1,14 @@
"""Controlled runner for installed CLI Apps."""
# pyright: reportIncompatibleMethodOverride=false
from __future__ import annotations
from pathlib import Path
from typing import Any
from pydantic import Field
from nanobot.agent.tools.base import Tool, ToolResult, tool_parameters
from nanobot.agent.tools.context import RequestContext, ToolContext
from nanobot.agent.tools.context import RequestContext
from nanobot.agent.tools.schema import (
ArraySchema,
BooleanSchema,
@@ -67,11 +66,11 @@ class CliAppsTool(Tool):
return CliAppsToolConfig
@classmethod
def enabled(cls, ctx: ToolContext) -> bool:
def enabled(cls, ctx: Any) -> bool:
return ctx.config.cli_apps.enable
@classmethod
def create(cls, ctx: ToolContext) -> Tool:
def create(cls, ctx: Any) -> Tool:
cfg = ctx.config.cli_apps
return cls(
workspace=Path(ctx.workspace),
+11 -22
View File
@@ -8,16 +8,6 @@ from pathlib import Path
from typing import TYPE_CHECKING, Any, Callable, Protocol, runtime_checkable
if TYPE_CHECKING:
from nanobot.agent.subagent import SubagentManager
from nanobot.agent.tools.exec_session import ExecSessionManager
from nanobot.agent.tools.file_state import FileStates
from nanobot.bus.queue import MessageBus
from nanobot.bus.runtime_events import RuntimeEventBus
from nanobot.config.schema import ProviderConfig, ToolsConfig
from nanobot.cron.service import CronService
from nanobot.providers.factory import ProviderSnapshot
from nanobot.security.workspace_access import WorkspaceSandboxStatus
from nanobot.session.manager import SessionManager
from nanobot.utils.llm_runtime import LLMRuntime
_CURRENT_REQUEST_CONTEXT: ContextVar["RequestContext | None"] = ContextVar(
@@ -39,7 +29,6 @@ class RequestContext:
sender_id: str | None = None
turn_id: str | None = None
workspace: Path | None = None
attributes: dict[str, Any] = field(default_factory=dict)
@runtime_checkable
@@ -77,16 +66,16 @@ def current_request_session_key() -> str | None:
@dataclass
class ToolContext:
config: ToolsConfig
config: Any
workspace: str
bus: MessageBus | None = None
subagent_manager: SubagentManager | None = None
cron_service: CronService | None = None
exec_session_manager: ExecSessionManager | None = None
sessions: SessionManager | None = None
file_state_store: FileStates | None = None
provider_snapshot_loader: Callable[..., ProviderSnapshot] | None = None
image_generation_provider_configs: dict[str, ProviderConfig] | None = None
bus: Any | None = None
subagent_manager: Any | None = None
cron_service: Any | None = None
exec_session_manager: Any | None = None
sessions: Any | None = None
file_state_store: Any = field(default=None)
provider_snapshot_loader: Callable[[], Any] | None = None
image_generation_provider_configs: dict[str, Any] | None = None
timezone: str = "UTC"
workspace_sandbox: WorkspaceSandboxStatus | None = None
runtime_events: RuntimeEventBus | None = None
workspace_sandbox: Any | None = None
runtime_events: Any | None = None
+11 -14
View File
@@ -1,15 +1,13 @@
"""Cron tool for scheduling reminders and tasks."""
# pyright: reportIncompatibleMethodOverride=false
from __future__ import annotations
from contextvars import ContextVar, Token
from contextvars import ContextVar
from datetime import datetime
from typing import Any
from nanobot.agent.tools.base import Tool, ToolResult, tool_parameters
from nanobot.agent.tools.context import ToolContext, current_request_context
from nanobot.agent.tools.context import current_request_context
from nanobot.agent.tools.schema import (
IntegerSchema,
StringSchema,
@@ -30,7 +28,7 @@ _CRON_PARAMETERS = tool_parameters_schema(
"(e.g., 'Send a reminder to WeChat: xxx' or 'Check system status and report'). "
"Not used for action='list' or action='remove'."
),
every_seconds=IntegerSchema(description="Interval in seconds (for recurring tasks)"),
every_seconds=IntegerSchema(0, description="Interval in seconds (for recurring tasks)"),
cron_expr=StringSchema("Cron expression like '0 9 * * *' (for scheduled tasks)"),
tz=StringSchema(
"Optional IANA timezone for cron expressions (e.g. 'America/Vancouver'). "
@@ -62,15 +60,12 @@ class CronTool(Tool):
self._in_cron_context: ContextVar[bool] = ContextVar("cron_in_context", default=False)
@classmethod
def enabled(cls, ctx: ToolContext) -> bool:
def enabled(cls, ctx: Any) -> bool:
return ctx.cron_service is not None
@classmethod
def create(cls, ctx: ToolContext) -> Tool:
cron_service = ctx.cron_service
if cron_service is None:
raise RuntimeError("CronTool requires an initialized cron service")
return cls(cron_service=cron_service, default_timezone=ctx.timezone)
def create(cls, ctx: Any) -> Tool:
return cls(cron_service=ctx.cron_service, default_timezone=ctx.timezone)
@staticmethod
def _request_route() -> tuple[str, str, str, dict[str, Any]]:
@@ -84,11 +79,11 @@ class CronTool(Tool):
)
return session_key, ctx.channel or "", ctx.chat_id or "", dict(ctx.metadata or {})
def set_cron_context(self, active: bool) -> Token[bool]:
def set_cron_context(self, active: bool):
"""Mark whether the tool is executing inside a cron job callback."""
return self._in_cron_context.set(active)
def reset_cron_context(self, token: Token[bool]) -> None:
def reset_cron_context(self, token) -> None:
"""Restore previous cron context."""
self._in_cron_context.reset(token)
@@ -143,6 +138,8 @@ class CronTool(Tool):
tz: str | None = None,
at: str | None = None,
job_id: str | None = None,
deliver: bool = True,
**kwargs: Any,
) -> str:
if action == "add":
if self._in_cron_context.get():
@@ -262,7 +259,7 @@ class CronTool(Tool):
jobs = self._cron.list_jobs()
if not jobs:
return "No scheduled jobs."
lines: list[str] = []
lines = []
for j in jobs:
timing = self._format_timing(j.schedule)
parts = [f"- {j.name} (id: {j.id}, {timing})"]
+54 -115
View File
@@ -5,13 +5,12 @@ from __future__ import annotations
import asyncio
import time
import uuid
from collections import deque
from contextlib import suppress
from dataclasses import dataclass
from typing import Any
from nanobot.agent.tools.base import Tool, ToolResult, tool_parameters
from nanobot.agent.tools.context import ToolContext, current_request_session_key
from nanobot.agent.tools.context import current_request_session_key
from nanobot.agent.tools.schema import (
BooleanSchema,
IntegerSchema,
@@ -52,66 +51,6 @@ class ExecSessionInfo:
owner_session_key: str | None = None
class _BoundedOutputBuffer:
"""Keep the first and most recent characters within a fixed budget."""
def __init__(self, max_chars: int) -> None:
self.max_chars = max_chars
self._content = ""
self._tail: deque[str] = deque()
self._tail_chars = 0
self._total_chars = 0
self._truncated = False
@property
def has_output(self) -> bool:
return self._total_chars > 0
@property
def retained_chars(self) -> int:
return len(self._content) + self._tail_chars
def append(self, text: str) -> None:
if not text:
return
self._total_chars += len(text)
if not self._truncated:
combined = self._content + text
if len(combined) <= self.max_chars:
self._content = combined
return
head_chars = self.max_chars // 2
tail_chars = self.max_chars - head_chars
self._content = combined[:head_chars]
self._tail.append(combined[-tail_chars:])
self._tail_chars = tail_chars
self._truncated = True
return
tail_chars = self.max_chars - len(self._content)
self._tail.append(text)
self._tail_chars += len(text)
while self._tail_chars > tail_chars:
excess = self._tail_chars - tail_chars
first = self._tail[0]
if len(first) <= excess:
self._tail.popleft()
self._tail_chars -= len(first)
else:
self._tail[0] = first[excess:]
self._tail_chars -= excess
def drain(self) -> tuple[str, int]:
output = self._content + "".join(self._tail)
truncated_chars = self._total_chars - len(output)
self._content = ""
self._tail.clear()
self._tail_chars = 0
self._total_chars = 0
self._truncated = False
return output, truncated_chars
class _ExecSession:
def __init__(
self,
@@ -134,27 +73,30 @@ class _ExecSession:
# timeout None/0 means no limit; an infinite deadline is never reached.
self.deadline = time.monotonic() + timeout if timeout else float("inf")
self.last_access = time.monotonic()
self._stdout = _BoundedOutputBuffer(MAX_OUTPUT_CHARS)
self._stderr = _BoundedOutputBuffer(MAX_OUTPUT_CHARS)
self._chunks: list[str] = []
self._lock = asyncio.Lock()
self._timed_out = False
self._stdout_task = asyncio.create_task(self._read_stream(process.stdout, self._stdout))
self._stderr_task = asyncio.create_task(self._read_stream(process.stderr, self._stderr))
self._stdout_task = asyncio.create_task(self._read_stream(process.stdout, ""))
self._stderr_task = asyncio.create_task(self._read_stream(process.stderr, "STDERR:\n"))
async def _read_stream(
self,
stream: asyncio.StreamReader | None,
buffer: _BoundedOutputBuffer,
prefix: str,
) -> None:
if stream is None:
return
first = True
while True:
chunk = await stream.read(4096)
if not chunk:
break
text = chunk.decode("utf-8", errors="replace")
if prefix and first:
text = prefix + text
first = False
async with self._lock:
buffer.append(text)
self._chunks.append(text)
async def write(self, chars: str) -> str | None:
if self.process.returncode is not None:
@@ -209,20 +151,16 @@ class _ExecSession:
timeout=2.0,
)
# Safety-net reap after normal exit.
from nanobot.agent.tools.shell import _reap_pid # pyright: ignore[reportPrivateUsage]
_reap_pid(self.process.pid) # pyright: ignore[reportPrivateUsage]
from nanobot.agent.tools.shell import _reap_pid
_reap_pid(self.process.pid)
elif yield_time_ms > 0:
await self._wait_for_buffered_output()
async with self._lock:
stdout, stdout_truncated = self._stdout.drain()
stderr, stderr_truncated = self._stderr.drain()
output = "".join(self._chunks)
self._chunks.clear()
output_parts = [stdout] if stdout else []
if stderr:
output_parts.append(f"STDERR:\n{stderr}")
output = "\n".join(output_parts)
output, response_truncated = _truncate_output(output, max_output_chars)
output, truncated = _truncate_output(output, max_output_chars)
return _SessionPoll(
output=output,
done=self.process.returncode is not None,
@@ -231,7 +169,7 @@ class _ExecSession:
timed_out=self._timed_out,
terminated=terminated,
stdin_closed=stdin_closed,
truncated_chars=stdout_truncated + stderr_truncated + response_truncated,
truncated_chars=truncated,
)
async def kill(self) -> None:
@@ -239,9 +177,9 @@ class _ExecSession:
try:
if self._process_tree:
await ExecTool._kill_process_tree(self.process) # pyright: ignore[reportPrivateUsage]
await ExecTool._kill_process_tree(self.process)
else:
await ExecTool._kill_process(self.process) # pyright: ignore[reportPrivateUsage]
await ExecTool._kill_process(self.process)
finally:
with suppress(asyncio.TimeoutError):
await asyncio.wait_for(
@@ -257,7 +195,7 @@ class _ExecSession:
deadline = time.monotonic() + OUTPUT_DRAIN_GRACE_S
while time.monotonic() < deadline:
async with self._lock:
if self._stdout.has_output or self._stderr.has_output:
if self._chunks:
return
await asyncio.sleep(0.01)
@@ -373,13 +311,13 @@ class ExecSessionManager:
"""Terminate and remove all active sessions during shutdown."""
async with self._lock:
self._closed = True
sessions: list[_ExecSession] = list(self._sessions.values())
sessions = list(self._sessions.values())
self._sessions.clear()
results: list[None | BaseException] = list(await asyncio.gather(
results = await asyncio.gather(
*(session.kill() for session in sessions),
return_exceptions=True,
))
failures: list[tuple[_ExecSession, BaseException]] = [
)
failures = [
(session, result)
for session, result in zip(sessions, results, strict=True)
if isinstance(result, BaseException)
@@ -399,15 +337,15 @@ class ExecSessionManager:
async def terminate_by_owner(self, owner_session_key: str) -> int:
"""Terminate all sessions owned by owner_session_key. Returns count."""
async with self._lock:
victims: list[_ExecSession] = []
victims = []
for sid, s in list(self._sessions.items()):
if s.owner_session_key == owner_session_key:
victims.append(self._sessions.pop(sid))
results: list[None | BaseException] = list(await asyncio.gather(
results = await asyncio.gather(
*(s.kill() for s in victims),
return_exceptions=True,
))
failures: list[tuple[_ExecSession, BaseException]] = [
)
failures = [
(session, result)
for session, result in zip(victims, results, strict=True)
if isinstance(result, BaseException)
@@ -446,7 +384,7 @@ class ExecSessionManager:
) -> asyncio.subprocess.Process:
from nanobot.agent.tools.shell import ExecTool
return await ExecTool._spawn( # pyright: ignore[reportPrivateUsage]
return await ExecTool._spawn(
command, cwd, env, shell_program, login,
stdin=asyncio.subprocess.PIPE,
process_tree=True,
@@ -465,16 +403,20 @@ def clamp_session_int(value: int | None, default: int, minimum: int, maximum: in
def _truncate_output(output: str, max_output_chars: int) -> tuple[str, int]:
if len(output) <= max_output_chars:
return output, 0
head_chars = max_output_chars // 2
tail_chars = max_output_chars - head_chars
half = max_output_chars // 2
omitted = len(output) - max_output_chars
return output[:head_chars] + output[-tail_chars:], omitted
return (
output[:half]
+ f"\n\n... ({omitted:,} chars truncated) ...\n\n"
+ output[-half:],
omitted,
)
def format_session_poll(session_id: str, poll: _SessionPoll) -> str:
parts = [poll.output] if poll.output else []
if poll.truncated_chars:
parts.append(f"({poll.truncated_chars:,} chars truncated from output)")
parts.append(f"(output truncated by {poll.truncated_chars:,} chars)")
if poll.timed_out:
parts.append("Error: Command timed out; session was terminated.")
if poll.terminated and not poll.timed_out:
@@ -505,6 +447,7 @@ def format_session_poll(session_id: str, poll: _SessionPoll) -> str:
default=False,
),
yield_time_ms=IntegerSchema(
DEFAULT_YIELD_MS,
description="Milliseconds to wait before returning recent output (default 1000, max 30000).",
minimum=0,
maximum=MAX_YIELD_MS,
@@ -515,17 +458,20 @@ def format_session_poll(session_id: str, poll: _SessionPoll) -> str:
nullable=True,
),
wait_timeout_ms=IntegerSchema(
DEFAULT_WAIT_FOR_MS,
description="Maximum milliseconds to wait for wait_for text (default 10000, max 120000).",
minimum=0,
maximum=MAX_WAIT_FOR_MS,
nullable=True,
),
max_output_chars=IntegerSchema(
DEFAULT_MAX_OUTPUT_CHARS,
description="Maximum output characters to return from this poll (default 10000, max 50000).",
minimum=1000,
maximum=MAX_OUTPUT_CHARS,
),
max_output_tokens=IntegerSchema(
DEFAULT_MAX_OUTPUT_CHARS,
description="Compatibility alias for max_output_chars. The current runtime uses a character budget.",
minimum=1000,
maximum=MAX_OUTPUT_CHARS,
@@ -547,7 +493,7 @@ class WriteStdinTool(Tool):
return ExecToolConfig
@classmethod
def enabled(cls, ctx: ToolContext) -> bool:
def enabled(cls, ctx: Any) -> bool:
return ctx.config.exec.enable
def __init__(
@@ -558,8 +504,8 @@ class WriteStdinTool(Tool):
self._manager = manager or DEFAULT_EXEC_SESSION_MANAGER
@classmethod
def create(cls, ctx: ToolContext) -> Tool:
return cls(manager=ctx.exec_session_manager)
def create(cls, ctx: Any) -> Tool:
return cls(manager=getattr(ctx, "exec_session_manager", None))
@property
def exclusive(self) -> bool:
@@ -580,7 +526,7 @@ class WriteStdinTool(Tool):
"Do not use this to start new commands; start them with exec."
)
async def execute( # pyright: ignore[reportIncompatibleMethodOverride]
async def execute(
self,
session_id: str,
chars: str | None = None,
@@ -645,9 +591,7 @@ class WriteStdinTool(Tool):
max_output_chars: int,
) -> str:
deadline = time.monotonic() + (wait_timeout_ms / 1000)
aggregate = _BoundedOutputBuffer(max_output_chars)
upstream_truncated = 0
search_overlap = ""
aggregate: list[str] = []
first = True
poll: _SessionPoll | None = None
@@ -660,24 +604,19 @@ class WriteStdinTool(Tool):
close_stdin=close_stdin if first else False,
terminate=terminate if first else False,
yield_time_ms=step_ms,
max_output_chars=MAX_OUTPUT_CHARS,
max_output_chars=max_output_chars,
owner_session_key=current_request_session_key(),
)
first = False
upstream_truncated += poll.truncated_chars
if poll.output:
aggregate.append(poll.output)
searchable = search_overlap + poll.output
if wait_for in searchable:
poll.output, aggregate_truncated = aggregate.drain()
poll.truncated_chars = upstream_truncated + aggregate_truncated
joined = "".join(aggregate)
if wait_for in joined:
poll.output = joined
result = format_session_poll(session_id, poll)
return ToolResult.error(result) if poll.timed_out else result
overlap_chars = max(0, len(wait_for) - 1)
search_overlap = searchable[-overlap_chars:] if overlap_chars else ""
if poll.done or remaining_ms <= 0:
poll.output, aggregate_truncated = aggregate.drain()
poll.truncated_chars = upstream_truncated + aggregate_truncated
poll.output = "".join(aggregate)
result = format_session_poll(session_id, poll)
if wait_for not in poll.output:
result += f"\nWait target not observed: {wait_for!r}"
@@ -698,7 +637,7 @@ class ListExecSessionsTool(Tool):
return ExecToolConfig
@classmethod
def enabled(cls, ctx: ToolContext) -> bool:
def enabled(cls, ctx: Any) -> bool:
return ctx.config.exec.enable
def __init__(
@@ -709,8 +648,8 @@ class ListExecSessionsTool(Tool):
self._manager = manager or DEFAULT_EXEC_SESSION_MANAGER
@classmethod
def create(cls, ctx: ToolContext) -> Tool:
return cls(manager=ctx.exec_session_manager)
def create(cls, ctx: Any) -> Tool:
return cls(manager=getattr(ctx, "exec_session_manager", None))
@property
def name(self) -> str:
@@ -736,7 +675,7 @@ class ListExecSessionsTool(Tool):
)
if not sessions:
return "No active exec sessions."
lines: list[str] = []
lines = []
for info in sessions:
command = " ".join(info.command.split())
if len(command) > 120:
+1 -5
View File
@@ -125,10 +125,6 @@ class FileStates:
"""Return the raw ReadState entry for a path, or None."""
return self._state.get(str(Path(path).resolve()))
def raw_state(self) -> dict[str, ReadState]:
"""Return the mutable backing map for legacy compatibility."""
return self._state
def clear(self) -> None:
"""Clear all tracked state (useful for testing)."""
self._state.clear()
@@ -205,5 +201,5 @@ def clear() -> None:
# so existing imports keep working.
def __getattr__(name: str):
if name == "_state":
return _default.raw_state()
return _default._state
raise AttributeError(name)
+14 -28
View File
@@ -1,7 +1,5 @@
"""File system tools: read, write, edit, list."""
# pyright: reportPrivateUsage=false, reportUnusedFunction=false
import difflib
import mimetypes
import os
@@ -10,7 +8,6 @@ from pathlib import Path
from typing import Any
from nanobot.agent.tools.base import Tool, ToolResult, tool_parameters
from nanobot.agent.tools.context import ToolContext
from nanobot.agent.tools.file_state import FileStates, _hash_file, current_file_states
from nanobot.agent.tools.path_utils import resolve_workspace_path
from nanobot.agent.tools.schema import (
@@ -40,7 +37,7 @@ class _FsTool(Tool):
return FileToolsConfig
@classmethod
def enabled(cls, ctx: ToolContext) -> bool:
def enabled(cls, ctx: Any) -> bool:
return ctx.config.file.enable
def __init__(
@@ -80,7 +77,7 @@ class _FsTool(Tool):
self._fallback_file_states = FileStates()
@classmethod
def create(cls, ctx: ToolContext) -> Tool:
def create(cls, ctx: Any) -> Tool:
from nanobot.agent.skills import BUILTIN_SKILLS_DIR
agent_workspace = Path(ctx.workspace)
@@ -229,10 +226,12 @@ def _builtin_skill_read_path(path: str) -> Path | None:
tool_parameters_schema(
path=StringSchema("The file path to read"),
offset=IntegerSchema(
1,
description="Line number to start reading from (1-indexed, default 1)",
minimum=1,
),
limit=IntegerSchema(
2000,
description="Maximum number of lines to read (default 2000)",
minimum=1,
),
@@ -264,8 +263,6 @@ class ReadFileTool(_FsTool):
"Text output format: LINE_NUM|CONTENT. "
"Images return visual content for analysis. "
"Supports PDF, DOCX, XLSX, PPTX documents. "
"Uploaded non-image attachments are referenced by path; read them "
"with this tool only when their contents are needed. "
"Use find_files/list_dir first when the path is uncertain. "
"Read the relevant range before editing so replacements or patches "
"are based on current content. "
@@ -371,25 +368,11 @@ class ReadFileTool(_FsTool):
try:
text_content = raw.decode("utf-8")
except UnicodeDecodeError:
# Match the former eager extractor for known text formats while
# keeping arbitrary binary files on the guarded error path.
from nanobot.utils.document import _is_text_extension
if _is_text_extension(fp.suffix.lower()):
text_content = raw.decode("latin-1")
else:
mime = detect_image_mime(raw) or mimetypes.guess_type(path)[0]
if mime and mime.startswith("image/"):
return build_image_content_blocks(
raw,
mime,
str(fp),
f"(Image file: {path})",
)
return ToolResult.error(
f"Error: Cannot read binary file {path} (MIME: {mime or 'unknown'}). "
"Only supported text files and images can be read."
)
# Binary file - return error message
mime = detect_image_mime(raw) or mimetypes.guess_type(path)[0]
if mime and mime.startswith("image/"):
return build_image_content_blocks(raw, mime, str(fp), f"(Image file: {path})")
return ToolResult.error(f"Error: Cannot read binary file {path} (MIME: {mime or 'unknown'}). Only UTF-8 text and images are supported.")
# Normalize CRLF -> LF before line-splitting. Primarily a Windows
# concern (git checkouts with autocrlf, editors saving CRLF) but
@@ -411,8 +394,7 @@ class ReadFileTool(_FsTool):
result = "\n".join(numbered)
if len(result) > self._MAX_CHARS:
trimmed: list[str] = []
chars = 0
trimmed, chars = [], 0
for line in numbered:
chars += len(line) + 1
if chars > self._MAX_CHARS:
@@ -808,11 +790,13 @@ def _find_match(content: str, old_text: str) -> tuple[str | None, int]:
new_text=StringSchema("The text to replace with"),
replace_all=BooleanSchema(description="Replace all occurrences (default false)"),
occurrence=IntegerSchema(
1,
description="Optional 1-based occurrence to replace when old_text appears multiple times.",
minimum=1,
nullable=True,
),
line_hint=IntegerSchema(
1,
description=(
"Optional exact 1-based target line copied from read_file. "
"The selected old_text match must cover this line."
@@ -821,6 +805,7 @@ def _find_match(content: str, old_text: str) -> tuple[str | None, int]:
nullable=True,
),
expected_replacements=IntegerSchema(
1,
description="Optional guard for the number of replacements that must be made.",
minimum=1,
nullable=True,
@@ -1051,6 +1036,7 @@ class EditFileTool(_FsTool):
path=StringSchema("The directory path to list"),
recursive=BooleanSchema(description="Recursively list all files (default false)"),
max_entries=IntegerSchema(
200,
description="Maximum entries to return (default 200)",
minimum=1,
),
+19 -25
View File
@@ -4,7 +4,7 @@ from __future__ import annotations
import asyncio
from pathlib import Path
from typing import TYPE_CHECKING, Any, cast
from typing import TYPE_CHECKING, Any
from loguru import logger
from pydantic import Field
@@ -23,7 +23,6 @@ from nanobot.bus.events import (
RUNTIME_CONTROL_IMAGE_GENERATION_RELOAD,
InboundMessage,
)
from nanobot.bus.queue import MessageBus
from nanobot.config.paths import get_media_dir
from nanobot.config_base import Base
from nanobot.providers.image_generation import (
@@ -42,7 +41,6 @@ from nanobot.utils.artifacts import (
from nanobot.utils.helpers import detect_image_mime
if TYPE_CHECKING:
from nanobot.agent.tools.context import ToolContext
from nanobot.config.schema import ProviderConfig
@@ -91,11 +89,11 @@ class ImageGenerationTool(Tool):
return ImageGenerationToolConfig
@classmethod
def enabled(cls, ctx: ToolContext) -> bool:
def enabled(cls, ctx: Any) -> bool:
return ctx.config.image_generation.enabled
@classmethod
def create(cls, ctx: ToolContext) -> Tool:
def create(cls, ctx: Any) -> Tool:
return cls(
workspace=ctx.workspace,
config=ctx.config.image_generation,
@@ -136,14 +134,12 @@ class ImageGenerationTool(Tool):
cls = get_image_gen_provider(self.config.provider)
if cls is None:
return None
kwargs: dict[str, Any] = {
"api_key": provider.api_key if provider and isinstance(provider.api_key, str) else None,
"api_base": provider.api_base if provider and isinstance(provider.api_base, str) else None,
"extra_headers": provider.extra_headers
if provider and isinstance(provider.extra_headers, dict) else None,
"extra_body": provider.extra_body
if provider and isinstance(provider.extra_body, dict) else None,
"proxy": provider.proxy if provider and isinstance(provider.proxy, str) else None,
kwargs = {
"api_key": provider.api_key if provider else None,
"api_base": provider.api_base if provider else None,
"extra_headers": provider.extra_headers if provider else None,
"extra_body": provider.extra_body if provider else None,
"proxy": provider.proxy if provider else None,
}
return cls(**kwargs)
@@ -176,7 +172,7 @@ class ImageGenerationTool(Tool):
return []
return [self._resolve_reference_image(value) for value in values if value]
async def execute( # pyright: ignore[reportIncompatibleMethodOverride]
async def execute(
self,
prompt: str,
reference_images: list[str] | None = None,
@@ -242,7 +238,7 @@ async def reload_image_generation_tool(state: Any, registry: ToolRegistry) -> di
}
next_tool = (
ImageGenerationTool( # pyright: ignore[reportAbstractUsage]
ImageGenerationTool(
workspace=state.workspace,
config=tool_config,
provider_configs=provider_configs,
@@ -275,7 +271,7 @@ async def reload_image_generation_tool(state: Any, registry: ToolRegistry) -> di
async def request_image_generation_reload(
bus: MessageBus,
bus: Any,
*,
timeout: float = 5.0,
) -> dict[str, Any]:
@@ -302,13 +298,11 @@ async def request_image_generation_reload(
"message": "Image generation hot reload timed out.",
"requires_restart": True,
}
if not isinstance(cast(object, result), dict):
return {
"ok": False,
"message": "Image generation hot reload returned an unexpected response.",
"requires_restart": True,
}
return result
return result if isinstance(result, dict) else {
"ok": False,
"message": "Image generation hot reload returned an unexpected response.",
"requires_restart": True,
}
async def handle_runtime_control(
@@ -317,7 +311,7 @@ async def handle_runtime_control(
registry: ToolRegistry,
) -> bool:
"""Handle an in-process image generation reload request."""
metadata = msg.metadata
metadata = msg.metadata if isinstance(msg.metadata, dict) else {}
if metadata.get(INBOUND_META_RUNTIME_CONTROL) != RUNTIME_CONTROL_IMAGE_GENERATION_RELOAD:
return False
@@ -333,5 +327,5 @@ async def handle_runtime_control(
"error": str(exc),
}
if isinstance(ack, asyncio.Future) and not ack.done():
cast(asyncio.Future[Any], ack).set_result(result)
ack.set_result(result)
return True
+3 -9
View File
@@ -1,22 +1,16 @@
"""Tool discovery and registration via package scanning."""
# pyright: reportIncompatibleVariableOverride=false
from __future__ import annotations
import importlib
import pkgutil
from importlib.metadata import entry_points
from typing import TYPE_CHECKING, Any
from typing import Any
from loguru import logger
from nanobot.agent.tools.base import Tool, ToolResult
from nanobot.agent.tools.registry import ToolRegistry
if TYPE_CHECKING:
from nanobot.agent.tools.context import RequestContext, ToolContext
_SKIP_MODULES = frozenset({
"base", "schema", "registry", "context", "loader", "config",
"file_state", "sandbox", "mcp", "__init__", "runtime_state",
@@ -89,7 +83,7 @@ class ToolLoader:
self._plugins = plugins
return plugins
def load(self, ctx: ToolContext, registry: ToolRegistry, *, scope: str = "core") -> list[str]:
def load(self, ctx: Any, registry: ToolRegistry, *, scope: str = "core") -> list[str]:
registered: list[str] = []
builtin_names: set[str] = set()
sources = [(self.discover(), False), (self._discover_plugins().values(), True)]
@@ -163,7 +157,7 @@ class _LegacyErrorPrefixTool(Tool):
def config_key(self) -> str:
return getattr(self._wrapped, "config_key", "")
def set_context(self, ctx: RequestContext) -> None:
def set_context(self, ctx: Any) -> None:
set_context = getattr(self._wrapped, "set_context", None)
if callable(set_context):
set_context(ctx)
+15 -19
View File
@@ -1,7 +1,5 @@
"""Sustained-goal tools with explicit user opt-in at the execution boundary."""
# pyright: reportIncompatibleMethodOverride=false
from __future__ import annotations
from copy import deepcopy
@@ -13,7 +11,7 @@ from nanobot.agent.goal_permission import (
revoke_goal_mutation_permission,
)
from nanobot.agent.tools.base import Tool, ToolResult, tool_parameters
from nanobot.agent.tools.context import RequestContext, ToolContext, current_request_context
from nanobot.agent.tools.context import RequestContext, current_request_context
from nanobot.agent.tools.schema import StringSchema, tool_parameters_schema
from nanobot.bus.runtime_events import GoalStateChanged, RuntimeEventBus, RuntimeEventContext
from nanobot.runtime_context import RuntimeContextBlock, wrap_runtime_context_lines
@@ -134,24 +132,23 @@ class CreateGoalTool(Tool, _GoalToolsMixin):
def __init__(
self,
sessions: SessionManager,
sessions: Any,
runtime_events: RuntimeEventBus | None = None,
) -> None:
_GoalToolsMixin.__init__(self, sessions, runtime_events)
@classmethod
def create(cls, ctx: ToolContext) -> Tool:
sess = ctx.sessions
if sess is None:
raise RuntimeError("CreateGoalTool requires an initialized session manager")
def create(cls, ctx: Any) -> Tool:
sess = getattr(ctx, "sessions", None)
assert sess is not None
return cls(
sessions=sess,
runtime_events=ctx.runtime_events,
runtime_events=getattr(ctx, "runtime_events", None),
)
@classmethod
def enabled(cls, ctx: ToolContext) -> bool:
return ctx.sessions is not None
def enabled(cls, ctx: Any) -> bool:
return getattr(ctx, "sessions", None) is not None
@property
def name(self) -> str:
@@ -265,24 +262,23 @@ class UpdateGoalTool(Tool, _GoalToolsMixin):
def __init__(
self,
sessions: SessionManager,
sessions: Any,
runtime_events: RuntimeEventBus | None = None,
) -> None:
_GoalToolsMixin.__init__(self, sessions, runtime_events)
@classmethod
def create(cls, ctx: ToolContext) -> Tool:
sess = ctx.sessions
if sess is None:
raise RuntimeError("UpdateGoalTool requires an initialized session manager")
def create(cls, ctx: Any) -> Tool:
sess = getattr(ctx, "sessions", None)
assert sess is not None
return cls(
sessions=sess,
runtime_events=ctx.runtime_events,
runtime_events=getattr(ctx, "runtime_events", None),
)
@classmethod
def enabled(cls, ctx: ToolContext) -> bool:
return ctx.sessions is not None
def enabled(cls, ctx: Any) -> bool:
return getattr(ctx, "sessions", None) is not None
@property
def name(self) -> str:
+48 -186
View File
@@ -7,9 +7,9 @@ import os
import re
import shutil
import urllib.parse
from collections.abc import AsyncIterator, Awaitable, Callable
from collections.abc import Awaitable, Callable
from contextlib import AsyncExitStack, suppress
from typing import TYPE_CHECKING, Any, Mapping, Protocol, cast
from typing import Any, Mapping, Protocol
from weakref import WeakKeyDictionary
import httpx
@@ -23,7 +23,6 @@ from nanobot.bus.events import (
RUNTIME_CONTROL_MCP_RELOAD,
InboundMessage,
)
from nanobot.bus.queue import MessageBus
from nanobot.security.network import (
PinnedDNSAsyncTransport,
env_proxy_applies_to_url,
@@ -33,13 +32,6 @@ from nanobot.security.network import (
)
from nanobot.utils.cancellation import task_is_cancelling
if TYPE_CHECKING:
from mcp import ClientSession
from mcp.types import Prompt, Resource
from mcp.types import Tool as MCPToolDefinition
from nanobot.config.schema import MCPServerConfig
# Transient connection errors that warrant a single retry.
# These typically happen when an MCP server restarts or a network
# connection is interrupted between calls.
@@ -100,7 +92,7 @@ def _mcp_jsonrpc_payload(message: Any) -> Any:
def _payload_value(payload: Any, key: str) -> Any:
if isinstance(payload, Mapping):
return cast(Mapping[str, Any], payload).get(key)
return payload.get(key)
return getattr(payload, key, None)
@@ -114,7 +106,7 @@ class _MalformedProgressNotificationFilter:
def __init__(self, read_stream: Any, server_name: str) -> None:
self._read_stream = read_stream
self._server_name = server_name
self._iterator: AsyncIterator[Any] | None = None
self._iterator: Any | None = None
async def __aenter__(self) -> "_MalformedProgressNotificationFilter":
await self._read_stream.__aenter__()
@@ -128,13 +120,11 @@ class _MalformedProgressNotificationFilter:
return self
async def __anext__(self) -> Any:
iterator = self._iterator
if iterator is None:
iterator = self._read_stream.__aiter__()
self._iterator = iterator
if self._iterator is None:
self._iterator = self._read_stream.__aiter__()
while True:
message = await anext(iterator)
message = await self._iterator.__anext__()
if _is_malformed_mcp_progress_notification(message):
logger.debug(
"MCP server '{}': dropped progress notification without progressToken",
@@ -251,8 +241,8 @@ def _redact_url(url: str) -> str:
return "<redacted-url>"
def _pinned_transport_kwargs() -> dict[str, Any]:
kwargs: dict[str, Any] = {"transport": PinnedDNSAsyncTransport()}
def _pinned_transport_kwargs() -> dict[str, object]:
kwargs: dict[str, object] = {"transport": PinnedDNSAsyncTransport()}
mounts = httpx_env_proxy_mounts()
if mounts:
kwargs["mounts"] = mounts
@@ -312,107 +302,30 @@ def _extract_nullable_branch(options: Any) -> tuple[dict[str, Any], bool] | None
non_null: list[dict[str, Any]] = []
saw_null = False
for option in cast(list[object], options):
for option in options:
if not isinstance(option, dict):
return None
option_schema = cast(dict[str, Any], option)
if option_schema.get("type") == "null":
if option.get("type") == "null":
saw_null = True
continue
non_null.append(option_schema)
non_null.append(option)
if saw_null and len(non_null) == 1:
return non_null[0], True
return None
def _resolve_local_schema_ref(root: dict[str, Any], ref: str) -> Any:
"""Resolve a local JSON Pointer without accepting remote references."""
if not ref.startswith("#"):
raise ValueError("not a local JSON Pointer")
def _normalize_schema_for_openai(schema: Any) -> dict[str, Any]:
"""Normalize only nullable JSON Schema patterns for tool definitions."""
if not isinstance(schema, dict):
return {"type": "object", "properties": {}}
pointer = urllib.parse.unquote(ref[1:], errors="strict")
if not pointer:
return root
if not pointer.startswith("/"):
raise ValueError("not a local JSON Pointer")
current: Any = root
for raw_part in pointer[1:].split("/"):
part = raw_part.replace("~1", "/").replace("~0", "~")
if isinstance(current, dict):
current = cast(dict[str, Any], current)[part]
elif isinstance(current, list):
current = cast(list[Any], current)[int(part)]
else:
raise KeyError(part)
return current
def _rewrite_local_schema_refs(schema: dict[str, Any]) -> dict[str, Any]:
"""Hoist arbitrary local JSON-Pointer refs into provider-compatible ``$defs``."""
rewritten_refs: dict[str, str] = {}
generated_defs: dict[str, Any] = {}
def rewrite(value: Any) -> Any:
if isinstance(value, list):
return [rewrite(item) for item in cast(list[Any], value)]
if not isinstance(value, dict):
return value
rewritten = dict(cast(dict[str, Any], value))
raw_ref = rewritten.get("$ref")
ref = raw_ref if isinstance(raw_ref, str) else None
is_rewritable_ref = False
if ref is not None and not ref.startswith("#/$defs/"):
try:
pointer = urllib.parse.unquote(ref[1:], errors="strict")
except (UnicodeDecodeError, ValueError):
pass
else:
is_rewritable_ref = ref.startswith("#") and (
not pointer or pointer.startswith("/")
)
if is_rewritable_ref:
assert ref is not None
name = rewritten_refs.get(ref)
if name is None:
try:
target = _resolve_local_schema_ref(schema, ref)
except (KeyError, IndexError, TypeError, UnicodeDecodeError, ValueError):
logger.warning("MCP tool schema contains an unresolved local $ref: {}", ref)
else:
name = f"ref_{hashlib.sha256(ref.encode()).hexdigest()[:12]}"
existing_defs = schema.get("$defs")
while isinstance(existing_defs, dict) and name in existing_defs:
name += "_"
rewritten_refs[ref] = name
# Reserve the name before descending so recursive refs terminate.
generated_defs[name] = {}
generated_defs[name] = rewrite(target)
if name is not None:
rewritten["$ref"] = f"#/$defs/{name}"
return {key: rewrite(item) for key, item in rewritten.items()}
result = cast(dict[str, Any], rewrite(schema))
if generated_defs:
existing_defs = result.get("$defs")
result["$defs"] = {
**(existing_defs if isinstance(existing_defs, dict) else {}),
**generated_defs,
}
return result
def _normalize_nullable_schema(schema: dict[str, Any]) -> dict[str, Any]:
"""Normalize nullable forms in structural subschemas only."""
normalized = dict(schema)
raw_type = normalized.get("type")
if isinstance(raw_type, list):
type_values = cast(list[Any], raw_type)
non_null = [item for item in type_values if item != "null"]
if "null" in type_values and len(non_null) == 1:
non_null = [item for item in raw_type if item != "null"]
if "null" in raw_type and len(non_null) == 1:
normalized["type"] = non_null[0]
normalized["nullable"] = True
@@ -426,53 +339,29 @@ def _normalize_nullable_schema(schema: dict[str, Any]) -> dict[str, Any]:
normalized["nullable"] = True
break
properties = normalized.get("properties")
if isinstance(properties, dict):
property_schemas = cast(dict[str, Any], properties)
if "properties" in normalized and isinstance(normalized["properties"], dict):
normalized["properties"] = {
name: (
_normalize_nullable_schema(cast(dict[str, Any], prop))
if isinstance(prop, dict)
else prop
)
for name, prop in property_schemas.items()
}
items = normalized.get("items")
if isinstance(items, dict):
normalized["items"] = _normalize_nullable_schema(cast(dict[str, Any], items))
definitions = normalized.get("$defs")
if isinstance(definitions, dict):
definition_schemas = cast(dict[str, Any], definitions)
normalized["$defs"] = {
name: _normalize_nullable_schema(cast(dict[str, Any], definition))
if isinstance(definition, dict)
else definition
for name, definition in definition_schemas.items()
name: _normalize_schema_for_openai(prop) if isinstance(prop, dict) else prop
for name, prop in normalized["properties"].items()
}
if normalized.get("type") == "object":
normalized.setdefault("properties", {})
normalized.setdefault("required", [])
if "items" in normalized and isinstance(normalized["items"], dict):
normalized["items"] = _normalize_schema_for_openai(normalized["items"])
if normalized.get("type") != "object":
return normalized
normalized.setdefault("properties", {})
normalized.setdefault("required", [])
return normalized
def _normalize_schema_for_openai(schema: Any) -> dict[str, Any]:
"""Normalize MCP JSON Schema patterns for tool definitions."""
if not isinstance(schema, dict):
return {"type": "object", "properties": {}}
schema_mapping = cast(dict[str, Any], schema)
return _normalize_nullable_schema(_rewrite_local_schema_refs(schema_mapping))
class _MCPWrapperBase(Tool):
"""Common reconnect handling for wrappers bound to one MCP server session."""
_plugin_discoverable = False
_session: "ClientSession"
_server_name: str
_name: str
def _set_mcp_connection(self, session: "ClientSession", server_name: str) -> None:
def _set_mcp_connection(self, session: Any, server_name: str) -> None:
self._session = session
self._server_name = server_name
self._reconnect: _ReconnectCallback | None = None
@@ -526,10 +415,9 @@ def _image_block_data_url(block: Any, types: Any) -> str | None:
if embedded_cls is not None and isinstance(block, embedded_cls):
resource = getattr(block, "resource", None)
if blob_cls is not None and isinstance(resource, blob_cls):
blob_resource = cast(Any, resource)
mime = getattr(blob_resource, "mimeType", None) or ""
mime = getattr(resource, "mimeType", None) or ""
if isinstance(mime, str) and mime.startswith("image/"):
return f"data:{mime};base64,{blob_resource.blob}"
return f"data:{mime};base64,{resource.blob}"
return None
@@ -560,13 +448,7 @@ class MCPToolWrapper(_MCPWrapperBase):
_plugin_discoverable = False
def __init__(
self,
session: "ClientSession",
server_name: str,
tool_def: "MCPToolDefinition",
tool_timeout: int = 30,
):
def __init__(self, session, server_name: str, tool_def, tool_timeout: int = 30):
self._set_mcp_connection(session, server_name)
self._original_name = tool_def.name
self._name = _sanitize_mcp_tool_name(f"mcp_{server_name}_{tool_def.name}")
@@ -722,13 +604,7 @@ class MCPResourceWrapper(_MCPWrapperBase):
_plugin_discoverable = False
def __init__(
self,
session: "ClientSession",
server_name: str,
resource_def: "Resource",
resource_timeout: int = 30,
):
def __init__(self, session, server_name: str, resource_def, resource_timeout: int = 30):
self._set_mcp_connection(session, server_name)
self._uri = resource_def.uri
self._name = _sanitize_mcp_tool_name(f"mcp_{server_name}_resource_{resource_def.name}")
@@ -814,7 +690,7 @@ class MCPResourceWrapper(_MCPWrapperBase):
for block in result.contents:
if isinstance(block, types.TextResourceContents):
parts.append(block.text)
elif isinstance(cast(object, block), types.BlobResourceContents):
elif isinstance(block, types.BlobResourceContents):
parts.append(f"[Binary resource: {len(block.blob)} bytes]")
else:
parts.append(str(block))
@@ -826,13 +702,7 @@ class MCPPromptWrapper(_MCPWrapperBase):
_plugin_discoverable = False
def __init__(
self,
session: "ClientSession",
server_name: str,
prompt_def: "Prompt",
prompt_timeout: int = 30,
):
def __init__(self, session, server_name: str, prompt_def, prompt_timeout: int = 30):
self._set_mcp_connection(session, server_name)
self._prompt_name = prompt_def.name
self._name = _sanitize_mcp_tool_name(f"mcp_{server_name}_prompt_{prompt_def.name}")
@@ -961,7 +831,7 @@ class MCPPromptWrapper(_MCPWrapperBase):
async def connect_mcp_servers(
mcp_servers: "dict[str, MCPServerConfig]", registry: ToolRegistry
mcp_servers: dict, registry: ToolRegistry
) -> dict[str, MCPConnection]:
"""Connect to configured MCP servers and register their tools, resources, prompts.
@@ -974,9 +844,7 @@ async def connect_mcp_servers(
from mcp.client.stdio import stdio_client
from mcp.client.streamable_http import streamable_http_client
async def open_single_server(
name: str, cfg: "MCPServerConfig"
) -> tuple[str, AsyncExitStack | None]:
async def open_single_server(name: str, cfg) -> tuple[str, AsyncExitStack | None]:
server_stack = AsyncExitStack()
await server_stack.__aenter__()
@@ -1195,9 +1063,7 @@ async def connect_mcp_servers(
await server_stack.aclose()
return name, None
async def connect_single_server(
name: str, cfg: "MCPServerConfig"
) -> tuple[str, MCPConnection | None]:
async def connect_single_server(name: str, cfg) -> tuple[str, MCPConnection | None]:
loop = asyncio.get_running_loop()
ready: asyncio.Future[bool] = loop.create_future()
close_requested = asyncio.Event()
@@ -1241,7 +1107,7 @@ async def connect_mcp_servers(
except Exception as e:
logger.exception("MCP server '{}' connection failed: {}", name, e)
continue
if result[1] is not None:
if result is not None and result[1] is not None:
server_stacks[result[0]] = result[1]
return server_stacks
@@ -1322,7 +1188,7 @@ async def reload_servers(state: Any, registry: ToolRegistry) -> dict[str, Any]:
tools_removed = 0
for name in [*removed, *changed]:
tools_removed += _unregister_server_tools(registry, name)
tools_removed += _unregister_server_tools(state, registry, name)
await _close_server(state, name)
state._mcp_servers = next_servers
@@ -1384,11 +1250,7 @@ async def reload_servers(state: Any, registry: ToolRegistry) -> dict[str, Any]:
}
async def request_mcp_reload(
bus: MessageBus,
*,
timeout: float = 15.0,
) -> dict[str, Any]:
async def request_mcp_reload(bus: Any, *, timeout: float = 15.0) -> dict[str, Any]:
"""Ask the running agent loop to reconcile live MCP connections."""
loop = asyncio.get_running_loop()
ack: asyncio.Future[dict[str, Any]] = loop.create_future()
@@ -1412,7 +1274,7 @@ async def request_mcp_reload(
"message": "MCP hot reload timed out. Restart nanobot to pick up changes.",
"requires_restart": True,
}
return result if isinstance(cast(object, result), dict) else {
return result if isinstance(result, dict) else {
"ok": False,
"message": "MCP hot reload returned an unexpected response.",
"requires_restart": True,
@@ -1420,7 +1282,7 @@ async def request_mcp_reload(
async def handle_runtime_control(state: Any, msg: InboundMessage, registry: ToolRegistry) -> bool:
metadata = msg.metadata if isinstance(cast(object, msg.metadata), dict) else {}
metadata = msg.metadata if isinstance(msg.metadata, dict) else {}
control = metadata.get(INBOUND_META_RUNTIME_CONTROL)
if control != RUNTIME_CONTROL_MCP_RELOAD:
return False
@@ -1437,7 +1299,7 @@ async def handle_runtime_control(state: Any, msg: InboundMessage, registry: Tool
"error": str(exc),
}
if isinstance(ack, asyncio.Future) and not ack.done():
cast(asyncio.Future[dict[str, Any]], ack).set_result(result)
ack.set_result(result)
return True
@@ -1500,7 +1362,7 @@ async def _refresh_terminated_server(
return current_tool
logger.warning("MCP server '{}' session terminated; refreshing connection", server_name)
_unregister_server_tools(registry, server_name)
_unregister_server_tools(state, registry, server_name)
await _close_server(state, server_name)
connected = await connect_mcp_servers({server_name: cfg}, registry)
@@ -1532,7 +1394,7 @@ def _tool_belongs_to_server(tool: Tool | None, tool_name: str, server_name: str)
return tool_name.startswith(_tool_prefix(server_name))
def _unregister_server_tools(registry: ToolRegistry, server_name: str) -> int:
def _unregister_server_tools(state: Any, registry: ToolRegistry, server_name: str) -> int:
removed = 0
for tool_name in list(registry.tool_names):
tool = registry.get(tool_name)
+38 -24
View File
@@ -1,15 +1,13 @@
"""Message tool for sending messages to users."""
# pyright: reportIncompatibleMethodOverride=false
from contextvars import ContextVar, Token
from contextvars import ContextVar
from pathlib import Path
from typing import Any, Awaitable, Callable, cast
from typing import Any, Awaitable, Callable
from loguru import logger
from nanobot.agent.tools.base import Tool, ToolResult, tool_parameters
from nanobot.agent.tools.context import ToolContext, current_request_context
from nanobot.agent.tools.context import current_request_context
from nanobot.agent.tools.path_utils import resolve_workspace_path
from nanobot.agent.tools.schema import ArraySchema, StringSchema, tool_parameters_schema
from nanobot.bus.events import OutboundMessage
@@ -69,13 +67,21 @@ class MessageTool(Tool):
self._fallback_message_id = default_message_id
self._fallback_metadata: dict[str, Any] = {}
self._sent_in_turn_var: ContextVar[bool] = ContextVar("message_sent_in_turn", default=False)
self._turn_delivered_media_var: ContextVar[tuple[str, ...]] = ContextVar(
"message_turn_delivered_media",
default=(),
)
self._record_channel_delivery_var: ContextVar[bool] = ContextVar(
"message_record_channel_delivery",
default=False,
)
self._suppress_delivery_var: ContextVar[bool] = ContextVar(
"message_suppress_delivery",
default=False,
)
@classmethod
def create(cls, ctx: ToolContext) -> Tool:
def create(cls, ctx: Any) -> Tool:
send_callback = ctx.bus.publish_outbound if ctx.bus else None
return cls(
send_callback=send_callback,
@@ -90,12 +96,25 @@ class MessageTool(Tool):
def start_turn(self) -> None:
"""Reset per-turn send tracking."""
self._sent_in_turn = False
self._turn_delivered_media_var.set(())
def set_suppress_delivery(self, active: bool) -> Token[bool]:
def turn_delivered_media_paths(self) -> list[str]:
"""Absolute paths attached via this tool to the active chat in the current turn."""
return list(self._turn_delivered_media_var.get())
def set_record_channel_delivery(self, active: bool):
"""Mark tool-sent messages as proactive channel deliveries."""
return self._record_channel_delivery_var.set(active)
def reset_record_channel_delivery(self, token) -> None:
"""Restore previous proactive delivery recording state."""
self._record_channel_delivery_var.reset(token)
def set_suppress_delivery(self, active: bool):
"""Acknowledge but don't deliver tool sends (heartbeat internal check)."""
return self._suppress_delivery_var.set(active)
def reset_suppress_delivery(self, token: Token[bool]) -> None:
def reset_suppress_delivery(self, token) -> None:
"""Restore previous delivery-suppression state."""
self._suppress_delivery_var.reset(token)
@@ -150,23 +169,19 @@ class MessageTool(Tool):
chat_id: str | None = None,
message_id: str | None = None,
media: list[str] | None = None,
buttons: Any = None,
buttons: list[list[str]] | None = None,
**kwargs: Any,
) -> str: # pyright: ignore[reportIncompatibleMethodOverride]
) -> str:
from nanobot.utils.helpers import strip_think
content = strip_think(content)
button_rows: list[list[str]] | None = None
if buttons is not None:
raw_buttons = cast(list[Any], buttons) if isinstance(buttons, list) else None
if raw_buttons is None or any(
not isinstance(row, list)
or any(not isinstance(label, str) for label in cast(list[Any], row))
for row in raw_buttons
if not isinstance(buttons, list) or any(
not isinstance(row, list) or any(not isinstance(label, str) for label in row)
for row in buttons
):
return ToolResult.error("Error: buttons must be a list of list of strings")
button_rows = cast(list[list[str]], raw_buttons)
request_ctx = current_request_context()
default_channel = (
request_ctx.channel if request_ctx is not None else self._fallback_channel
@@ -226,7 +241,7 @@ class MessageTool(Tool):
metadata = dict(default_metadata) if same_target else {}
if message_id:
metadata["message_id"] = message_id
if media:
if self._record_channel_delivery_var.get() or media:
metadata["_record_channel_delivery"] = True
msg = OutboundMessage(
@@ -234,7 +249,7 @@ class MessageTool(Tool):
chat_id=chat_id,
content=content,
media=media or [],
buttons=button_rows or [],
buttons=buttons or [],
metadata=metadata,
)
@@ -246,12 +261,11 @@ class MessageTool(Tool):
await self._send_callback(msg)
if channel == default_channel and chat_id == default_chat_id:
self._sent_in_turn = True
if media:
prev = self._turn_delivered_media_var.get()
self._turn_delivered_media_var.set(prev + tuple(str(p) for p in media))
media_info = f" with {len(media)} attachments" if media else ""
button_info = (
f" with {sum(len(row) for row in button_rows)} button(s)"
if button_rows
else ""
)
button_info = f" with {sum(len(row) for row in buttons)} button(s)" if buttons else ""
return f"Message sent to {channel}:{chat_id}{media_info}{button_info}"
except Exception as e:
return ToolResult.error(f"Error sending message: {str(e)}")
+8 -11
View File
@@ -3,7 +3,7 @@
from __future__ import annotations
import json
from typing import TYPE_CHECKING, Any, cast
from typing import TYPE_CHECKING, Any
from nanobot.agent.tools.base import Tool, ToolResult
from nanobot.agent.tools.context import ContextAware, current_request_context
@@ -12,7 +12,7 @@ if TYPE_CHECKING:
from nanobot.runtime_context import RuntimeContextProvider
def is_tool_error_result(result: Any) -> bool:
def is_tool_error_result(name: str, result: Any) -> bool:
return isinstance(result, ToolResult) and result.is_error
@@ -77,7 +77,7 @@ class ToolRegistry:
"""Extract a normalized tool name from either OpenAI or flat schemas."""
fn = schema.get("function")
if isinstance(fn, dict):
name = cast(dict[str, Any], fn).get("name")
name = fn.get("name")
if isinstance(name, str):
return name
name = schema.get("name")
@@ -140,7 +140,7 @@ class ToolRegistry:
)
)
cast_params = tool.cast_params(cast(dict[str, Any], params))
cast_params = tool.cast_params(params)
errors = tool.validate_params(cast_params)
if errors:
return tool, cast_params, (
@@ -176,15 +176,12 @@ class ToolRegistry:
@classmethod
def _unwrap_arguments_payload(cls, tool: Tool, params: Any) -> Any:
if not isinstance(params, dict):
if not isinstance(params, dict) or set(params) != {"arguments"}:
return params
arguments_payload = cast(dict[str, Any], params)
if set(arguments_payload) != {"arguments"}:
return arguments_payload
properties = (tool.parameters or {}).get("properties", {})
if isinstance(properties, dict) and "arguments" in properties:
return arguments_payload
return cls._coerce_argument_value(arguments_payload.get("arguments"))
return params
return cls._coerce_argument_value(params.get("arguments"))
async def execute(self, name: str, params: Any) -> Any:
"""Execute a tool by name with given parameters."""
@@ -196,7 +193,7 @@ class ToolRegistry:
try:
assert tool is not None # guarded by prepare_call()
result = await tool.execute(**params)
if is_tool_error_result(result):
if is_tool_error_result(name, result):
return ToolResult.error(str(result) + hint)
return result
except Exception as e:
+12 -18
View File
@@ -1,15 +1,6 @@
"""RuntimeState protocol: agent loop state exposed to MyTool."""
from __future__ import annotations
from pathlib import Path
from typing import TYPE_CHECKING, Any, Protocol
if TYPE_CHECKING:
from nanobot.agent.subagent import SubagentManager
from nanobot.agent.tools.shell import ExecToolConfig
from nanobot.agent.tools.web import WebToolsConfig
from nanobot.utils.llm_runtime import LLMRuntime
from typing import Any, Protocol
class RuntimeState(Protocol):
@@ -34,7 +25,7 @@ class RuntimeState(Protocol):
def tool_names(self) -> list[str]: ...
@property
def workspace(self) -> Path: ...
def workspace(self) -> str: ...
@property
def provider_retry_mode(self) -> str: ...
@@ -46,31 +37,34 @@ class RuntimeState(Protocol):
def context_window_tokens(self) -> int: ...
@property
def web_config(self) -> WebToolsConfig: ...
def web_config(self) -> Any: ...
@property
def exec_config(self) -> ExecToolConfig: ...
def exec_config(self) -> Any: ...
@property
def subagents(self) -> SubagentManager: ...
def workspace_sandbox(self) -> Any: ...
@property
def subagents(self) -> Any: ...
@property
def _runtime_vars(self) -> dict[str, Any]: ...
@property
def _last_usage(self) -> dict[str, int]: ...
def _last_usage(self) -> Any: ...
def _sync_subagent_runtime_limits(self) -> None: ...
def set_runtime_model(self, model: str) -> LLMRuntime: ...
def set_runtime_model(self, model: str) -> Any: ...
def set_runtime_context_window(self, context_window_tokens: int) -> LLMRuntime: ...
def set_runtime_context_window(self, context_window_tokens: int) -> Any: ...
def set_session_model_preset(
self,
session_key: str,
name: str,
) -> LLMRuntime: ...
) -> Any: ...
@property
def model_preset(self) -> str | None: ...
+5 -63
View File
@@ -5,54 +5,13 @@ To add a new backend, implement a function with the signature:
and register it in _BACKENDS below.
"""
import os
import shlex
from pathlib import Path
from typing import Iterable
from nanobot.config.paths import get_media_dir
def _normalize_bind_paths(
paths: Iterable[str] | None,
*,
workspace: Path | None = None,
) -> list[str]:
out: list[str] = []
seen: set[str] = set()
for raw in paths or []:
value = str(raw).strip()
if not value:
continue
path = Path(os.path.expandvars(value)).expanduser()
if not path.is_absolute():
continue
resolved_path = path.resolve(strict=False)
if workspace is not None:
try:
workspace.relative_to(resolved_path)
except ValueError:
pass
else:
# A later bind of the workspace or one of its parents could
# cover the tmpfs that hides the config directory.
continue
resolved = str(resolved_path)
if resolved in seen:
continue
seen.add(resolved)
out.append(resolved)
return out
def _bwrap(
command: str,
workspace: str,
cwd: str,
*,
sandbox_ro_binds: Iterable[str] | None = None,
sandbox_rw_binds: Iterable[str] | None = None,
) -> str:
def _bwrap(command: str, workspace: str, cwd: str) -> str:
"""Wrap command in a bubblewrap sandbox (requires bwrap in container).
Only the workspace is bind-mounted read-write; its parent dir (which holds
@@ -92,34 +51,17 @@ def _bwrap(
"--dir", str(ws), # recreate workspace mount point
"--bind", str(ws), str(ws),
"--ro-bind-try", str(media), str(media), # read-only access to media
"--chdir", sandbox_cwd,
"--", "sh", "-c", command,
]
for p in _normalize_bind_paths(sandbox_ro_binds, workspace=ws):
args += ["--ro-bind-try", p, p]
for p in _normalize_bind_paths(sandbox_rw_binds, workspace=ws):
args += ["--bind-try", p, p]
args += ["--chdir", sandbox_cwd, "--", "sh", "-c", command]
return shlex.join(args)
_BACKENDS = {"bwrap": _bwrap}
def wrap_command(
sandbox: str,
command: str,
workspace: str,
cwd: str,
*,
sandbox_ro_binds: Iterable[str] | None = None,
sandbox_rw_binds: Iterable[str] | None = None,
) -> str:
def wrap_command(sandbox: str, command: str, workspace: str, cwd: str) -> str:
"""Wrap *command* using the named sandbox backend."""
if backend := _BACKENDS.get(sandbox):
return backend(
command,
workspace,
cwd,
sandbox_ro_binds=sandbox_ro_binds,
sandbox_rw_binds=sandbox_rw_binds,
)
return backend(command, workspace, cwd)
raise ValueError(f"Unknown sandbox backend {sandbox!r}. Available: {list(_BACKENDS)}")
+5 -1
View File
@@ -52,10 +52,11 @@ class StringSchema(Schema):
class IntegerSchema(Schema):
"""Integer parameter with a description and optional bounds."""
"""Integer parameter: optional placeholder int (legacy ctor signature), description, and bounds."""
def __init__(
self,
value: int = 0,
*,
description: str = "",
minimum: int | None = None,
@@ -63,6 +64,7 @@ class IntegerSchema(Schema):
enum: tuple[int, ...] | list[int] | None = None,
nullable: bool = False,
) -> None:
self._value = value
self._description = description
self._minimum = minimum
self._maximum = maximum
@@ -90,6 +92,7 @@ class NumberSchema(Schema):
def __init__(
self,
value: float = 0.0,
*,
description: str = "",
minimum: float | None = None,
@@ -97,6 +100,7 @@ class NumberSchema(Schema):
enum: tuple[float, ...] | list[float] | None = None,
nullable: bool = False,
) -> None:
self._value = value
self._description = description
self._minimum = minimum
self._maximum = maximum
-2
View File
@@ -1,7 +1,5 @@
"""Search tools: file discovery and grep."""
# pyright: reportIncompatibleMethodOverride=false, reportPrivateUsage=false
from __future__ import annotations
import fnmatch
+30 -53
View File
@@ -1,14 +1,10 @@
"""MyTool: runtime state inspection and configuration for the agent loop."""
# RuntimeState intentionally exposes a narrow set of AgentLoop internals to
# this manually registered tool. Tool.execute accepts heterogeneous schemas.
# pyright: reportPrivateUsage=false, reportIncompatibleMethodOverride=false
from __future__ import annotations
import time
from collections.abc import Mapping
from typing import TYPE_CHECKING, Any, TypeGuard, cast
from typing import TYPE_CHECKING, Any
from loguru import logger
@@ -19,7 +15,6 @@ from nanobot.config_base import Base
if TYPE_CHECKING:
from nanobot.agent.subagent import SubagentStatus
from nanobot.agent.tools.context import ToolContext
class MyToolConfig(Base):
@@ -41,7 +36,7 @@ def _has_real_attr(obj: Any, key: str) -> bool:
return False
def _is_subagent_status(value: object) -> TypeGuard[SubagentStatus]:
def _is_subagent_status(value: Any) -> bool:
from nanobot.agent.subagent import SubagentStatus
return isinstance(value, SubagentStatus)
@@ -58,7 +53,7 @@ class MyTool(Tool):
return MyToolConfig
@classmethod
def enabled(cls, ctx: ToolContext) -> bool:
def enabled(cls, ctx: Any) -> bool:
return ctx.config.my.enable
BLOCKED = frozenset({
@@ -210,7 +205,7 @@ class MyTool(Tool):
def _resolve_path(self, path: str) -> tuple[Any, str | None]:
parts = path.split(".")
obj: Any = self._runtime_state
obj = self._runtime_state
for part in parts:
if part in self._DENIED_ATTRS or part.startswith("__"):
return None, f"'{part}' is not accessible"
@@ -220,9 +215,8 @@ class MyTool(Tool):
return None, f"'{part}' is not accessible"
try:
if isinstance(obj, Mapping):
mapping = cast(Mapping[str, Any], obj)
if part in mapping:
obj = mapping[part]
if part in obj:
obj = obj[part]
else:
return None, f"'{part}' not found in mapping"
else:
@@ -265,40 +259,28 @@ class MyTool(Tool):
detail = MyTool._format_status(val, " ")
return f"{header}\n task: {val.task_description}\n{detail}"
# SubagentManager: delegate to its _task_statuses dict
task_statuses = getattr(val, "_task_statuses", None)
if isinstance(task_statuses, dict):
return MyTool._format_value(task_statuses, key)
if isinstance(val, Mapping):
mapping = cast(Mapping[object, object], val)
else:
mapping = None
if (
mapping
and _is_subagent_status(next(iter(mapping.values())))
):
status_mapping: Mapping[object, SubagentStatus] = cast(Any, mapping)
if hasattr(val, "_task_statuses") and isinstance(val._task_statuses, dict):
return MyTool._format_value(val._task_statuses, key)
if isinstance(val, Mapping) and val and _is_subagent_status(next(iter(val.values()))):
prefix = f"{key}: " if key else ""
lines = [f"{prefix}{len(status_mapping)} subagent(s):"]
for tid, st in status_mapping.items():
lines = [f"{prefix}{len(val)} subagent(s):"]
for tid, st in val.items():
detail = MyTool._format_status(st, " ")
lines.append(f" [{tid}] '{st.label}'\n{detail}")
return "\n".join(lines)
dynamic_value = cast(Any, val)
if hasattr(dynamic_value, "tool_names"):
tool_names: Any = getattr(dynamic_value, "tool_names")
return f"tools: {len(tool_names)} registered — {tool_names}"
if hasattr(val, "tool_names"):
return f"tools: {len(val.tool_names)} registered — {val.tool_names}"
# Scalar types — repr is fine
if isinstance(val, (str, int, float, bool, type(None))):
r = repr(val)
return f"{key}: {r}" if key else r
# Mapping — small: show content; large: show keys for dot-path navigation
if isinstance(val, Mapping):
value_mapping = cast(Mapping[object, object], val)
ks = list(value_mapping.keys())
ks = list(val.keys())
if not ks:
return f"{key}: {{}}" if key else "{}"
if len(ks) <= 5:
r = repr(value_mapping)
r = repr(val)
if len(r) <= 200:
return f"{key}: {r}" if key else r
preview = ", ".join(str(k) for k in ks[:15])
@@ -306,20 +288,18 @@ class MyTool(Tool):
return f"{key}: {{{preview}{suffix}}}" if key else f"{{{preview}{suffix}}}"
# List/tuple — count for large, repr for small
if isinstance(val, (list, tuple)):
sequence = cast(list[object] | tuple[object, ...], val)
if len(sequence) > 20:
return f"{key}: [{len(sequence)} items]" if key else f"[{len(sequence)} items]"
r = repr(sequence)
if len(val) > 20:
return f"{key}: [{len(val)} items]" if key else f"[{len(val)} items]"
r = repr(val)
return f"{key}: {r}" if key else r
# Complex object — small Pydantic models: show values; others: show field names for navigation
value_type = type(cast(object, val))
cls_name = value_type.__name__
model_fields = cast(object, getattr(value_type, "model_fields", None))
if isinstance(model_fields, Mapping) and model_fields:
fields = list(cast(Mapping[str, object], model_fields).keys())
cls_name = type(val).__name__
model_fields = getattr(type(val), "model_fields", None)
if model_fields:
fields = list(model_fields.keys())
if len(fields) <= 8:
# Small config objects: show field=value pairs
pairs: list[str] = []
pairs = []
for f in fields:
fv = getattr(val, f, "?")
if MyTool._is_sensitive_field_name(f):
@@ -331,8 +311,7 @@ class MyTool(Tool):
preview = ", ".join(pairs)
return f"{key}: {preview}" if key else preview
else:
attributes = cast(dict[str, Any], getattr(val, "__dict__", {}))
fields = [name for name in attributes if not name.startswith("__")]
fields = [a for a in getattr(val, "__dict__", {}) if not a.startswith("__")]
if fields:
preview = ", ".join(str(f) for f in fields[:20])
suffix = ", ..." if len(fields) > 20 else ""
@@ -438,7 +417,6 @@ class MyTool(Tool):
def _modify(self, key: str | None, value: Any) -> str:
if err := self._validate_key(key):
return err
key = cast(str, key)
top = key.split(".")[0]
if top in self.BLOCKED or top in self._DENIED_ATTRS or top.startswith("__") or top.lower() in self._SENSITIVE_NAMES:
self._audit("modify", f"BLOCKED {key}")
@@ -500,7 +478,7 @@ class MyTool(Tool):
def _modify_restricted(self, key: str, value: Any) -> str:
spec = self.RESTRICTED[key]
expected = cast(type[Any], spec["type"])
expected = spec["type"]
if expected is int and isinstance(value, bool):
return ToolResult.error(f"Error: '{key}' must be {expected.__name__}, got bool")
if not isinstance(value, expected):
@@ -521,9 +499,9 @@ class MyTool(Tool):
"during an active session; use a configured model_preset"
)
if key == "model":
self._runtime_state.set_runtime_model(cast(str, value))
self._runtime_state.set_runtime_model(value)
elif key == "context_window_tokens":
self._runtime_state.set_runtime_context_window(cast(int, value))
self._runtime_state.set_runtime_context_window(value)
else:
setattr(self._runtime_state, key, value)
if key == "max_iterations" and hasattr(
@@ -538,8 +516,7 @@ class MyTool(Tool):
if _has_real_attr(self._runtime_state, key):
old = getattr(self._runtime_state, key)
if isinstance(old, (str, int, float, bool)):
old_t: type[Any] = type(old)
new_t = cast(type[Any], type(value))
old_t, new_t = type(old), type(value)
if old_t is float and new_t is int:
pass # int → float coercion allowed
elif old_t is not new_t:
@@ -578,12 +555,12 @@ class MyTool(Tool):
if isinstance(value, (str, int, float, bool, type(None))):
return None
if isinstance(value, list):
for i, item in enumerate(cast(list[Any], value)):
for i, item in enumerate(value):
if err := cls._validate_json_safe(item, depth + 1):
return f"list[{i}] contains {err}"
return None
if isinstance(value, dict):
for k, v in cast(dict[Any, Any], value).items():
for k, v in value.items():
if not isinstance(k, str):
return f"dict key must be str, got {type(k).__name__}"
if err := cls._validate_json_safe(v, depth + 1):
+12 -77
View File
@@ -18,14 +18,13 @@ from loguru import logger
from pydantic import Field
from nanobot.agent.tools.base import Tool, ToolResult, tool_parameters
from nanobot.agent.tools.context import ToolContext, current_request_session_key
from nanobot.agent.tools.context import current_request_session_key
from nanobot.agent.tools.exec_session import (
DEFAULT_EXEC_SESSION_MANAGER,
DEFAULT_MAX_OUTPUT_CHARS,
DEFAULT_YIELD_MS,
MAX_OUTPUT_CHARS,
MAX_YIELD_MS,
ExecSessionManager,
clamp_session_int,
format_session_poll,
)
@@ -85,8 +84,6 @@ class ExecToolConfig(Base):
path_prepend: str = ""
path_append: str = ""
sandbox: str = ""
sandbox_ro_binds: list[str] = Field(default_factory=list)
sandbox_rw_binds: list[str] = Field(default_factory=list)
allowed_env_keys: list[str] = Field(default_factory=list)
allow_patterns: list[str] = Field(default_factory=list)
deny_patterns: list[str] = Field(default_factory=list)
@@ -109,6 +106,7 @@ class _PreparedCommand:
working_dir=StringSchema("Optional working directory for the command"),
workdir=StringSchema("Compatibility alias for working_dir"),
timeout=IntegerSchema(
60,
description=(
"Timeout in seconds. Increase for long-running commands "
"like compilation or installation (default 60, max 600)."
@@ -175,11 +173,11 @@ class ExecTool(Tool):
return ExecToolConfig
@classmethod
def enabled(cls, ctx: ToolContext) -> bool:
def enabled(cls, ctx: Any) -> bool:
return ctx.config.exec.enable
@classmethod
def create(cls, ctx: ToolContext) -> Tool:
def create(cls, ctx: Any) -> Tool:
cfg = ctx.config.exec
return cls(
working_dir=ctx.workspace,
@@ -189,12 +187,10 @@ class ExecTool(Tool):
sandbox=cfg.sandbox,
path_prepend=cfg.path_prepend,
path_append=cfg.path_append,
sandbox_ro_binds=cfg.sandbox_ro_binds,
sandbox_rw_binds=cfg.sandbox_rw_binds,
allowed_env_keys=cfg.allowed_env_keys,
allow_patterns=cfg.allow_patterns,
deny_patterns=cfg.deny_patterns,
session_manager=ctx.exec_session_manager,
session_manager=getattr(ctx, "exec_session_manager", None),
)
def __init__(
@@ -209,10 +205,8 @@ class ExecTool(Tool):
sandbox: str = "",
path_prepend: str = "",
path_append: str = "",
sandbox_ro_binds: list[str] | None = None,
sandbox_rw_binds: list[str] | None = None,
allowed_env_keys: list[str] | None = None,
session_manager: ExecSessionManager | None = None,
session_manager: Any | None = None,
):
self.timeout = timeout
self.working_dir = working_dir
@@ -243,8 +237,6 @@ class ExecTool(Tool):
self.webui_allow_local_service_access = webui_allow_local_service_access
self.path_prepend = path_prepend
self.path_append = path_append
self.sandbox_ro_binds = self._normalize_bind_roots(sandbox_ro_binds)
self.sandbox_rw_binds = self._normalize_bind_roots(sandbox_rw_binds)
self.allowed_env_keys = allowed_env_keys or []
self._session_manager = session_manager or DEFAULT_EXEC_SESSION_MANAGER
@@ -345,7 +337,7 @@ class ExecTool(Tool):
# misses it, leaving a zombie.
_reap_pid(process.pid)
output_parts: list[str] = []
output_parts = []
if stdout:
output_parts.append(stdout.decode("utf-8", errors="replace"))
@@ -472,14 +464,7 @@ class ExecTool(Tool):
)
else:
workspace = workspace_root or cwd
command = wrap_command(
self.sandbox,
command,
workspace,
cwd,
sandbox_ro_binds=[str(p) for p in self.sandbox_ro_binds],
sandbox_rw_binds=[str(p) for p in self.sandbox_rw_binds],
)
command = wrap_command(self.sandbox, command, workspace, cwd)
cwd = str(Path(workspace).resolve())
effective_timeout = self._resolve_timeout(timeout)
@@ -505,7 +490,7 @@ class ExecTool(Tool):
)
def _compose_path(self, current_path: str) -> str:
parts: list[str] = []
parts = []
if self.path_prepend:
parts.append(self.path_prepend)
if current_path:
@@ -515,7 +500,7 @@ class ExecTool(Tool):
return os.pathsep.join(parts)
def _wrap_path_export(self, command: str, env: dict[str, str]) -> str:
segments: list[str] = []
segments = []
if self.path_prepend:
env["NANOBOT_PATH_PREPEND"] = self.path_prepend
segments.append("$NANOBOT_PATH_PREPEND")
@@ -556,7 +541,6 @@ class ExecTool(Tool):
command = ExecTool._normalize_powershell_command(command)
command = (
"[Console]::OutputEncoding = [System.Text.UTF8Encoding]::new($false)\n"
"if ($PSVersionTable.PSVersion.Major -lt 6) { $OutputEncoding = [Console]::OutputEncoding }\n"
"$PSDefaultParameterValues['Out-File:Encoding'] = 'utf8'\n"
f"{command}\n"
"if ($LASTEXITCODE -ne $null) { exit $LASTEXITCODE }"
@@ -570,21 +554,11 @@ class ExecTool(Tool):
env=env,
)
shell_program = shell_program or shutil.which("bash") or "/bin/bash"
args: list[str] = [shell_program]
args = [shell_program]
shell_name = Path(shell_program).name.lower()
if login and shell_name in {"bash", "bash.exe", "zsh", "zsh.exe"}:
args.append("-l")
args.extend(["-c", command])
if process_tree:
return await asyncio.create_subprocess_exec(
*args,
stdin=stdin,
stdout=asyncio.subprocess.PIPE,
stderr=asyncio.subprocess.PIPE,
cwd=cwd,
env=env,
start_new_session=True,
)
return await asyncio.create_subprocess_exec(
*args,
stdin=stdin,
@@ -592,6 +566,7 @@ class ExecTool(Tool):
stderr=asyncio.subprocess.PIPE,
cwd=cwd,
env=env,
**({"start_new_session": True} if process_tree else {}),
)
@staticmethod
@@ -819,9 +794,6 @@ class ExecTool(Tool):
if workspace_root
else None
)
sandbox_bind_roots = self._active_sandbox_bind_roots(
resolved_workspace or cwd_path
)
for raw in self._extract_absolute_paths(cmd):
try:
@@ -845,8 +817,6 @@ class ExecTool(Tool):
)
if not allowed and resolved_workspace is not None:
allowed = is_path_within(p, resolved_workspace)
if not allowed and sandbox_bind_roots:
allowed = any(is_path_within(p, root) for root in sandbox_bind_roots)
if p.is_absolute() and not allowed:
return ToolResult.error(
"Error: Command blocked by safety guard (path outside working dir)"
@@ -951,38 +921,3 @@ class ExecTool(Tool):
posix_paths = re.findall(r"(?:^|[\s|>='\"])(/[^\s\"'>;|<]+)", command) # POSIX: /absolute only
home_paths = re.findall(r"(?:^|[\s>='\"])(~[/+][^\s\"'>;|<]*)", command) # POSIX/Windows home shortcut: ~/ or ~+
return win_paths + posix_paths + home_paths
@staticmethod
def _normalize_bind_roots(paths: list[str] | None) -> list[Path]:
roots: list[Path] = []
seen: set[str] = set()
for raw in paths or []:
value = str(raw).strip()
if not value:
continue
path = Path(os.path.expandvars(value)).expanduser()
if not path.is_absolute():
continue
with suppress(OSError, RuntimeError, ValueError):
resolved = path.resolve(strict=False)
key = os.path.normcase(os.fspath(resolved))
if key in seen:
continue
seen.add(key)
roots.append(resolved)
return roots
def _active_sandbox_bind_roots(
self,
workspace_root: Path | None = None,
) -> list[Path]:
if self.sandbox != "bwrap" or _IS_WINDOWS:
return []
roots = [*self.sandbox_ro_binds, *self.sandbox_rw_binds]
if workspace_root is None:
return roots
return [
root
for root in roots
if not is_path_within(workspace_root, root)
]
+2 -8
View File
@@ -1,7 +1,5 @@
"""Spawn tool for creating background subagents."""
# pyright: reportIncompatibleMethodOverride=false
from __future__ import annotations
from typing import TYPE_CHECKING, Any
@@ -18,7 +16,6 @@ from nanobot.security.workspace_access import current_workspace_scope
if TYPE_CHECKING:
from nanobot.agent.subagent import SubagentManager
from nanobot.agent.tools.context import ToolContext
@tool_parameters(
@@ -52,11 +49,8 @@ class SpawnTool(Tool):
self._manager = manager
@classmethod
def create(cls, ctx: ToolContext) -> Tool:
manager = ctx.subagent_manager
if manager is None:
raise RuntimeError("SpawnTool requires an initialized subagent manager")
return cls(manager=manager)
def create(cls, ctx: Any) -> Tool:
return cls(manager=ctx.subagent_manager)
@property
def name(self) -> str:
+58 -102
View File
@@ -1,7 +1,5 @@
"""Web tools: web_search and web_fetch."""
# pyright: reportIncompatibleMethodOverride=false
from __future__ import annotations
import asyncio
@@ -9,8 +7,7 @@ import html
import json
import os
import re
from collections.abc import Callable
from typing import Any, cast
from typing import Any, Callable
from urllib.parse import quote, urljoin, urlparse
import httpx
@@ -18,7 +15,6 @@ from loguru import logger
from pydantic import Field
from nanobot.agent.tools.base import Tool, ToolResult, tool_parameters
from nanobot.agent.tools.context import ToolContext
from nanobot.agent.tools.schema import (
BooleanSchema,
IntegerSchema,
@@ -275,12 +271,13 @@ def _normalize_volcengine_auth_level(value: Any) -> int | None:
@tool_parameters(
tool_parameters_schema(
query=StringSchema("Search query"),
count=IntegerSchema(description="Results (1-10)", minimum=1, maximum=10),
count=IntegerSchema(1, description="Results (1-10)", minimum=1, maximum=10),
timeRange=StringSchema(
"Optional time filter for providers that support it: "
"OneDay, OneWeek, OneMonth, OneYear, or YYYY-MM-DD..YYYY-MM-DD",
),
authLevel=IntegerSchema(
0,
description="Optional authority filter for providers that support it: 0=all, 1=authoritative",
minimum=0,
maximum=1,
@@ -295,8 +292,8 @@ class WebSearchTool(Tool):
"""Search the web using configured provider."""
_scopes = {"core", "subagent"}
name = "web_search" # pyright: ignore[reportIncompatibleMethodOverride, reportAssignmentType]
description = ( # pyright: ignore[reportIncompatibleMethodOverride, reportAssignmentType]
name = "web_search"
description = (
"Search the web. Returns titles, URLs, and snippets. "
"count defaults to 5 (max 10). "
"Some providers support timeRange, authLevel, and queryRewrite. "
@@ -306,21 +303,20 @@ class WebSearchTool(Tool):
config_key = "web"
@classmethod
def config_cls(cls) -> type[WebToolsConfig]:
def config_cls(cls):
return WebToolsConfig
@classmethod
def enabled(cls, ctx: ToolContext) -> bool:
def enabled(cls, ctx: Any) -> bool:
return ctx.config.web.enable
@classmethod
def create(cls, ctx: ToolContext) -> Tool:
config_loader: Callable[[], WebSearchConfig] | None = None
def create(cls, ctx: Any) -> Tool:
config_loader = None
if ctx.provider_snapshot_loader is not None:
def _load_search_config() -> WebSearchConfig:
def config_loader():
from nanobot.config.loader import load_config, resolve_config_env_vars
return resolve_config_env_vars(load_config()).tools.web.search
config_loader = _load_search_config
return cls(
config=ctx.config.web.search,
proxy=ctx.config.web.proxy,
@@ -409,7 +405,7 @@ class WebSearchTool(Tool):
auth_level: int | None = None,
query_rewrite: bool | None = None,
**kwargs: Any,
) -> str: # pyright: ignore[reportIncompatibleMethodOverride]
) -> str:
self._refresh_config()
provider = self.config.provider.strip().lower() or "brave"
n = min(max(count or self.config.max_results, 1), 10)
@@ -453,20 +449,15 @@ class WebSearchTool(Tool):
async def _search_olostep(self, query: str, n: int) -> str:
try:
from olostep import ( # pyright: ignore[reportMissingImports]
AsyncOlostep, # pyright: ignore[reportUnknownVariableType]
Olostep_BaseError, # pyright: ignore[reportUnknownVariableType]
)
from olostep import AsyncOlostep, Olostep_BaseError
except ImportError:
return ToolResult.error("Error: olostep package not installed. Run: pip install olostep")
async_olostep = cast(Any, AsyncOlostep)
olostep_base_error = cast(type[Exception], Olostep_BaseError)
api_key = self.config.api_key or os.environ.get("OLOSTEP_API_KEY", "")
if not api_key:
logger.warning("OLOSTEP_API_KEY not set, falling back to DuckDuckGo")
return await self._search_duckduckgo(query, n)
try:
async with async_olostep(api_key=api_key) as client:
async with AsyncOlostep(api_key=api_key) as client:
if self.proxy:
transport = getattr(client, "_transport", None)
http_client = getattr(transport, "_client", None)
@@ -482,16 +473,14 @@ class WebSearchTool(Tool):
),
http2=True,
)
result: Any = await client.answers.create(task=query)
result = await client.answers.create(task=query)
sources = cast(list[Any], getattr(result, "sources", None) or [])
source_lines: list[str] = []
for i, source_value in enumerate(sources[:n], 1):
source: Any = source_value
sources = getattr(result, "sources", None) or []
source_lines = []
for i, source in enumerate(sources[:n], 1):
if isinstance(source, dict):
source_dict = cast(dict[str, Any], source)
title = source_dict.get("title", "")
url = source_dict.get("url", "")
title = source.get("title", "")
url = source.get("url", "")
else:
title = getattr(source, "title", "")
url = getattr(source, "url", "")
@@ -505,7 +494,7 @@ class WebSearchTool(Tool):
answer_text = getattr(result, "answer", "") or ""
items = [{"title": answer_text or "Olostep answer", "url": "", "content": "\n".join(source_lines)}]
return _format_results(query, items, n)
except olostep_base_error as e:
except Olostep_BaseError as e:
return ToolResult.error(f"Error: Olostep search error: {type(e).__name__}: {e}")
except Exception as e:
return ToolResult.error(f"Error: Olostep search error: {type(e).__name__}: {e}")
@@ -522,7 +511,6 @@ class WebSearchTool(Tool):
"User-Agent": self.user_agent,
}
async with httpx.AsyncClient(proxy=self.proxy) as client:
r: httpx.Response | None = None
for attempt in range(2):
r = await client.get(
"https://api.search.brave.com/res/v1/web/search",
@@ -535,7 +523,6 @@ class WebSearchTool(Tool):
if attempt == 0:
logger.warning("Brave search rate limited; retrying once in 1.0s")
await asyncio.sleep(1.0)
assert r is not None
r.raise_for_status()
items = [
{"title": x.get("title", ""), "url": x.get("url", ""), "content": x.get("description", "")}
@@ -705,19 +692,13 @@ class WebSearchTool(Tool):
timeout=float(self.config.timeout),
)
r.raise_for_status()
data = cast(dict[str, Any], r.json())
items: list[dict[str, Any]] = []
for result_value in cast(list[object], data.get("results", [])):
if not isinstance(result_value, dict):
items = []
for result in r.json().get("results", []):
if not isinstance(result, dict):
continue
result = cast(dict[str, Any], result_value)
highlights: Any = result.get("highlights") or []
highlights = result.get("highlights") or []
if isinstance(highlights, list):
content = "\n".join(
str(highlight)
for highlight in cast(list[object], highlights)
if highlight
)
content = "\n".join(str(highlight) for highlight in highlights if highlight)
else:
content = str(highlights)
if not content:
@@ -757,17 +738,14 @@ class WebSearchTool(Tool):
timeout=float(self.config.timeout),
)
r.raise_for_status()
data = cast(dict[str, Any], r.json())
organic = cast(list[object], data.get("organic", []))
items: list[dict[str, Any]] = [
items = [
{
"title": result.get("title", ""),
"url": result.get("link", ""),
"content": result.get("snippet", ""),
}
for result_value in organic
if isinstance(result_value, dict)
for result in (cast(dict[str, Any], result_value),)
for result in r.json().get("organic", [])
if isinstance(result, dict)
]
return _format_results(query, items, n)
except httpx.HTTPStatusError as e:
@@ -829,7 +807,7 @@ class WebSearchTool(Tool):
timeout=float(self.config.timeout),
)
r.raise_for_status()
data = cast(dict[str, Any], r.json())
data = r.json()
except httpx.HTTPStatusError as e:
if e.response.status_code == 429:
return ToolResult.error("Error: Volcengine search rate limited. Try again later or reduce search frequency.")
@@ -837,36 +815,20 @@ class WebSearchTool(Tool):
except Exception as e:
return ToolResult.error(f"Error: Volcengine search failed: {e}")
response_metadata = cast(
dict[str, Any],
data.get("ResponseMetadata") or {},
)
error = (
response_metadata.get("Error")
or data.get("Error")
or data.get("error")
)
error = (data.get("ResponseMetadata") or {}).get("Error") or data.get("Error") or data.get("error")
if error:
if isinstance(error, dict):
error = cast(dict[str, Any], error)
code = error.get("Code") or error.get("code") or "unknown"
message = error.get("Message") or error.get("message") or error
return ToolResult.error(f"Error: Volcengine search error {code}: {message}")
return ToolResult.error(f"Error: Volcengine search error: {error}")
result = cast(dict[str, Any], data.get("Result") or data)
web_results = cast(
list[object],
result.get("WebResults")
or result.get("webResults")
or result.get("results")
or [],
)
result = data.get("Result") or data
web_results = result.get("WebResults") or result.get("webResults") or result.get("results") or []
items: list[dict[str, Any]] = []
for item_value in web_results:
if not isinstance(item_value, dict):
for item in web_results:
if not isinstance(item, dict):
continue
item = cast(dict[str, Any], item_value)
meta_parts = [
str(part)
for part in (
@@ -876,7 +838,7 @@ class WebSearchTool(Tool):
)
if part
]
summary = cast(str, (
summary = (
item.get("Summary")
or item.get("summary")
or item.get("Snippet")
@@ -884,7 +846,7 @@ class WebSearchTool(Tool):
or item.get("Content")
or item.get("content")
or ""
))
)
content = "\n".join(part for part in (" | ".join(meta_parts), summary) if part)
items.append(
{
@@ -900,20 +862,18 @@ class WebSearchTool(Tool):
try:
# Note: duckduckgo_search is synchronous and does its own requests
# We run it in a thread to avoid blocking the loop
from ddgs import DDGS # pyright: ignore[reportUnknownVariableType]
from ddgs import DDGS
ddgs_type = cast(Any, DDGS)
ddgs = ddgs_type(timeout=10, proxy=self.proxy)
ddgs = DDGS(timeout=10, proxy=self.proxy)
raw = await asyncio.wait_for(
asyncio.to_thread(ddgs.text, query, max_results=n),
timeout=self.config.timeout,
)
if not raw:
return f"No results for: {query}"
raw_items = cast(list[dict[str, Any]], raw)
items: list[dict[str, Any]] = [
items = [
{"title": r.get("title", ""), "url": r.get("href", ""), "content": r.get("body", "")}
for r in raw_items
for r in raw
]
return _format_results(query, items, n)
except Exception as e:
@@ -948,19 +908,15 @@ class WebSearchTool(Tool):
if r.status_code == 429:
return ToolResult.error("Error: Bocha search rate-limited (HTTP 429). Wait and retry.")
r.raise_for_status()
data = cast(dict[str, Any], r.json())
wrapped_data = data.get("data")
result_data = (
cast(dict[str, Any], wrapped_data)
if isinstance(wrapped_data, dict)
else data
data = r.json()
wrapped_data = data.get("data") if isinstance(data, dict) else None
result_data = wrapped_data if isinstance(wrapped_data, dict) else data
web_pages = (
result_data.get("webPages", {}).get("value", [])
if isinstance(result_data, dict)
else []
)
web_pages_data = cast(
dict[str, Any],
result_data.get("webPages", {}),
)
web_pages = cast(list[dict[str, Any]], web_pages_data.get("value", []))
items: list[dict[str, Any]] = [
items = [
{
"title": x.get("name", ""),
"url": x.get("url", ""),
@@ -983,7 +939,7 @@ class WebSearchTool(Tool):
"enum": ["markdown", "text"],
"default": "markdown",
},
maxChars=IntegerSchema(minimum=100),
maxChars=IntegerSchema(0, minimum=100),
required=["url"],
)
)
@@ -991,8 +947,8 @@ class WebFetchTool(Tool):
"""Fetch and extract content from a URL."""
_scopes = {"core", "subagent"}
name = "web_fetch" # pyright: ignore[reportIncompatibleMethodOverride, reportAssignmentType]
description = ( # pyright: ignore[reportIncompatibleMethodOverride, reportAssignmentType]
name = "web_fetch"
description = (
"Fetch a URL and extract readable content (HTML → markdown/text). "
"Output is capped at maxChars (default 50 000). "
"Works for most web pages and docs; may fail on login-walled or JS-heavy sites."
@@ -1001,15 +957,15 @@ class WebFetchTool(Tool):
config_key = "web"
@classmethod
def config_cls(cls) -> type[WebToolsConfig]:
def config_cls(cls):
return WebToolsConfig
@classmethod
def enabled(cls, ctx: ToolContext) -> bool:
def enabled(cls, ctx: Any) -> bool:
return ctx.config.web.enable
@classmethod
def create(cls, ctx: ToolContext) -> Tool:
def create(cls, ctx: Any) -> Tool:
return cls(
config=ctx.config.web.fetch,
proxy=ctx.config.web.proxy,
@@ -1032,10 +988,10 @@ class WebFetchTool(Tool):
extract_mode: str = "markdown",
max_chars: int | None = None,
**kwargs: Any,
) -> Any: # pyright: ignore[reportIncompatibleMethodOverride]
) -> Any:
url = url.strip(" \t\r\n`\"'")
extract_mode = kwargs.pop("extractMode", extract_mode)
max_chars = cast(int, kwargs.pop("maxChars", max_chars) or self.max_chars)
max_chars = kwargs.pop("maxChars", max_chars) or self.max_chars
is_valid, error_msg = _validate_url_safe(url)
if not is_valid:
return json.dumps({"error": f"URL validation failed: {error_msg}", "url": url}, ensure_ascii=False)
@@ -1164,10 +1120,10 @@ class WebFetchTool(Tool):
return json.dumps({"error": str(e), "url": url}, ensure_ascii=False)
def _extract_readable_html(self, html_content: str, extract_mode: str) -> str:
from readability import Document # pyright: ignore[reportMissingTypeStubs]
from readability import Document
doc = Document(html_content)
summary = cast(str, doc.summary())
summary = doc.summary()
content = self._to_markdown(summary) if extract_mode == "markdown" else _strip_tags(summary)
return f"# {doc.title()}\n\n{content}" if doc.title() else content
+5 -23
View File
@@ -6,7 +6,7 @@ import dataclasses
import time
from collections.abc import Awaitable, Callable
from dataclasses import dataclass, field
from typing import TYPE_CHECKING, Any, cast
from typing import Any
from nanobot.bus.events import InboundMessage, OutboundMessage
from nanobot.bus.outbound_events import (
@@ -20,9 +20,6 @@ from nanobot.bus.progress import build_bus_progress_callback
from nanobot.bus.queue import MessageBus
from nanobot.bus.runtime_events import RuntimeEventBus, RuntimeEventPublisher
if TYPE_CHECKING:
from nanobot.utils.llm_runtime import LLMRuntime
@dataclass(frozen=True)
class TurnRoute:
@@ -65,7 +62,7 @@ class TurnDeliveryFactory:
route = self._default_route(msg, session_key)
if self.route_policy is not None:
route = self.route_policy(msg, session_key, route)
if not isinstance(cast(object, route), TurnRoute):
if not isinstance(route, TurnRoute):
raise TypeError("turn route policy must return TurnRoute")
return TurnDelivery(
bus=self.bus,
@@ -129,7 +126,6 @@ class TurnDelivery:
lifecycle_message: InboundMessage = field(init=False)
_stream_base_id: str | None = field(init=False, default=None)
_stream_segment: int = field(init=False, default=0)
_stream_open: bool = field(init=False, default=False)
def __post_init__(self) -> None:
self.delivery_message = dataclasses.replace(
@@ -189,7 +185,7 @@ class TurnDelivery:
started_at=started_at,
)
def record_runtime(self, runtime: LLMRuntime) -> None:
def record_runtime(self, runtime: Any) -> None:
self.runtime_event_publisher.record_turn_runtime(self.session_key, runtime)
def record_latency(self, latency_ms: int | None) -> None:
@@ -288,14 +284,8 @@ class TurnDelivery:
metadata=self.delivery_message.metadata,
)
)
self._stream_open = True
async def _publish_stream_end(
self,
*,
resuming: bool = False,
merge_next: bool = False,
) -> None:
async def _publish_stream_end(self, *, resuming: bool = False) -> None:
await self.bus.publish_outbound(
outbound_message_for_event(
channel=self.delivery_message.channel,
@@ -303,16 +293,8 @@ class TurnDelivery:
event=StreamEndEvent(
stream_id=self._stream_id(),
resuming=resuming,
merge_next=merge_next,
),
metadata=self.delivery_message.metadata,
)
)
self._stream_open = merge_next
if not merge_next:
self._stream_segment += 1
async def abort_stream(self) -> None:
"""Close an interrupted stream so stateful channels can release its buffer."""
if self._stream_open:
await self._publish_stream_end()
self._stream_segment += 1
-2
View File
@@ -39,7 +39,6 @@ class AgentTurnHookSpec:
turn_hooks: list[AgentHook] = field(default_factory=list)
ephemeral: bool = False
run_extra_hooks_for_ephemeral: bool = False
attributes: dict[str, Any] | None = None
def build_agent_turn_hook(spec: AgentTurnHookSpec) -> AgentHook:
@@ -63,7 +62,6 @@ def build_agent_turn_hook(spec: AgentTurnHookSpec) -> AgentHook:
message_id=spec.message_id,
session_key=spec.session_key,
metadata=dict(spec.metadata or {}),
attributes=dict(spec.attributes or {}),
ephemeral=spec.ephemeral,
)
hook_chain: list[AgentHook] = [progress_hook]
+1 -1
View File
@@ -35,7 +35,7 @@ def api_runtime_paths(config_path: Path) -> ProcessRuntimePaths:
)
class ApiRuntime(ManagedProcessRuntime[ApiStartOptions]):
class ApiRuntime(ManagedProcessRuntime):
"""Manage a WebUI-controlled OpenAI-compatible API process."""
service_name = "api"
+18 -64
View File
@@ -12,7 +12,7 @@ import hmac
import json as _json
import time
import uuid
from typing import TYPE_CHECKING, Any, Awaitable, Callable, cast
from typing import Any
from aiohttp import web
from loguru import logger
@@ -30,9 +30,6 @@ from nanobot.utils.media_decode import (
)
from nanobot.utils.runtime import EMPTY_FINAL_RESPONSE_MESSAGE
if TYPE_CHECKING:
from nanobot.agent.loop import AgentLoop
__all__ = (
"MAX_FILE_SIZE",
"_FileSizeExceeded",
@@ -47,7 +44,7 @@ API_CHAT_ID = "default"
_AGENT_LOOP_KEY = web.AppKey[Any]("agent_loop")
_MODEL_NAME_KEY = web.AppKey[str]("model_name")
_REQUEST_TIMEOUT_KEY = web.AppKey[float]("request_timeout")
_SESSION_LOCKS_KEY = web.AppKey[dict[str, asyncio.Lock]]("session_locks")
_SESSION_LOCKS_KEY = web.AppKey[dict]("session_locks")
_MISSING = object()
@@ -114,26 +111,6 @@ def _response_text(value: Any) -> str:
return str(getattr(value, "content") or "")
return str(value)
def _as_str(value: object) -> str:
"""Return *value* when it is text, otherwise an empty string."""
return value if isinstance(value, str) else ""
def _require_json_object(value: object, field: str) -> dict[str, Any]:
"""Validate an object-valued field from an untrusted JSON request."""
if not isinstance(value, dict):
raise TypeError(f"{field} must be an object")
return cast(dict[str, Any], value)
def _require_json_string(value: object, field: str) -> str:
"""Validate a string-valued field from an untrusted JSON request."""
if not isinstance(value, str):
raise TypeError(f"{field} must be a string")
return value
# ---------------------------------------------------------------------------
# SSE helpers
# ---------------------------------------------------------------------------
@@ -164,19 +141,13 @@ _SSE_DONE = b"data: [DONE]\n\n"
# ---------------------------------------------------------------------------
def _parse_json_content(body: dict[str, Any]) -> tuple[str, list[str]]:
def _parse_json_content(body: dict) -> tuple[str, list[str]]:
"""Parse JSON request body. Returns (text, media_paths)."""
messages_value = cast(object, body.get("messages"))
if not isinstance(messages_value, list):
messages = body.get("messages")
if not isinstance(messages, list) or len(messages) != 1:
raise ValueError("Only a single user message is supported")
messages = cast(list[object], messages_value)
if len(messages) != 1:
raise ValueError("Only a single user message is supported")
message_value: object = messages[0]
if not isinstance(message_value, dict):
raise ValueError("Only a single user message is supported")
message = cast(dict[str, Any], message_value)
if message.get("role") != "user":
message = messages[0]
if not isinstance(message, dict) or message.get("role") != "user":
raise ValueError("Only a single user message is supported")
user_content = message.get("content", "")
@@ -185,26 +156,13 @@ def _parse_json_content(body: dict[str, Any]) -> tuple[str, list[str]]:
if isinstance(user_content, list):
text_parts: list[str] = []
for part_value in cast(list[object], user_content):
if not isinstance(part_value, dict):
for part in user_content:
if not isinstance(part, dict):
continue
part = cast(dict[str, Any], part_value)
if part.get("type") == "text":
text_parts.append(
_require_json_string(
cast(object, part.get("text", "")),
"messages[0].content[].text",
)
)
text_parts.append(part.get("text", ""))
elif part.get("type") == "image_url":
image_url = _require_json_object(
cast(object, part.get("image_url", {})),
"messages[0].content[].image_url",
)
url = _require_json_string(
cast(object, image_url.get("url", "")),
"messages[0].content[].image_url.url",
)
url = part.get("image_url", {}).get("url", "")
if url.startswith("data:"):
saved = _save_base64_data_url(url, media_dir)
if saved:
@@ -233,7 +191,7 @@ async def _parse_multipart(request: web.Request) -> tuple[str, list[str], str |
media_paths: list[str] = []
while True:
part: Any = await reader.next()
part = await reader.next()
if part is None:
break
if part.name == "message":
@@ -265,9 +223,11 @@ async def _parse_multipart(request: web.Request) -> tuple[str, list[str], str |
# ---------------------------------------------------------------------------
async def handle_chat_completions(request: web.Request) -> web.Response | web.StreamResponse:
async def handle_chat_completions(request: web.Request) -> web.Response:
"""POST /v1/chat/completions — supports JSON and multipart/form-data."""
content_type = _as_str(cast(object, request.content_type or ""))
content_type = request.content_type or ""
if not isinstance(content_type, str):
content_type = ""
agent_loop = _app_value(request.app, _AGENT_LOOP_KEY, "agent_loop")
timeout_s: float = _app_value(
@@ -287,9 +247,6 @@ async def handle_chat_completions(request: web.Request) -> web.Response | web.St
body = await request.json()
except Exception:
return _error_json(400, "Invalid JSON body")
if not isinstance(body, dict):
return _error_json(400, "Invalid JSON body")
body = cast(dict[str, Any], body)
stream = body.get("stream", False)
requested_model = body.get("model")
text, media_paths = _parse_json_content(body)
@@ -448,7 +405,7 @@ async def handle_health(request: web.Request) -> web.Response:
def create_app(
agent_loop: "AgentLoop",
agent_loop,
model_name: str = "nanobot",
request_timeout: float = 120.0,
api_key: str = "",
@@ -468,10 +425,7 @@ def create_app(
app[_SESSION_LOCKS_KEY] = {} # per-user locks, keyed by session_key
@web.middleware
async def auth_middleware(
request: web.Request,
handler: Callable[[web.Request], Awaitable[web.StreamResponse]],
) -> web.StreamResponse:
async def auth_middleware(request: web.Request, handler) -> web.StreamResponse:
# Allow unauthenticated health checks.
if request.path == "/health":
return await handler(request)
+23 -35
View File
@@ -10,11 +10,10 @@ import shutil
import subprocess
import sys
import time
from collections.abc import Iterable
from dataclasses import dataclass
from importlib import metadata as importlib_metadata
from pathlib import Path
from typing import Any, cast
from typing import Any
from urllib.parse import urlparse
import httpx
@@ -205,11 +204,6 @@ def _now() -> float:
return time.time()
def _as_object_dict(value: object) -> dict[str, Any] | None:
"""Narrow a JSON-like object to the string-keyed mapping used by this module."""
return cast(dict[str, Any], value) if isinstance(value, dict) else None
def _safe_skill_name(name: str) -> str:
clean = _SAFE_NAME_RE.sub("-", name.lower()).strip("-")
return f"cli-app-{clean or 'app'}"
@@ -283,11 +277,10 @@ def _console_script_distribution(entry_point: str) -> str | None:
if item.group != "console_scripts" or item.name != entry_point:
continue
try:
name: object = cast(Any, distribution.metadata).get("Name")
name = distribution.metadata.get("Name")
except Exception:
name = None
fallback_name = cast(object, getattr(distribution, "name", ""))
return str(name or fallback_name or "").strip() or None
return str(name or getattr(distribution, "name", "") or "").strip() or None
return None
@@ -342,10 +335,10 @@ def _brand_payload(app: dict[str, Any]) -> tuple[str | None, str | None]:
def _read_json(path: Path) -> dict[str, Any] | None:
try:
data: object = json.loads(path.read_text(encoding="utf-8"))
data = json.loads(path.read_text(encoding="utf-8"))
except (OSError, json.JSONDecodeError):
return None
return _as_object_dict(data)
return data if isinstance(data, dict) else None
def _write_json(path: Path, data: dict[str, Any]) -> None:
@@ -421,8 +414,8 @@ class CliAppManager:
cached = _read_json(cache_path)
if not cached:
return None, 0.0
data = _as_object_dict(cached.get("data"))
if data is None:
data = cached.get("data")
if not isinstance(data, dict):
return None, 0.0
try:
cached_at = float(cached.get("_cached_at", 0))
@@ -432,8 +425,8 @@ class CliAppManager:
def _load_installed(self) -> dict[str, Any]:
data = _read_json(self.installed_path) or {}
apps = _as_object_dict(data.get("apps"))
return apps if apps is not None else data
apps = data.get("apps") if isinstance(data.get("apps"), dict) else data
return apps if isinstance(apps, dict) else {}
def _save_installed(self, installed: dict[str, Any]) -> None:
_write_json(self.installed_path, {"schema_version": 1, "apps": installed})
@@ -460,8 +453,8 @@ class CliAppManager:
try:
response = httpx.get(url, timeout=15.0, follow_redirects=True)
response.raise_for_status()
fetched = _as_object_dict(response.json())
if fetched is None:
fetched = response.json()
if not isinstance(fetched, dict):
raise ValueError("registry response must be an object")
except Exception:
if data is not None:
@@ -490,8 +483,8 @@ class CliAppManager:
async with httpx.AsyncClient(timeout=15.0, follow_redirects=True) as client:
response = await client.get(url)
response.raise_for_status()
fetched = _as_object_dict(response.json())
if fetched is None:
fetched = response.json()
if not isinstance(fetched, dict):
raise ValueError("registry response must be an object")
except Exception:
if data is not None:
@@ -541,14 +534,13 @@ class CliAppManager:
apps_by_name: dict[str, dict[str, Any]] = {}
updated_values: list[str] = []
for source, raw_base, registry in registries:
meta = _as_object_dict(registry.get("meta"))
if meta is not None and isinstance(meta.get("updated"), str):
meta = registry.get("meta")
if isinstance(meta, dict) and isinstance(meta.get("updated"), str):
updated_values.append(meta["updated"])
for row in cast(Iterable[object], registry.get("clis", [])):
entry = _as_object_dict(row)
if entry is None or not entry.get("name"):
for row in registry.get("clis", []):
if not isinstance(row, dict) or not row.get("name"):
continue
entry = dict(entry)
entry = dict(row)
entry["_source"] = source
entry["_raw_base"] = raw_base
key = str(entry["name"]).lower()
@@ -596,7 +588,7 @@ class CliAppManager:
if not installed:
return []
installed_by_name = {
str(name).lower(): (str(name), _as_object_dict(data) or {})
str(name).lower(): (str(name), data if isinstance(data, dict) else {})
for name, data in installed.items()
}
seen: set[str] = set()
@@ -777,14 +769,12 @@ class CliAppManager:
for app in cached_apps
if app.get("name")
}
rows: list[dict[str, Any]] = []
rows = []
for name, raw_entry in sorted(installed.items()):
entry = _as_object_dict(raw_entry)
if entry is None:
entry = {}
entry = raw_entry if isinstance(raw_entry, dict) else {}
strategy = str(entry.get("strategy") or "bundled")
cached_app = cached_by_name.get(str(name).lower(), {})
app: dict[str, Any] = {
app = {
"name": str(name),
"display_name": str(
cached_app.get("display_name") or entry.get("display_name") or name
@@ -1175,9 +1165,7 @@ Use the `run_cli_app` tool with `name="{name}"` for command execution. Do not in
if str(app["name"]) not in installed:
raise CliAppError("CLI app is not installed")
raw_installed_entry = installed.get(str(app["name"]))
installed_entry = _as_object_dict(raw_installed_entry)
if installed_entry is None:
installed_entry = {}
installed_entry = raw_installed_entry if isinstance(raw_installed_entry, dict) else {}
strategy = self._strategy(app)
entry_point = str(app.get("entry_point") or "").strip()
managed_entry_path = str(installed_entry.get("entry_point_path") or "").strip()
+4 -9
View File
@@ -3,7 +3,7 @@
from __future__ import annotations
from pathlib import Path
from typing import Any, Mapping, cast
from typing import Any, Mapping
def session_extra(metadata: Mapping[str, Any] | None) -> dict[str, Any]:
@@ -29,11 +29,9 @@ def runtime_lines_for_request(
"""Return CLI App annotations from an immutable request snapshot."""
structured = metadata.get("cli_apps") if isinstance(metadata, Mapping) else None
if isinstance(structured, list):
structured_items = cast(list[Any], structured)
mentions = [
cast(Mapping[str, Any], item) for item in structured_items
if isinstance(item, Mapping)
and isinstance(cast(Mapping[str, Any], item).get("name"), str)
item for item in structured
if isinstance(item, Mapping) and isinstance(item.get("name"), str)
]
if mentions:
return [
@@ -51,10 +49,7 @@ def runtime_lines_for_request(
try:
from nanobot.apps.cli import CliAppManager
mentions = cast(
list[dict[str, Any]],
CliAppManager(workspace=workspace).mentioned_installed_apps(text),
)
mentions = CliAppManager(workspace=workspace).mentioned_installed_apps(text)
except Exception:
return []
return [
+6 -14
View File
@@ -22,7 +22,6 @@ from nanobot.audio.transcription_registry import (
)
from nanobot.config.loader import resolve_env_refs
from nanobot.config.paths import get_media_dir
from nanobot.config.schema import Config, ProviderConfig
from nanobot.providers.registry import find_by_name
from nanobot.utils.media_decode import FileSizeExceeded, save_base64_data_url
@@ -74,9 +73,8 @@ def _as_provider(value: Any) -> TranscriptionProviderName | None:
return spec.name if spec else None
def _provider_config(config: Config, provider: str) -> ProviderConfig | None:
value = getattr(config.providers, provider, None)
return value if isinstance(value, ProviderConfig) else None
def _provider_config(config: Any, provider: str) -> Any:
return getattr(getattr(config, "providers", None), provider, None)
def _provider_default_api_base(provider: str) -> str | None:
@@ -84,10 +82,7 @@ def _provider_default_api_base(provider: str) -> str | None:
return spec.default_api_base if spec else None
def _resolve_transcription_api_key(
provider: str,
provider_cfg: ProviderConfig | None,
) -> str:
def _resolve_transcription_api_key(provider: str, provider_cfg: Any) -> str:
api_key = resolve_env_refs(getattr(provider_cfg, "api_key", None) or "") if provider_cfg else ""
if api_key:
return api_key
@@ -99,13 +94,10 @@ def _resolve_transcription_api_key(
return env_key
env_key = spec.env_key if spec else ""
return os.environ.get(env_key, "") if env_key else ""
return os.environ.get(env_key) if env_key else ""
def _resolve_transcription_api_base(
provider: str,
provider_cfg: ProviderConfig | None,
) -> str:
def _resolve_transcription_api_base(provider: str, provider_cfg: Any) -> str:
api_base = resolve_env_refs(getattr(provider_cfg, "api_base", None) or "") if provider_cfg else ""
if api_base:
return api_base
@@ -119,7 +111,7 @@ def _extract_data_url_mime(url: str) -> str | None:
return header[5:].split(";", 1)[0].strip().lower() or None
def resolve_transcription_config(config: Config) -> EffectiveTranscriptionConfig:
def resolve_transcription_config(config: Any) -> EffectiveTranscriptionConfig:
"""Resolve top-level transcription settings with legacy channel fallback."""
top = getattr(config, "transcription", None)
channels = getattr(config, "channels", None)
+5 -15
View File
@@ -9,7 +9,7 @@ from __future__ import annotations
from collections.abc import Mapping
from dataclasses import dataclass, replace
from typing import Any, cast
from typing import Any
from nanobot.bus.events import OutboundMessage
@@ -46,7 +46,6 @@ class StreamEndEvent(OutboundEvent):
content: str = ""
stream_id: str | None = None
resuming: bool = False
merge_next: bool = False
@dataclass(frozen=True)
@@ -153,11 +152,7 @@ def _legacy_event_from_metadata(msg: OutboundMessage) -> OutboundEvent | None:
)
if meta.get("_goal_state_sync"):
goal_state = meta.get("goal_state")
return GoalStateSyncEvent(
cast(dict[str, Any], goal_state)
if isinstance(goal_state, dict)
else {"active": False}
)
return GoalStateSyncEvent(goal_state if isinstance(goal_state, dict) else {"active": False})
if meta.get("_goal_status"):
status = meta.get("goal_status")
if not isinstance(status, str) or not status:
@@ -170,7 +165,7 @@ def _legacy_event_from_metadata(msg: OutboundMessage) -> OutboundEvent | None:
goal_state = meta.get("goal_state")
return TurnEndEvent(
latency_ms=_metadata_int(meta, "latency_ms"),
goal_state=cast(dict[str, Any], goal_state) if isinstance(goal_state, dict) else None,
goal_state=goal_state if isinstance(goal_state, dict) else None,
)
if meta.get("_session_updated"):
return SessionUpdatedEvent(scope=_metadata_str(meta, "_session_update_scope"))
@@ -181,7 +176,6 @@ def _legacy_event_from_metadata(msg: OutboundMessage) -> OutboundEvent | None:
content=msg.content,
stream_id=_metadata_str(meta, "_stream_id"),
resuming=bool(meta.get("_resuming")),
merge_next=bool(meta.get("_merge_next")),
)
if meta.get("_stream_delta"):
return StreamDeltaEvent(
@@ -207,12 +201,8 @@ def _legacy_event_from_metadata(msg: OutboundMessage) -> OutboundEvent | None:
reasoning_delta=bool(meta.get("_reasoning_delta")),
reasoning_end=bool(meta.get("_reasoning_end")),
stream_id=_metadata_str(meta, "_stream_id"),
tool_events=cast(list[dict[str, Any]], tool_events)
if isinstance(tool_events, list)
else None,
file_edit_events=cast(list[dict[str, Any]], file_edit_events)
if isinstance(file_edit_events, list)
else None,
tool_events=tool_events if isinstance(tool_events, list) else None,
file_edit_events=file_edit_events if isinstance(file_edit_events, list) else None,
)
return None
+20 -43
View File
@@ -12,15 +12,12 @@ import contextlib
import inspect
from collections.abc import Awaitable, Callable
from dataclasses import dataclass, field
from typing import TYPE_CHECKING, Any
from typing import Any
from loguru import logger
from nanobot.bus.events import InboundMessage
if TYPE_CHECKING:
from nanobot.utils.llm_runtime import LLMRuntime
@dataclass(frozen=True)
class RuntimeEventContext:
@@ -30,7 +27,6 @@ class RuntimeEventContext:
chat_id: str
session_key: str
metadata: dict[str, Any] = field(default_factory=dict)
attributes: dict[str, Any] = field(default_factory=dict)
@dataclass(frozen=True)
@@ -55,16 +51,7 @@ class TurnCompleted:
context: RuntimeEventContext
latency_ms: int | None = None
runtime: LLMRuntime | None = None
@dataclass(frozen=True)
class SessionTurnPersisted:
"""A completed turn has been written to local session storage."""
context: RuntimeEventContext
turn_id: str
sender_id: str
runtime: Any | None = None
@dataclass(frozen=True)
@@ -85,7 +72,6 @@ class RuntimeModelChanged:
RuntimeEvent = (
SessionTurnStarted
| SessionTurnPersisted
| TurnRunStatusChanged
| TurnCompleted
| GoalStateChanged
@@ -93,7 +79,6 @@ RuntimeEvent = (
)
RuntimeEventType = (
type[SessionTurnStarted]
| type[SessionTurnPersisted]
| type[TurnRunStatusChanged]
| type[TurnCompleted]
| type[GoalStateChanged]
@@ -158,7 +143,7 @@ class RuntimeEventPublisher:
def __init__(self, bus: RuntimeEventBus | None = None) -> None:
self.bus = bus or RuntimeEventBus()
self._turn_latency_ms: dict[str, int] = {}
self._turn_runtime: dict[str, LLMRuntime] = {}
self._turn_runtime: dict[str, Any] = {}
@staticmethod
def _context(
@@ -167,17 +152,15 @@ class RuntimeEventPublisher:
chat_id: str,
session_key: str,
metadata: dict[str, Any] | None,
attributes: dict[str, Any] | None = None,
) -> RuntimeEventContext:
return RuntimeEventContext(
channel=channel,
chat_id=chat_id,
session_key=session_key,
metadata=dict(metadata or {}),
attributes=dict(attributes or {}),
)
def record_turn_runtime(self, session_key: str, runtime: LLMRuntime) -> None:
def record_turn_runtime(self, session_key: str, runtime: Any) -> None:
self._turn_runtime[session_key] = runtime
def record_turn_latency(self, session_key: str, latency_ms: int | None) -> None:
@@ -225,28 +208,6 @@ class RuntimeEventPublisher:
)
)
async def session_turn_persisted(
self,
msg: InboundMessage,
session_key: str,
*,
turn_id: str,
attributes: dict[str, Any] | None = None,
) -> None:
await self.bus.publish(
SessionTurnPersisted(
context=self._context(
channel=msg.channel,
chat_id=msg.chat_id,
session_key=session_key,
metadata=msg.metadata,
attributes=attributes,
),
turn_id=turn_id,
sender_id=msg.sender_id,
)
)
async def turn_completed(
self,
*,
@@ -272,3 +233,19 @@ class RuntimeEventPublisher:
self.bus.publish_nowait(
RuntimeModelChanged(model=model, model_preset=model_preset)
)
def ensure_runtime_event_publisher(owner: Any) -> RuntimeEventPublisher:
"""Return an owner's runtime publisher, creating missing state lazily."""
publisher = getattr(owner, "runtime_event_publisher", None)
if isinstance(publisher, RuntimeEventPublisher):
return publisher
bus = getattr(owner, "runtime_events", None)
if not isinstance(bus, RuntimeEventBus):
bus = RuntimeEventBus()
owner.runtime_events = bus
publisher = RuntimeEventPublisher(bus)
owner.runtime_event_publisher = publisher
return publisher
+5 -25
View File
@@ -4,7 +4,7 @@ from __future__ import annotations
from abc import ABC, abstractmethod
from pathlib import Path
from typing import Any, cast
from typing import Any
from loguru import logger
@@ -29,7 +29,7 @@ class BaseChannel(ABC):
name: str = "base"
display_name: str = "Base"
send_progress: bool = True
send_tool_hints: bool = True
send_tool_hints: bool = False
show_reasoning: bool = True
def __init__(self, config: Any, bus: MessageBus):
@@ -110,7 +110,6 @@ class BaseChannel(ABC):
stream_id: str | None = None,
stream_end: bool = False,
resuming: bool = False,
merge_next: bool = False,
) -> None:
"""Deliver a streaming text chunk.
@@ -119,9 +118,6 @@ class BaseChannel(ABC):
Stateful implementations should key buffers by ``stream_id`` rather
than only by ``chat_id`` when it is provided.
``merge_next`` marks a resumable provider boundary whose next text
segment belongs to the same user-visible message.
"""
pass
@@ -201,21 +197,13 @@ class BaseChannel(ABC):
def supports_streaming(self) -> bool:
"""True when config enables streaming AND this subclass implements send_delta."""
cfg = self.config
config_mapping = cast(dict[str, Any], cfg) if isinstance(cfg, dict) else None
streaming: Any = (
config_mapping.get("streaming", False)
if config_mapping is not None
else getattr(cast(Any, cfg), "streaming", False)
)
streaming = cfg.get("streaming", False) if isinstance(cfg, dict) else getattr(cfg, "streaming", False)
return bool(streaming) and type(self).send_delta is not BaseChannel.send_delta
def is_allowed(self, sender_id: str) -> bool:
"""Check sender permission: star > allowlist > pairing store > deny."""
if isinstance(self.config, dict):
config_mapping = cast(dict[str, Any], self.config)
allow_list: Any = (
config_mapping.get("allow_from") or config_mapping.get("allowFrom") or []
)
allow_list = self.config.get("allow_from") or self.config.get("allowFrom") or []
else:
allow_list = getattr(self.config, "allow_from", None) or []
if "*" in allow_list:
@@ -248,15 +236,7 @@ class BaseChannel(ABC):
permission_id = authorization_id if authorization_id is not None else sender_id
if not self.is_allowed(permission_id):
if is_dm:
try:
code = generate_code(self.name, str(sender_id))
except OSError:
# Transient pairing-store I/O failure: skip the pairing
# reply for this message rather than crash the handler.
self.logger.warning(
"Pairing store unavailable; dropping DM from {}", sender_id
)
return
code = generate_code(self.name, str(sender_id))
await self.send(
OutboundMessage(
channel=self.name,
+33 -62
View File
@@ -6,7 +6,7 @@ from collections.abc import Iterable
from copy import deepcopy
from dataclasses import dataclass
from pathlib import Path
from typing import TYPE_CHECKING, Any, Callable, Literal, TypeGuard, cast
from typing import TYPE_CHECKING, Any, Callable, Literal
if TYPE_CHECKING:
from nanobot.channels.plugin import ChannelPlugin
@@ -22,8 +22,6 @@ class ChannelValidationContext:
allow_local_service_access: bool = False
# Keep callback contracts precise for static consumers. The public adapters below
# still validate third-party implementations at runtime.
SetupValidator = Callable[[dict[str, Any], ChannelValidationContext], dict[str, Any]]
DefaultConfigFactory = Callable[[], dict[str, Any]]
InstanceSpecsFactory = Callable[..., Iterable["ChannelInstanceSpec"]]
@@ -89,7 +87,7 @@ class ChannelActivation:
instances = (
tuple(
cls.from_config(item, include_instances=True)
for item in cast(list[Any], raw_instances)
for item in raw_instances
if _config_mapping(item) is not None
)
if isinstance(raw_instances, list)
@@ -195,7 +193,7 @@ class ChannelSetupSpec:
def to_public_dict(self, channel_name: str) -> dict[str, Any]:
"""Serialize the writable setup contract for generic WebUI consumers."""
simple_required = set(self.simple_required_fields)
fields: list[dict[str, Any]] = []
fields = []
for name, field in self.fields.items():
if not field.writable:
continue
@@ -270,37 +268,35 @@ def channel_default_config(plugin: ChannelPlugin) -> dict[str, Any]:
defaults: dict[str, Any] = {"enabled": plugin.default_enabled}
if plugin.setup is not None:
for name, field in plugin.setup.fields.items():
value: Any = field.default
value = field.default
if value is None:
fallback_defaults: dict[str, Any] = {
value = {
"string": "",
"secret": "",
"list": [],
"bool": False,
}
value = fallback_defaults.get(field.kind, _MISSING)
}.get(field.kind, _MISSING)
if value is not _MISSING:
_assign_channel_field(defaults, name, deepcopy(value))
factory = plugin.management.default_config
if factory is None:
return defaults
values_raw = cast(object, factory())
if not isinstance(values_raw, dict):
values = factory()
if not isinstance(values, dict):
raise TypeError(f"ChannelPlugin.management.default_config for '{plugin.name}' must return a dict")
values = cast(dict[str, Any], values_raw)
return cast(dict[str, Any], merge_missing_defaults(values, defaults))
return merge_missing_defaults(values, defaults)
def _assign_channel_field(values: dict[str, Any], field: str, value: Any) -> None:
target = values
parts = field.split(".")
for part in parts[:-1]:
nested: object = target.get(part)
nested = target.get(part)
if not isinstance(nested, dict):
nested = {}
target[part] = nested
target = cast(dict[str, Any], nested)
target = nested
target[parts[-1]] = value
@@ -331,28 +327,27 @@ def channel_instance_specs(
factory = plugin.management.instance_specs
if factory is None:
activation = ChannelActivation.from_config(section)
raw_specs: object = (
raw_specs: Iterable[ChannelInstanceSpec] = (
[]
if enabled_only and not activation.resolve(default=plugin.default_enabled)
else [ChannelInstanceSpec(instance_id="default", config=section)]
)
else:
raw_specs = cast(object, factory(section, enabled_only=enabled_only))
raw_specs = factory(section, enabled_only=enabled_only)
if not isinstance(raw_specs, Iterable):
raise TypeError(
f"ChannelPlugin.management.instance_specs for '{plugin.name}' must return an iterable"
)
specs = list(cast(Iterable[object], raw_specs))
if not _all_channel_instance_specs(specs):
raise TypeError(
f"ChannelPlugin.management.instance_specs for '{plugin.name}' returned an invalid item"
)
specs = list(raw_specs)
instance_ids: set[str] = set()
runtime_names: set[str] = set()
for spec in specs:
instance_id = cast(object, spec.instance_id)
if not isinstance(instance_id, str) or not instance_id.strip():
if not isinstance(spec, ChannelInstanceSpec):
raise TypeError(
f"ChannelPlugin.management.instance_specs for '{plugin.name}' returned an invalid item"
)
if not isinstance(spec.instance_id, str) or not spec.instance_id.strip():
raise ValueError(
f"ChannelPlugin.management.instance_specs for '{plugin.name}' returned an empty instance id"
)
@@ -372,12 +367,6 @@ def channel_instance_specs(
return specs
def _all_channel_instance_specs(
values: list[object],
) -> TypeGuard[list[ChannelInstanceSpec]]:
return all(isinstance(value, ChannelInstanceSpec) for value in values)
def resolve_channel_action_target(
requested_instance_id: str | None,
) -> str:
@@ -404,17 +393,8 @@ def channel_instance_config(
return {}
config = selected.config
if hasattr(config, "model_dump"):
dumped: dict[str, Any] = config.model_dump(mode="json", by_alias=True)
copied: dict[str, Any] = {}
for key in dumped:
copied[key] = dumped[key]
return copied
if not isinstance(config, dict):
return {}
copied_config: dict[str, Any] = {}
for key, value in cast(dict[object, Any], config).items():
copied_config[cast(str, key)] = value
return copied_config
return dict(config.model_dump(mode="json", by_alias=True))
return dict(config) if isinstance(config, dict) else {}
def channel_update_instance_config(
@@ -429,10 +409,7 @@ def channel_update_instance_config(
if instance_id not in {"", "default"}:
raise ValueError(f"{plugin.name} does not support multiple instances")
return values
updated = cast(object, updater(section, values, instance_id=instance_id))
if not isinstance(updated, dict):
raise TypeError(f"ChannelPlugin.management.update_instance_config for '{plugin.name}' must return a dict")
return cast(dict[str, Any], updated)
return updater(section, values, instance_id=instance_id)
def channel_set_config_enabled(
@@ -446,7 +423,7 @@ def channel_set_config_enabled(
from nanobot.config.loader import merge_missing_defaults
values = channel_instance_config(plugin, section, instance_id=instance_id)
values = cast(dict[str, Any], merge_missing_defaults(values, channel_default_config(plugin)))
values = merge_missing_defaults(values, channel_default_config(plugin))
values["enabled"] = enabled
return channel_update_instance_config(
plugin,
@@ -463,16 +440,12 @@ def channel_feature_instances(
setup_spec: ChannelSetupSpec | None = None,
) -> list[dict[str, Any]] | None:
factory = plugin.management.feature_instances
overrides = (
cast(object, factory(section, setup_spec=setup_spec))
if factory is not None
else None
)
overrides = factory(section, setup_spec=setup_spec) if factory is not None else None
if overrides is None and not plugin.management.multi_instance:
return None
if overrides is not None and (
not isinstance(overrides, list)
or any(not isinstance(instance, dict) for instance in cast(list[object], overrides))
or any(not isinstance(instance, dict) for instance in overrides)
):
raise TypeError(
f"ChannelPlugin.management.feature_instances for '{plugin.name}' "
@@ -497,8 +470,7 @@ def channel_feature_instances(
by_id = {instance["id"]: instance for instance in instances}
seen: set[str] = set()
for override_value in cast(list[object], overrides):
override = cast(dict[str, Any], override_value)
for override in overrides:
instance_id = override.get("id")
if not isinstance(instance_id, str) or instance_id not in by_id:
raise ValueError(
@@ -542,21 +514,20 @@ def _validate_runtime_name(plugin: ChannelPlugin, runtime_name: Any) -> None:
def channel_field_value(values: Any, field_path: str) -> Any:
current: Any = values
current = values
for part in field_path.split("."):
candidates = (part, _camel_to_snake(part))
if isinstance(current, dict):
for candidate in candidates:
if candidate in current:
current = cast(Any, current)[candidate]
current = current[candidate]
break
else:
return None
continue
for candidate in candidates:
current_value = current
if hasattr(current_value, candidate):
current = getattr(current_value, candidate)
if hasattr(current, candidate):
current = getattr(current, candidate)
break
else:
return None
@@ -571,7 +542,7 @@ def stringify_channel_value(value: Any) -> str:
if isinstance(value, bool):
return "true" if value else "false"
if isinstance(value, list):
return ", ".join(str(item) for item in cast(list[Any], value))
return ", ".join(str(item) for item in value)
return str(value)
@@ -615,8 +586,8 @@ def _channel_feature_instance(
def _config_mapping(value: Any) -> dict[str, Any] | None:
if hasattr(value, "model_dump"):
dumped = value.model_dump(mode="json", by_alias=True)
return cast(dict[str, Any], dumped) if isinstance(dumped, dict) else None
return cast(dict[str, Any], value) if isinstance(value, dict) else None
return dumped if isinstance(dumped, dict) else None
return value if isinstance(value, dict) else None
def _camel_to_snake(value: str) -> str:
+37 -114
View File
@@ -1,4 +1,3 @@
# pyright: reportConstantRedefinition=false, reportMissingTypeStubs=false, reportPrivateUsage=false
"""DingTalk/DingDing channel implementation using Stream Mode."""
import asyncio
@@ -11,7 +10,7 @@ from contextlib import suppress
from inspect import isawaitable
from io import BytesIO
from pathlib import Path
from typing import Any, cast
from typing import Any
from urllib.parse import unquote, urljoin, urlparse
import httpx
@@ -25,29 +24,12 @@ from nanobot.security.network import validate_resolved_url, validate_url_target
DINGTALK_MAX_REMOTE_MEDIA_BYTES = 20 * 1024 * 1024
DINGTALK_MAX_REMOTE_MEDIA_REDIRECTS = 3
_DINGTALK_MARKDOWN_INLINE_SPECIALS = frozenset(r"\`*_{}[]()<>#+-.!|~")
_DINGTALK_SENDER_NAME_MAX_CHARS = 80
def _escape_markdown_sender_name(value: str) -> str:
"""Render an untrusted display name as one bounded Markdown-safe line."""
normalized = " ".join(value.split())[:_DINGTALK_SENDER_NAME_MAX_CHARS]
return "".join(
f"\\{char}" if char in _DINGTALK_MARKDOWN_INLINE_SPECIALS else char
for char in normalized
)
DINGTALK_AVAILABLE = False
AckMessage: Any = None
CallbackHandler: Any = object
Credential: Any = None
DingTalkStreamClient: Any = None
ChatbotMessage: Any = None
try:
from dingtalk_stream import (
AckMessage,
CallbackHandler,
CallbackMessage,
Credential,
DingTalkStreamClient,
)
@@ -55,41 +37,41 @@ try:
DINGTALK_AVAILABLE = True
except ImportError:
pass
DINGTALK_AVAILABLE = False
# Fallback so class definitions don't crash at module level
CallbackHandler = object # type: ignore[assignment,misc]
CallbackMessage = None # type: ignore[assignment,misc]
AckMessage = None # type: ignore[assignment,misc]
ChatbotMessage = None # type: ignore[assignment,misc]
_CallbackHandlerBase = CallbackHandler
class NanobotDingTalkHandler(_CallbackHandlerBase):
class NanobotDingTalkHandler(CallbackHandler):
"""
Standard DingTalk Stream SDK Callback Handler.
Parses incoming messages and forwards them to the Nanobot channel.
"""
def __init__(self, channel: "DingTalkChannel"):
super().__init__() # pyright: ignore[reportUnknownMemberType]
super().__init__()
self.channel = channel
async def process(self, message: Any) -> tuple[Any, str]:
async def process(self, message: CallbackMessage):
"""Process incoming stream message."""
try:
# Parse using SDK's ChatbotMessage for robust handling
chatbot_msg: Any = ChatbotMessage.from_dict(message.data)
message_data = cast(dict[str, Any], message.data)
chatbot_msg = ChatbotMessage.from_dict(message.data)
# Extract text content; fall back to raw dict if SDK object is empty
content = ""
if chatbot_msg.text:
content = cast(str, chatbot_msg.text.content).strip()
content = chatbot_msg.text.content.strip()
elif chatbot_msg.extensions.get("content", {}).get("recognition"):
content = cast(str, chatbot_msg.extensions["content"]["recognition"]).strip()
content = chatbot_msg.extensions["content"]["recognition"].strip()
if not content:
text_data = cast(dict[str, Any], message_data.get("text", {}))
content = cast(str, text_data.get("content", "")).strip()
content = message.data.get("text", {}).get("content", "").strip()
# Handle file/image messages
file_paths: list[str] = []
file_paths = []
if chatbot_msg.message_type == "picture" and chatbot_msg.image_content:
download_code = chatbot_msg.image_content.download_code
if download_code:
@@ -100,18 +82,8 @@ class NanobotDingTalkHandler(_CallbackHandlerBase):
content = content or "[Image]"
elif chatbot_msg.message_type == "file":
message_content = cast(dict[str, Any], message_data.get("content", {}))
download_code = cast(
str,
message_content.get("downloadCode")
or message_data.get("downloadCode"),
)
fname = cast(
str,
message_content.get("fileName")
or message_data.get("fileName")
or "file",
)
download_code = message.data.get("content", {}).get("downloadCode") or message.data.get("downloadCode")
fname = message.data.get("content", {}).get("fileName") or message.data.get("fileName") or "file"
if download_code:
sender_uid = chatbot_msg.sender_staff_id or chatbot_msg.sender_id or "unknown"
fp = await self.channel._download_dingtalk_file(download_code, fname, sender_uid)
@@ -120,17 +92,13 @@ class NanobotDingTalkHandler(_CallbackHandlerBase):
content = content or "[File]"
elif chatbot_msg.message_type == "richText" and chatbot_msg.rich_text_content:
rich_list = cast(
list[object],
chatbot_msg.rich_text_content.rich_text_list or [],
)
for item_value in rich_list:
if not isinstance(item_value, dict):
rich_list = chatbot_msg.rich_text_content.rich_text_list or []
for item in rich_list:
if not isinstance(item, dict):
continue
item = cast(dict[str, Any], item_value)
# A rich-text item may carry text and/or a downloadCode; the
# DingTalk SDK treats them independently, so handle both.
t = cast(str, item.get("text", "")).strip()
t = item.get("text", "").strip()
if t:
fmt = item.get("type", "")
if fmt == "bold":
@@ -145,8 +113,8 @@ class NanobotDingTalkHandler(_CallbackHandlerBase):
formatted = t
content = (content + " " + formatted).strip() if content else formatted
if item.get("downloadCode"):
dc = cast(str, item["downloadCode"])
fname = cast(str, item.get("fileName") or "file")
dc = item["downloadCode"]
fname = item.get("fileName") or "file"
sender_uid = chatbot_msg.sender_staff_id or chatbot_msg.sender_id or "unknown"
fp = await self.channel._download_dingtalk_file(dc, fname, sender_uid)
if fp:
@@ -164,22 +132,13 @@ class NanobotDingTalkHandler(_CallbackHandlerBase):
)
return AckMessage.STATUS_OK, "OK"
sender_id = cast(
str | None,
chatbot_msg.sender_staff_id or chatbot_msg.sender_id,
)
sender_name = cast(str, chatbot_msg.sender_nick or "Unknown")
sender_id = chatbot_msg.sender_staff_id or chatbot_msg.sender_id
sender_name = chatbot_msg.sender_nick or "Unknown"
conversation_type = cast(
str | None,
message_data.get("conversationType"),
)
conversation_type = message.data.get("conversationType")
conversation_id = (
cast(
str | None,
message_data.get("conversationId")
or message_data.get("openConversationId"),
)
message.data.get("conversationId")
or message.data.get("openConversationId")
)
self.channel.logger.info("Received message from {} ({}): {}", sender_name, sender_id, content)
@@ -216,7 +175,6 @@ class DingTalkConfig(Base):
allow_remote_media_redirects: bool = False
remote_media_redirect_allowed_hosts: list[str] = Field(default_factory=list)
group_user_isolation: bool = False # If True, each user in group chat gets their own session
disable_private_chat: bool = False # If True, reject 1:1 DMs with a notice; group chats only
class DingTalkChannel(BaseChannel):
@@ -248,14 +206,14 @@ class DingTalkChannel(BaseChannel):
self.config: DingTalkConfig = config
self._client: Any = None
self._http: httpx.AsyncClient | None = None
self._start_task: asyncio.Task[Any] | None = None
self._start_task: asyncio.Task | None = None
# Access Token management for sending messages
self._access_token: str | None = None
self._token_expiry: float = 0
# Hold references to background tasks to prevent GC
self._background_tasks: set[asyncio.Task[None]] = set()
self._background_tasks: set[asyncio.Task] = set()
async def start(self) -> None:
"""Start the DingTalk bot with Stream Mode."""
@@ -605,11 +563,7 @@ class DingTalkChannel(BaseChannel):
try:
resp = await self._http.post(url, files=files)
text = resp.text
result = (
cast(dict[str, Any], resp.json())
if resp.headers.get("content-type", "").startswith("application/json")
else {}
)
result = resp.json() if resp.headers.get("content-type", "").startswith("application/json") else {}
if resp.status_code >= 400:
self.logger.error("media upload failed status={} type={} body={}", resp.status_code, media_type, text[:500])
return None
@@ -617,7 +571,7 @@ class DingTalkChannel(BaseChannel):
if errcode != 0:
self.logger.error("media upload api error type={} errcode={} body={}", media_type, errcode, text[:500])
return None
sub = cast(dict[str, Any], result.get("result") or {})
sub = result.get("result") or {}
media_id = result.get("media_id") or result.get("mediaId") or sub.get("media_id") or sub.get("mediaId")
if not media_id:
self.logger.error("media upload missing media_id body={}", text[:500])
@@ -668,7 +622,7 @@ class DingTalkChannel(BaseChannel):
self.logger.error("send failed msgKey={} status={} body={}", msg_key, resp.status_code, body[:500])
return False
try:
result = cast(dict[str, Any], resp.json())
result = resp.json()
except Exception:
result = {}
errcode = result.get("errcode")
@@ -758,20 +712,8 @@ class DingTalkChannel(BaseChannel):
if not token:
raise RuntimeError("DingTalk access token unavailable")
content = msg.content.strip() if msg.content else ""
if content:
# In group chats, prefix the reply with a markdown header naming the
# sender so the addressed user can spot the reply. Visual only —
# DingTalk's markdown robot messages do not push real @ notifications.
sender_name = msg.metadata.get("sender_name") if msg.metadata else None
safe_sender_name = (
_escape_markdown_sender_name(sender_name)
if isinstance(sender_name, str)
else ""
)
if msg.chat_id.startswith("group:") and safe_sender_name:
content = f"# @{safe_sender_name}\n\n{content}"
if not await self._send_markdown_text(token, msg.chat_id, content):
if msg.content and msg.content.strip():
if not await self._send_markdown_text(token, msg.chat_id, msg.content.strip()):
raise RuntimeError("DingTalk text message was not delivered")
for media_ref in msg.media or []:
@@ -791,7 +733,7 @@ class DingTalkChannel(BaseChannel):
async def _on_message(
self,
content: str,
sender_id: str | None,
sender_id: str,
sender_name: str,
conversation_type: str | None = None,
conversation_id: str | None = None,
@@ -803,30 +745,11 @@ class DingTalkChannel(BaseChannel):
"""
try:
self.logger.info("inbound: {} from {}", content, sender_name)
if not sender_id:
self.logger.warning("dropping DingTalk message without a sender ID")
return
is_group = conversation_type == "2" and conversation_id
chat_id = f"group:{conversation_id}" if is_group else sender_id
session_key = None
if is_group and self.config.group_user_isolation:
session_key = f"{self.name}:group:{conversation_id}:{sender_id}"
if not is_group and self.config.disable_private_chat:
# Group-only kill switch: drop DMs with a notice *before* any
# allow_from / pairing check, so even allowlisted senders are
# redirected — intentional, this is a hard private-chat guard
# rather than an authorization decision. No session is created.
self.logger.info("private chat disabled; rejecting DM from {}", sender_name)
await self.send(
OutboundMessage(
channel=self.name,
chat_id=chat_id,
content="该机器人未开启私聊,请在群聊中与我对话。",
)
)
return
await self._handle_message(
sender_id=sender_id,
chat_id=chat_id,
@@ -1,5 +1,4 @@
import asyncio
import json
import zipfile
from io import BytesIO
from types import SimpleNamespace
@@ -10,15 +9,15 @@ import pytest
# Check optional dingtalk dependencies before running tests
try:
import nanobot.channels.dingtalk.runtime as dingtalk_module
DINGTALK_AVAILABLE = dingtalk_module.DINGTALK_AVAILABLE
from nanobot.channels import dingtalk
DINGTALK_AVAILABLE = getattr(dingtalk, "DINGTALK_AVAILABLE", False)
except ImportError:
DINGTALK_AVAILABLE = False
if not DINGTALK_AVAILABLE:
pytest.skip("DingTalk dependencies not installed (dingtalk-stream)", allow_module_level=True)
import nanobot.channels.dingtalk.runtime as dingtalk_module
from nanobot.bus.events import OutboundMessage
from nanobot.bus.queue import MessageBus
from nanobot.channels.dingtalk.runtime import (
@@ -154,92 +153,6 @@ async def test_group_user_isolation_true_separates_sessions() -> None:
assert msg1.chat_id == msg2.chat_id == "group:conv123"
def test_disable_private_chat_uses_camel_case_config_key() -> None:
config = DingTalkConfig.model_validate({"disablePrivateChat": True})
assert config.disable_private_chat is True
assert config.model_dump(mode="json", by_alias=True)["disablePrivateChat"] is True
@pytest.mark.asyncio
async def test_dm_rejected_when_private_chat_disabled(monkeypatch) -> None:
"""With disable_private_chat=True, a 1:1 DM is rejected: nothing reaches the
bus (no session is created) and the bot replies with a notice directing the
user to group chat. Even allowlisted senders are blocked in DMs."""
config = DingTalkConfig(
client_id="app",
client_secret="secret",
allow_from=["*"], # even allowlisted senders are blocked in DMs
disable_private_chat=True,
)
bus = MessageBus()
channel = DingTalkChannel(config, bus)
async def fake_get_token():
return "test-token"
monkeypatch.setattr(channel, "_get_access_token", fake_get_token)
channel._http = _FakeHttp()
await channel._on_message(
"hello",
sender_id="user1",
sender_name="Alice",
conversation_type="1",
)
# No inbound message was published -> no session created
assert bus.inbound.empty()
# A notice was sent back to the DM user via the private-chat API
assert len(channel._http.calls) == 1
call = channel._http.calls[0]
assert call["url"] == "https://api.dingtalk.com/v1.0/robot/oToMessages/batchSend"
assert call["json"]["msgKey"] == "sampleMarkdown"
assert call["json"]["userIds"] == ["user1"]
assert "该机器人未开启私聊,请在群聊中与我对话。" in call["json"]["msgParam"]
@pytest.mark.asyncio
async def test_dm_allowed_when_private_chat_not_disabled() -> None:
"""By default (disable_private_chat=False), a 1:1 DM still reaches the bus."""
config = DingTalkConfig(client_id="app", client_secret="secret", allow_from=["*"])
bus = MessageBus()
channel = DingTalkChannel(config, bus)
await channel._on_message(
"hello",
sender_id="user1",
sender_name="Alice",
conversation_type="1",
)
msg = await bus.consume_inbound()
assert msg.chat_id == "user1"
assert msg.metadata["conversation_type"] == "1"
@pytest.mark.asyncio
async def test_group_message_allowed_when_private_chat_disabled() -> None:
"""Disabling private chat must not affect group messages."""
config = DingTalkConfig(
client_id="app", client_secret="secret", allow_from=["*"], disable_private_chat=True
)
bus = MessageBus()
channel = DingTalkChannel(config, bus)
await channel._on_message(
"hello",
sender_id="user1",
sender_name="Alice",
conversation_type="2",
conversation_id="conv123",
)
msg = await bus.consume_inbound()
assert msg.chat_id == "group:conv123"
@pytest.mark.asyncio
async def test_group_send_uses_group_messages_api() -> None:
config = DingTalkConfig(client_id="app", client_secret="secret", allow_from=["*"])
@@ -260,105 +173,6 @@ async def test_group_send_uses_group_messages_api() -> None:
assert call["json"]["msgKey"] == "sampleMarkdown"
@pytest.mark.asyncio
async def test_group_send_prepends_sender_mention(monkeypatch) -> None:
"""Group replies are prefixed with a markdown header naming the sender."""
config = DingTalkConfig(client_id="app", client_secret="secret", allow_from=["*"])
channel = DingTalkChannel(config, MessageBus())
channel._http = _FakeHttp()
async def _fake_token() -> str:
return "token"
monkeypatch.setattr(channel, "_get_access_token", _fake_token)
await channel.send(
OutboundMessage(
channel="dingtalk",
chat_id="group:conv123",
content="hello",
metadata={"sender_name": "Alice"},
)
)
sent_text = json.loads(channel._http.calls[0]["json"]["msgParam"])["text"]
assert sent_text == "# @Alice\n\nhello"
@pytest.mark.asyncio
async def test_group_send_escapes_untrusted_sender_name(monkeypatch) -> None:
"""A sender nickname cannot inject extra Markdown blocks into the reply."""
config = DingTalkConfig(client_id="app", client_secret="secret", allow_from=["*"])
channel = DingTalkChannel(config, MessageBus())
channel._http = _FakeHttp()
async def _fake_token() -> str:
return "token"
monkeypatch.setattr(channel, "_get_access_token", _fake_token)
await channel.send(
OutboundMessage(
channel="dingtalk",
chat_id="group:conv123",
content="hello",
metadata={"sender_name": "Alice\n# [click](https://evil) *admin*"},
)
)
sent_text = json.loads(channel._http.calls[0]["json"]["msgParam"])["text"]
assert sent_text == r"# @Alice \# \[click\]\(https://evil\) \*admin\*" + "\n\nhello"
@pytest.mark.asyncio
async def test_private_send_does_not_prepend_mention(monkeypatch) -> None:
"""Private replies are sent verbatim, without the sender header."""
config = DingTalkConfig(client_id="app", client_secret="secret", allow_from=["*"])
channel = DingTalkChannel(config, MessageBus())
channel._http = _FakeHttp()
async def _fake_token() -> str:
return "token"
monkeypatch.setattr(channel, "_get_access_token", _fake_token)
await channel.send(
OutboundMessage(
channel="dingtalk",
chat_id="user1", # private chat: no "group:" prefix
content="hello",
metadata={"sender_name": "Alice"},
)
)
sent_text = json.loads(channel._http.calls[0]["json"]["msgParam"])["text"]
assert sent_text == "hello"
@pytest.mark.asyncio
async def test_message_without_sender_id_is_dropped() -> None:
"""Malformed inbound events must not publish or attempt an invalid reply."""
config = DingTalkConfig(
client_id="app",
client_secret="secret",
allow_from=["*"],
disable_private_chat=True,
)
bus = MessageBus()
channel = DingTalkChannel(config, bus)
channel._http = _FakeHttp()
await channel._on_message(
"hello",
sender_id=None,
sender_name="Unknown",
conversation_type="1",
)
assert bus.inbound.empty()
assert channel._http.calls == []
@pytest.mark.asyncio
async def test_handler_uses_voice_recognition_text_when_text_is_empty(monkeypatch) -> None:
bus = MessageBus()
+16 -24
View File
@@ -1,5 +1,4 @@
"""Discord channel implementation using discord.py."""
# pyright: reportPrivateUsage=false, reportUnusedFunction=false
from __future__ import annotations
@@ -9,7 +8,7 @@ import time
from contextlib import suppress
from dataclasses import dataclass
from pathlib import Path
from typing import TYPE_CHECKING, Any, Literal, cast
from typing import TYPE_CHECKING, Any, Literal
from pydantic import Field
@@ -44,7 +43,7 @@ class _StreamBuf:
"""Per-chat streaming accumulator for progressive Discord message edits."""
text: str = ""
message: discord.Message | None = None
message: Any | None = None
last_edit: float = 0.0
stream_id: str | None = None
@@ -267,14 +266,13 @@ if DISCORD_AVAILABLE:
self._channel.logger.warning("channel {} unavailable: {}", msg.chat_id, e)
raise
messageable_channel = cast(Messageable, channel)
reference, mention_settings = self._build_reply_context(messageable_channel, msg.reply_to)
reference, mention_settings = self._build_reply_context(channel, msg.reply_to)
sent_media = False
failed_media: list[str] = []
for index, media_path in enumerate(msg.media or []):
if await self._send_file(
messageable_channel,
channel,
media_path,
reference=reference if index == 0 else None,
mention_settings=mention_settings,
@@ -290,7 +288,7 @@ if DISCORD_AVAILABLE:
if index == 0 and reference is not None and not sent_media:
kwargs["reference"] = reference
kwargs["allowed_mentions"] = mention_settings
await messageable_channel.send(**kwargs)
await channel.send(**kwargs)
async def _send_file(
self,
@@ -346,7 +344,7 @@ if DISCORD_AVAILABLE:
self._channel.logger.warning("Invalid reply target: {}", reply_to)
return None, mention_settings
return cast(Any, channel).get_partial_message(message_id), mention_settings
return channel.get_partial_message(message_id), mention_settings
class DiscordChannel(BaseChannel):
@@ -425,8 +423,8 @@ class DiscordChannel(BaseChannel):
import aiohttp
proxy_auth = aiohttp.BasicAuth(
login=cast(str, self.config.proxy_username),
password=cast(str, self.config.proxy_password),
login=self.config.proxy_username,
password=self.config.proxy_password,
)
elif has_user != has_pass:
self.logger.warning(
@@ -491,7 +489,6 @@ class DiscordChannel(BaseChannel):
stream_id: str | None = None,
stream_end: bool = False,
resuming: bool = False,
merge_next: bool = False,
) -> None:
"""Progressive Discord delivery: send once, then edit until the stream ends."""
client = self._client
@@ -499,17 +496,13 @@ class DiscordChannel(BaseChannel):
self.logger.warning("client not ready; dropping stream delta")
return
if stream_end and merge_next:
if not delta:
return
stream_end = False
if stream_end:
buf = self._stream_bufs.get(chat_id)
if not buf or buf.message is None or not buf.text:
return
if stream_id is not None and buf.stream_id is not None and buf.stream_id != stream_id:
return
await self._finalize_stream(chat_id, buf, buf.message)
await self._finalize_stream(chat_id, buf)
return
buf = self._stream_bufs.get(chat_id)
@@ -637,12 +630,7 @@ class DiscordChannel(BaseChannel):
self.logger.warning("channel {} unavailable: {}", chat_id, e)
return None
async def _finalize_stream(
self,
chat_id: str,
buf: _StreamBuf,
message: discord.Message,
) -> None:
async def _finalize_stream(self, chat_id: str, buf: _StreamBuf) -> None:
"""Commit the final streamed content and flush overflow chunks."""
chunks = DiscordBotClient._build_chunks(buf.text, [], False)
if not chunks:
@@ -650,12 +638,16 @@ class DiscordChannel(BaseChannel):
return
try:
await message.edit(content=chunks[0])
await buf.message.edit(content=chunks[0])
except Exception as e:
self.logger.warning("final stream edit failed: {}", e)
raise
target = message.channel
target = getattr(buf.message, "channel", None) or await self._resolve_channel(chat_id)
if target is None:
self.logger.warning("stream follow-up target {} unavailable", chat_id)
self._stream_bufs.pop(chat_id, None)
return
for extra_chunk in chunks[1:]:
await target.send(content=extra_chunk)
@@ -754,36 +754,6 @@ async def test_send_delta_streams_by_editing_message(monkeypatch) -> None:
assert owner._stream_bufs == {}
@pytest.mark.asyncio
async def test_send_delta_merge_next_keeps_one_message(monkeypatch) -> None:
owner = DiscordChannel(DiscordConfig(enabled=True, allow_from=["*"]), MessageBus())
client = _FakeDiscordClient(owner, intents=None)
owner._client = client
owner._running = True
target = _FakeChannel(channel_id=123)
client.channels[123] = target
times = iter([1.0, 3.0, 5.0])
monkeypatch.setattr("nanobot.channels.discord.runtime.time.monotonic", lambda: next(times, 5.0))
await owner.send_delta(
"123",
"first-",
stream_id="s1",
stream_end=True,
merge_next=True,
)
await owner.send_delta("123", "second", stream_id="s1")
await owner.send_delta("123", "", stream_id="s1", stream_end=True)
assert target.sent_payloads == [{"content": "first-"}]
assert target.sent_messages[0].edits == [
{"content": "first-second"},
{"content": "first-second"},
]
assert owner._stream_bufs == {}
@pytest.mark.asyncio
async def test_send_delta_stream_end_splits_oversized_reply(monkeypatch) -> None:
owner = DiscordChannel(DiscordConfig(enabled=True, allow_from=["*"]), MessageBus())
+8 -12
View File
@@ -17,7 +17,7 @@ from email.parser import BytesParser
from email.utils import parseaddr
from fnmatch import fnmatch
from pathlib import Path
from typing import Any, Literal, cast
from typing import Any, Literal
from loguru import logger
from pydantic import Field
@@ -188,9 +188,7 @@ class EmailChannel(BaseChannel):
self.logger.exception("Error delivering email from {}", sender)
continue
metadata = item.get("metadata")
metadata_data = cast(dict[str, Any], metadata) if isinstance(metadata, dict) else {}
uid = str(metadata_data.get("uid") or "")
uid = str((item.get("metadata") or {}).get("uid") or "")
if uid and should_apply_post_action:
post_actions_uids.add(uid)
@@ -314,7 +312,7 @@ class EmailChannel(BaseChannel):
raise
def _validate_config(self) -> bool:
missing: list[str] = []
missing = []
if not self.config.imap_host:
missing.append("imap_host")
if not self.config.imap_username:
@@ -429,7 +427,7 @@ class EmailChannel(BaseChannel):
messages: list[dict[str, Any]],
skipped_uids: set[str],
cycle_uids: set[str],
) -> list[dict[str, Any]] | None:
) -> None:
"""Fetch messages by arbitrary IMAP search criteria."""
mailbox = self.config.imap_mailbox or "INBOX"
@@ -767,10 +765,8 @@ class EmailChannel(BaseChannel):
@staticmethod
def _extract_message_bytes(fetched: list[Any]) -> bytes | None:
for item in fetched:
if isinstance(item, tuple):
fetched_item = cast(tuple[Any, ...], item)
if len(fetched_item) >= 2 and isinstance(fetched_item[1], (bytes, bytearray)):
return bytes(fetched_item[1])
if isinstance(item, tuple) and len(item) >= 2 and isinstance(item[1], (bytes, bytearray)):
return bytes(item[1])
return None
@staticmethod
@@ -841,8 +837,8 @@ class EmailChannel(BaseChannel):
"""
spf_pass = False
dkim_pass = False
for ar_header in cast(list[Any], parsed_msg.get_all("Authentication-Results") or []):
ar_lower = str(ar_header).lower()
for ar_header in parsed_msg.get_all("Authentication-Results") or []:
ar_lower = ar_header.lower()
if re.search(r"\bspf\s*=\s*pass\b", ar_lower):
spf_pass = True
if re.search(r"\bdkim\s*=\s*pass\b", ar_lower):
+17 -31
View File
@@ -1,13 +1,10 @@
"""Short-lived WebUI channel connection sessions."""
# pyright: reportPrivateUsage=false
from __future__ import annotations
import asyncio
import json
import secrets
import threading
import time
from dataclasses import dataclass
from typing import Any
@@ -44,7 +41,6 @@ class FeishuConnectStore:
def __init__(self) -> None:
self._sessions: dict[str, FeishuConnectSession] = {}
self._completion_lock = threading.Lock()
async def handle(self, action: str, query: QueryParams) -> dict[str, Any]:
"""Handle one generic settings connection action."""
@@ -62,7 +58,7 @@ class FeishuConnectStore:
if action == "poll":
return await asyncio.to_thread(self.poll, session_id)
if action == "cancel":
return await asyncio.to_thread(self.cancel, session_id)
return self.cancel(session_id)
raise ChannelConnectError(f"unsupported Feishu connect action: {action}", status=404)
def start(
@@ -131,33 +127,24 @@ class FeishuConnectStore:
session.last_error = str(exc)
return _pending_payload(session)
session.domain = str(result.get("domain") or session.domain)
status = result.get("status")
if status == "succeeded":
with self._completion_lock:
if self._sessions.get(session_id) is not session:
return {
"session_id": session_id,
"instance_id": session.instance_id,
"status": "cancelled",
"message": "Feishu connection cancelled.",
}
session.domain = str(result.get("domain") or session.domain)
session.instance_id = feishu.save_registration_result(
result,
instance_id=session.instance_id,
name=session.instance_name,
)
self._sessions.pop(session_id, None)
return {
"session_id": session_id,
"instance_id": session.instance_id,
"status": "succeeded",
"message": "Feishu is connected.",
"domain": session.domain,
"app_id": result.get("app_id"),
}
session.instance_id = feishu.save_registration_result(
result,
instance_id=session.instance_id,
name=session.instance_name,
)
self._sessions.pop(session_id, None)
return {
"session_id": session_id,
"instance_id": session.instance_id,
"status": "succeeded",
"message": "Feishu is connected.",
"domain": session.domain,
"app_id": result.get("app_id"),
}
session.domain = str(result.get("domain") or session.domain)
if status == "failed":
self._sessions.pop(session_id, None)
return {
@@ -171,8 +158,7 @@ class FeishuConnectStore:
return _pending_payload(session)
def cancel(self, session_id: str) -> dict[str, Any]:
with self._completion_lock:
session = self._sessions.pop(session_id, None)
session = self._sessions.pop(session_id, None)
return {
"session_id": session_id,
"instance_id": session.instance_id if session else DEFAULT_INSTANCE_ID,
+12 -13
View File
@@ -3,7 +3,7 @@
from __future__ import annotations
import re
from typing import Any, cast
from typing import Any
from loguru import logger
@@ -46,7 +46,7 @@ def update_managed_feishu_instance(
*,
instance_id: str = DEFAULT_INSTANCE_ID,
) -> dict[str, Any]:
existing = cast(dict[str, Any], section) if isinstance(section, dict) else {}
existing = section if isinstance(section, dict) else {}
return upsert_feishu_instance(
existing,
feishu_default_config(),
@@ -69,8 +69,8 @@ def _normalize_feishu_instance(
inherited: dict[str, Any] | None = None,
fallback_id: str = DEFAULT_INSTANCE_ID,
) -> dict[str, Any]:
config = cast(dict[str, Any], merge_missing_defaults(inherited or {}, defaults))
config = cast(dict[str, Any], merge_missing_defaults(raw, config))
config = merge_missing_defaults(inherited or {}, defaults)
config = merge_missing_defaults(raw, config)
raw_id = raw.get("id") or raw.get("instanceId") or raw.get("instance_id") or fallback_id
instance_id = validate_instance_id(str(raw_id))
@@ -97,13 +97,12 @@ def _feishu_instance_inputs(
section = section.model_dump(mode="json", by_alias=True)
if not isinstance(section, dict):
section = {}
section_data = cast(dict[str, Any], section)
instances = section_data.get("instances")
instances = section.get("instances")
if isinstance(instances, list):
inherited = {key: value for key, value in section_data.items() if key != "instances"}
return list(cast(list[Any], instances)), inherited
return ([section_data] if section_data else [_base_feishu_instance_config(defaults)]), None
inherited = {key: value for key, value in section.items() if key != "instances"}
return list(instances), inherited
return ([section] if section else [_base_feishu_instance_config(defaults)]), None
def feishu_instance_specs(
@@ -125,7 +124,7 @@ def feishu_instance_specs(
fallback_id = DEFAULT_INSTANCE_ID if index == 0 else f"assistant-{index + 1}"
try:
config = _normalize_feishu_instance(
cast(dict[str, Any], raw),
raw,
defaults,
inherited=inherited,
fallback_id=fallback_id,
@@ -180,7 +179,7 @@ def canonical_feishu_section(section: Any, defaults: dict[str, Any]) -> dict[str
fallback_id = DEFAULT_INSTANCE_ID if index == 0 else f"assistant-{index + 1}"
try:
config = _normalize_feishu_instance(
cast(dict[str, Any], raw),
raw,
defaults,
inherited=inherited,
fallback_id=fallback_id,
@@ -239,9 +238,9 @@ def update_feishu_instance_preserving_shape(
if (
instance_id == DEFAULT_INSTANCE_ID
and isinstance(section, dict)
and not isinstance(cast(dict[str, Any], section).get("instances"), list)
and not isinstance(section.get("instances"), list)
):
return {**cast(dict[str, Any], section), **values}
return {**section, **values}
return upsert_feishu_instance(section, defaults, instance_id, values)
+131 -235
View File
@@ -1,5 +1,4 @@
"""Feishu/Lark channel implementation using lark-oapi SDK with WebSocket long connection."""
# pyright: reportMissingModuleSource=false, reportMissingTypeStubs=false
from __future__ import annotations
@@ -15,9 +14,8 @@ from collections import OrderedDict
from contextlib import suppress
from dataclasses import dataclass
from datetime import UTC, datetime
from functools import partial
from pathlib import Path
from typing import TYPE_CHECKING, Any, TypedDict, cast
from typing import TYPE_CHECKING, Any
from rich.console import Console
from rich.markup import escape
@@ -46,10 +44,7 @@ from nanobot.utils.helpers import safe_filename
from nanobot.utils.logging_bridge import redirect_lib_logging
if TYPE_CHECKING:
from lark_oapi.api.im.v1.model import ( # pyright: ignore[reportMissingTypeStubs]
MentionEvent,
P2ImMessageReceiveV1,
)
from lark_oapi.api.im.v1.model import MentionEvent, P2ImMessageReceiveV1
FEISHU_AVAILABLE = importlib.util.find_spec("lark_oapi") is not None
_LOGIN_CONSOLE = Console()
@@ -60,20 +55,6 @@ def _identity_timestamp() -> str:
return datetime.now(UTC).isoformat(timespec="seconds").replace("+00:00", "Z")
def _as_json_object(value: Any) -> dict[str, Any] | None:
"""Narrow untyped SDK/JSON objects at the channel boundary."""
return cast(dict[str, Any], value) if isinstance(value, dict) else None
def _as_json_list(value: Any) -> list[Any] | None:
"""Narrow untyped SDK/JSON arrays at the channel boundary."""
return cast(list[Any], value) if isinstance(value, list) else None
def _ignore_event(_: Any) -> None:
"""Consume SDK events that intentionally have no channel action."""
def _load_lark_runtime() -> tuple[Any, str, str]:
"""Import the heavy Feishu SDK lazily.
@@ -88,12 +69,9 @@ def _load_lark_runtime() -> tuple[Any, str, str]:
# close the same loop.
with _LARK_RUNTIME_LOCK:
ws_client_already_imported = "lark_oapi.ws.client" in sys.modules
import lark_oapi as lark # pyright: ignore[reportMissingTypeStubs]
import lark_oapi.ws.client as lark_ws_client # pyright: ignore[reportMissingTypeStubs]
from lark_oapi.core.const import ( # pyright: ignore[reportMissingTypeStubs]
FEISHU_DOMAIN,
LARK_DOMAIN,
)
import lark_oapi as lark
import lark_oapi.ws.client as lark_ws_client
from lark_oapi.core.const import FEISHU_DOMAIN, LARK_DOMAIN
if (
not ws_client_already_imported
@@ -128,7 +106,7 @@ def fetch_feishu_app_identity(
try:
lark, feishu_domain, lark_domain = _load_lark_runtime()
from lark_oapi.api.application.v6.model.get_application_request import ( # pyright: ignore[reportMissingTypeStubs]
from lark_oapi.api.application.v6.model.get_application_request import (
GetApplicationRequest,
)
@@ -173,9 +151,9 @@ MSG_TYPE_MAP = {
}
def _extract_share_card_content(content_json: dict[str, Any], msg_type: str) -> str:
def _extract_share_card_content(content_json: dict, msg_type: str) -> str:
"""Extract text representation from share cards and interactive messages."""
parts: list[str] = []
parts = []
if msg_type == "share_chat":
parts.append(f"[shared chat: {content_json.get('chat_id', '')}]")
@@ -193,9 +171,9 @@ def _extract_share_card_content(content_json: dict[str, Any], msg_type: str) ->
return "\n".join(parts) if parts else f"[{msg_type}]"
def _extract_interactive_content(content: str | dict[str, Any]) -> list[str]:
def _extract_interactive_content(content: dict) -> list[str]:
"""Recursively extract text and links from interactive card content."""
parts: list[str] = []
parts = []
if isinstance(content, str):
try:
@@ -211,9 +189,8 @@ def _extract_interactive_content(content: str | dict[str, Any]) -> list[str]:
if isinstance(user_dsl, str) and user_dsl.strip():
try:
dsl = json.loads(user_dsl)
dsl_object = _as_json_object(dsl)
if dsl_object is not None:
parts.extend(_extract_interactive_content(dsl_object))
if isinstance(dsl, dict):
parts.extend(_extract_interactive_content(dsl))
if parts:
return parts
except (json.JSONDecodeError, TypeError):
@@ -221,9 +198,8 @@ def _extract_interactive_content(content: str | dict[str, Any]) -> list[str]:
if "title" in content:
title = content["title"]
title_object = _as_json_object(title)
if title_object is not None:
title_content = title_object.get("content", "") or title_object.get("text", "")
if isinstance(title, dict):
title_content = title.get("content", "") or title.get("text", "")
if title_content:
parts.append(f"title: {title_content}")
elif isinstance(title, str):
@@ -231,39 +207,34 @@ def _extract_interactive_content(content: str | dict[str, Any]) -> list[str]:
# Top-level elements: flat list or nested list format
elements = content.get("elements")
elements_list = _as_json_list(elements)
if elements_list is not None:
if elements_list and isinstance(elements_list[0], list):
if isinstance(elements, list):
if elements and isinstance(elements[0], list):
# Nested list: [[{tag:"text",text:"..."}], ...]
for row in elements_list:
row_list = _as_json_list(row)
if row_list is not None:
for element in row_list:
for row in elements:
if isinstance(row, list):
for element in row:
parts.extend(_extract_element_content(element))
else:
# Flat list: [{tag:"markdown",content:"..."}, ...]
for element in elements_list:
for element in elements:
parts.extend(_extract_element_content(element))
# Body elements (schema 2.0)
body = content.get("body", {})
body_object = _as_json_object(body)
if body_object is not None:
body_elements = _as_json_list(body_object.get("elements"))
if body_elements is not None:
if isinstance(body, dict):
body_elements = body.get("elements")
if isinstance(body_elements, list):
for element in body_elements:
parts.extend(_extract_element_content(element))
card = content.get("card", {})
card_object = _as_json_object(card)
if card_object:
parts.extend(_extract_interactive_content(card_object))
if card:
parts.extend(_extract_interactive_content(card))
header = content.get("header", {})
header_object = _as_json_object(header)
if header_object is not None:
header_title = _as_json_object(header_object.get("title", {}))
if header_title is not None:
if header:
header_title = header.get("title", {})
if isinstance(header_title, dict):
header_text = header_title.get("content", "") or header_title.get("text", "")
if header_text:
parts.append(f"title: {header_text}")
@@ -271,16 +242,13 @@ def _extract_interactive_content(content: str | dict[str, Any]) -> list[str]:
return parts
def _extract_element_content(element: Any) -> list[str]:
def _extract_element_content(element: dict) -> list[str]:
"""Extract content from a single card element."""
parts: list[str] = []
parts = []
element_object = _as_json_object(element)
if element_object is None:
if not isinstance(element, dict):
return parts
element = element_object
tag = element.get("tag", "")
if tag in ("markdown", "lark_md"):
@@ -295,18 +263,16 @@ def _extract_element_content(element: Any) -> list[str]:
elif tag == "div":
text = element.get("text", {})
text_object = _as_json_object(text)
if text_object is not None:
text_content = text_object.get("content", "") or text_object.get("text", "")
if isinstance(text, dict):
text_content = text.get("content", "") or text.get("text", "")
if text_content:
parts.append(text_content)
elif isinstance(text, str):
parts.append(text)
for field in _as_json_list(element.get("fields")) or []:
field_object = _as_json_object(field)
if field_object is not None:
field_text = _as_json_object(field_object.get("text", {}))
if field_text is not None:
for field in element.get("fields", []):
if isinstance(field, dict):
field_text = field.get("text", {})
if isinstance(field_text, dict):
c = field_text.get("content", "")
if c:
parts.append(c)
@@ -321,33 +287,25 @@ def _extract_element_content(element: Any) -> list[str]:
elif tag == "button":
text = element.get("text", {})
text_object = _as_json_object(text)
if text_object is not None:
c = text_object.get("content", "")
if isinstance(text, dict):
c = text.get("content", "")
if c:
parts.append(c)
multi_url: Any = element.get("multi_url") or {}
multi_url_object = _as_json_object(multi_url)
url = element.get("url", "") or (
multi_url_object.get("url", "") if multi_url_object is not None else ""
)
url = element.get("url", "") or element.get("multi_url", {}).get("url", "")
if url:
parts.append(f"link: {url}")
elif tag == "img":
alt = _as_json_object(element.get("alt", {}))
parts.append(alt.get("content", "[image]") if alt is not None else "[image]")
alt = element.get("alt", {})
parts.append(alt.get("content", "[image]") if isinstance(alt, dict) else "[image]")
elif tag == "note":
for ne in _as_json_list(element.get("elements")) or []:
for ne in element.get("elements", []):
parts.extend(_extract_element_content(ne))
elif tag == "column_set":
for col in _as_json_list(element.get("columns")) or []:
col_object = _as_json_object(col)
if col_object is None:
continue
for ce in _as_json_list(col_object.get("elements")) or []:
for col in element.get("columns", []):
for ce in col.get("elements", []):
parts.extend(_extract_element_content(ce))
elif tag == "plain_text":
@@ -356,44 +314,36 @@ def _extract_element_content(element: Any) -> list[str]:
parts.append(content)
elif tag == "table":
columns: list[tuple[str, str]] = []
for column in _as_json_list(element.get("columns")) or []:
column_object = _as_json_object(column)
if column_object is None:
continue
name = column_object.get("name")
if isinstance(name, str) and name:
columns.append((name, str(column_object.get("display_name") or name)))
rows = _as_json_list(element.get("rows")) or []
columns = [
(column["name"], str(column.get("display_name") or column["name"]))
for column in (element.get("columns") or [])
if isinstance(column, dict) and column.get("name")
]
rows = element.get("rows", [])
if columns:
parts.append(" | ".join(header for _, header in columns))
if rows:
if isinstance(rows, list):
for row in rows:
row_object = _as_json_object(row)
if row_object is None:
if not isinstance(row, dict):
continue
values: list[str] = []
values = []
for name, _ in columns:
value = row_object.get(name)
value = row.get(name)
if isinstance(value, list):
value = " ".join(
str(item).strip()
for item in cast(list[Any], value)
if item is not None
)
value = " ".join(str(item).strip() for item in value if item is not None)
values.append("" if value is None else str(value).strip())
row_text = " | ".join(values).strip()
if row_text:
parts.append(row_text)
else:
for ne in _as_json_list(element.get("elements")) or []:
for ne in element.get("elements", []):
parts.extend(_extract_element_content(ne))
return parts
def _extract_post_content(content_json: dict[str, Any]) -> tuple[str, list[str]]:
def _extract_post_content(content_json: dict) -> tuple[str, list[str]]:
"""Extract text and image keys from Feishu post (rich text) message.
Handles three payload shapes:
@@ -402,48 +352,37 @@ def _extract_post_content(content_json: dict[str, Any]) -> tuple[str, list[str]]
- Wrapped: {"post": {"zh_cn": {"title": "...", "content": [...]}}}
"""
def _parse_block(block: dict[str, Any]) -> tuple[str | None, list[str]]:
content = _as_json_list(block.get("content"))
if content is None:
def _parse_block(block: dict) -> tuple[str | None, list[str]]:
if not isinstance(block, dict) or not isinstance(block.get("content"), list):
return None, []
texts: list[str] = []
images: list[str] = []
title = block.get("title")
if isinstance(title, str) and title:
texts, images = [], []
if title := block.get("title"):
texts.append(title)
for row in content:
row_items = _as_json_list(row)
if row_items is None:
for row in block["content"]:
if not isinstance(row, list):
continue
for el in row_items:
element = _as_json_object(el)
if element is None:
for el in row:
if not isinstance(el, dict):
continue
tag = element.get("tag")
tag = el.get("tag")
if tag in ("text", "a"):
text = element.get("text", "")
if isinstance(text, str):
texts.append(text)
texts.append(el.get("text", ""))
elif tag == "at":
user = element.get("user_name", "user")
texts.append(f"@{user if isinstance(user, str) and user else 'user'}")
texts.append(f"@{el.get('user_name', 'user')}")
elif tag == "code_block":
lang = element.get("language", "")
code_text = element.get("text", "")
if not isinstance(lang, str):
lang = ""
if not isinstance(code_text, str):
code_text = ""
lang = el.get("language", "")
code_text = el.get("text", "")
texts.append(f"\n```{lang}\n{code_text}\n```\n")
elif tag == "img" and isinstance((key := element.get("image_key")), str):
elif tag == "img" and (key := el.get("image_key")):
images.append(key)
return (" ".join(texts).strip() or None), images
# Unwrap optional {"post": ...} envelope
root = content_json
post = _as_json_object(root.get("post"))
if post is not None:
root = post
if isinstance(root, dict) and isinstance(root.get("post"), dict):
root = root["post"]
if not isinstance(root, dict):
return "", []
# Direct format
if "content" in root:
@@ -454,23 +393,19 @@ def _extract_post_content(content_json: dict[str, Any]) -> tuple[str, list[str]]
# Localized: prefer known locales, then fall back to any dict child
for key in ("zh_cn", "en_us", "ja_jp"):
if key in root:
block = _as_json_object(root[key])
if block is None:
continue
text, imgs = _parse_block(block)
text, imgs = _parse_block(root[key])
if text or imgs:
return text or "", imgs
for val in root.values():
block = _as_json_object(val)
if block is not None:
text, imgs = _parse_block(block)
if isinstance(val, dict):
text, imgs = _parse_block(val)
if text or imgs:
return text or "", imgs
return "", []
def _extract_post_text(content_json: dict[str, Any]) -> str: # pyright: ignore[reportUnusedFunction]
def _extract_post_text(content_json: dict) -> str:
"""Extract plain text from Feishu post (rich text) message content.
Legacy wrapper for _extract_post_content, returns only text.
@@ -494,18 +429,11 @@ _REGISTRATION_PATH = "/oauth/v1/app/registration"
_ONBOARD_REQUEST_TIMEOUT_S = 10
class _RegistrationStart(TypedDict):
device_code: str
qr_url: str
interval: int
expire_in: int
def _accounts_base_url(domain: str) -> str:
return _ONBOARD_ACCOUNTS_URLS.get(domain, _ONBOARD_ACCOUNTS_URLS["feishu"])
def _post_registration(base_url: str, body: dict[str, str]) -> dict[str, Any]:
def _post_registration(base_url: str, body: dict[str, str]) -> dict:
"""POST form-encoded data to the registration endpoint, return parsed JSON.
The registration endpoint returns JSON even on HTTP errors (e.g. poll
@@ -521,8 +449,7 @@ def _post_registration(base_url: str, body: dict[str, str]) -> dict[str, Any]:
headers={"Content-Type": "application/x-www-form-urlencoded"},
)
try:
parsed = resp.json()
return _as_json_object(parsed) or {}
return resp.json()
except json.JSONDecodeError:
resp.raise_for_status()
return {}
@@ -532,7 +459,7 @@ def _init_registration(domain: str = "feishu") -> None:
"""Verify the environment supports client_secret auth. Raises RuntimeError if not."""
base_url = _accounts_base_url(domain)
res = _post_registration(base_url, {"action": "init"})
methods = _as_json_list(res.get("supported_auth_methods")) or []
methods = res.get("supported_auth_methods") or []
if "client_secret" not in methods:
raise RuntimeError(
f"Feishu / Lark registration does not support client_secret auth. "
@@ -540,7 +467,7 @@ def _init_registration(domain: str = "feishu") -> None:
)
def _begin_registration(domain: str = "feishu") -> _RegistrationStart:
def _begin_registration(domain: str = "feishu") -> dict:
"""Start the device-code flow. Returns device_code, qr_url, interval, expire_in."""
base_url = _accounts_base_url(domain)
res = _post_registration(base_url, {
@@ -550,18 +477,16 @@ def _begin_registration(domain: str = "feishu") -> _RegistrationStart:
"request_user_info": "open_id",
})
device_code = res.get("device_code")
if not isinstance(device_code, str) or not device_code:
if not device_code:
raise RuntimeError("Feishu / Lark registration did not return a device_code")
qr_url = res.get("verification_uri_complete", "")
if not isinstance(qr_url, str) or not qr_url:
if not qr_url:
raise RuntimeError("Feishu / Lark registration did not return a login URL")
interval = res.get("interval")
expire_in = res.get("expire_in")
return {
"device_code": device_code,
"qr_url": qr_url,
"interval": interval if isinstance(interval, int) else 5,
"expire_in": expire_in if isinstance(expire_in, int) else 600,
"interval": res.get("interval") or 5,
"expire_in": res.get("expire_in") or 600,
}
@@ -571,7 +496,7 @@ def _poll_registration(
interval: int,
expire_in: int,
domain: str = "feishu",
) -> dict[str, Any] | None:
) -> dict | None:
"""Poll until the user scans the QR code, or timeout/denial.
Returns dict with app_id, app_secret, domain on success, None on failure.
@@ -610,7 +535,7 @@ def poll_registration_once(
*,
device_code: str,
domain: str = "feishu",
) -> dict[str, Any]:
) -> dict:
"""Poll the Feishu/Lark device-code flow once.
This non-blocking shape is used by WebUI. The CLI keeps using
@@ -624,7 +549,7 @@ def poll_registration_once(
"tp": "ob_app",
})
user_info = _as_json_object(res.get("user_info")) or {}
user_info = res.get("user_info") or {}
tenant_brand = user_info.get("tenant_brand")
if tenant_brand == "lark":
current_domain = "lark"
@@ -703,7 +628,9 @@ def sync_saved_feishu_identity_boundary(
from nanobot.config.loader import load_config, save_config
full_config = load_config()
feishu_cfg = _as_json_object(getattr(full_config.channels, "feishu", None)) or {}
feishu_cfg = getattr(full_config.channels, "feishu", None) or {}
if not isinstance(feishu_cfg, dict):
feishu_cfg = {}
defaults = feishu_default_config()
previous_identity_key = ""
@@ -735,7 +662,7 @@ def sync_saved_feishu_identity_boundary(
def save_registration_result(
result: dict[str, Any],
result: dict,
*,
instance_id: str = DEFAULT_INSTANCE_ID,
name: str | None = None,
@@ -744,7 +671,9 @@ def save_registration_result(
from nanobot.config.loader import load_config, save_config
full_config = load_config()
feishu_cfg = _as_json_object(getattr(full_config.channels, "feishu", None)) or {}
feishu_cfg = getattr(full_config.channels, "feishu", None) or {}
if not isinstance(feishu_cfg, dict):
feishu_cfg = {}
defaults = feishu_default_config()
app_id = str(result["app_id"]).strip()
domain = str(result.get("domain", "feishu") or "feishu").strip().lower()
@@ -867,7 +796,7 @@ def refresh_saved_feishu_identities(
def qr_register(
*,
initial_domain: str = "feishu",
) -> dict[str, Any] | None:
) -> dict | None:
"""Run the Feishu / Lark scan-to-create QR registration flow.
Returns on success:
@@ -911,7 +840,7 @@ def _print_qr_code(url: str) -> None:
def _qr_register_inner(
*,
initial_domain: str,
) -> dict[str, Any] | None:
) -> dict | None:
"""Run init → begin → poll. Raises on network/protocol errors."""
_LOGIN_CONSOLE.print("[cyan]Preparing Feishu/Lark login...[/cyan]")
_init_registration(initial_domain)
@@ -993,7 +922,7 @@ class FeishuChannel(BaseChannel):
self._loop: asyncio.AbstractEventLoop | None = None
self._stream_bufs: dict[str, _FeishuStreamBuf] = {}
self._bot_open_id: str | None = None
self._background_tasks: set[asyncio.Task[Any]] = set()
self._background_tasks: set[asyncio.Task] = set()
self._reaction_ids: dict[str, str] = {} # message_id → reaction_id
# ------------------------------------------------------------------
@@ -1120,12 +1049,12 @@ class FeishuChannel(BaseChannel):
builder = self._register_optional_event(
builder,
"register_p2_im_chat_member_bot_added_v1",
_ignore_event,
lambda _: None,
)
builder = self._register_optional_event(
builder,
"register_p2_im_chat_member_bot_deleted_v1",
_ignore_event,
lambda _: None,
)
event_handler = builder.build()
@@ -1184,11 +1113,9 @@ class FeishuChannel(BaseChannel):
if response.success():
import json
data = _as_json_object(json.loads(response.raw.content)) or {}
wrapped = _as_json_object(data.get("data")) or data
bot = _as_json_object(wrapped.get("bot")) or _as_json_object(data.get("bot")) or {}
open_id = bot.get("open_id")
return open_id if isinstance(open_id, str) else None
data = json.loads(response.raw.content)
bot = (data.get("data") or data).get("bot") or data.get("bot") or {}
return bot.get("open_id")
self.logger.warning("Failed to get bot info: code={}, msg={}", response.code, response.msg)
return None
except Exception as e:
@@ -1278,7 +1205,7 @@ class FeishuChannel(BaseChannel):
if "@_all" in raw_content:
return True
for mention in cast(list[Any], getattr(message, "mentions", None) or []):
for mention in getattr(message, "mentions", None) or []:
if self._is_bot_mention_event(mention):
return True
return False
@@ -1372,7 +1299,7 @@ class FeishuChannel(BaseChannel):
loop = asyncio.get_running_loop()
await loop.run_in_executor(None, self._remove_reaction_sync, message_id, reaction_id)
def _on_background_task_done(self, task: asyncio.Task[Any]) -> None:
def _on_background_task_done(self, task: asyncio.Task) -> None:
"""Callback: remove from tracking set and log unhandled exceptions."""
self._background_tasks.discard(task)
if task.cancelled():
@@ -1382,7 +1309,7 @@ class FeishuChannel(BaseChannel):
except Exception as exc:
self.logger.warning("Background task failed: {}", exc)
def _on_reaction_added(self, message_id: str, task: asyncio.Task[Any]) -> None:
def _on_reaction_added(self, message_id: str, task: asyncio.Task) -> None:
"""Callback: store reaction_id after background add-reaction completes."""
if task.cancelled():
return
@@ -1435,7 +1362,7 @@ class FeishuChannel(BaseChannel):
return text
@classmethod
def _parse_md_table(cls, table_text: str) -> dict[str, Any] | None:
def _parse_md_table(cls, table_text: str) -> dict | None:
"""Parse a markdown table into a Feishu table element."""
lines = [_line.strip() for _line in table_text.strip().split("\n") if _line.strip()]
if len(lines) < 3:
@@ -1459,7 +1386,7 @@ class FeishuChannel(BaseChannel):
],
}
def _build_card_elements(self, content: str) -> list[dict[str, Any]]:
def _build_card_elements(self, content: str) -> list[dict]:
"""Split content into div/markdown + table elements for Feishu card."""
protected = content
code_blocks: list[str] = []
@@ -1467,8 +1394,7 @@ class FeishuChannel(BaseChannel):
code_blocks.append(m.group(1))
protected = protected.replace(m.group(1), f"\x00CODE{len(code_blocks) - 1}\x00", 1)
elements: list[dict[str, Any]] = []
last_end = 0
elements, last_end = [], 0
for m in self._TABLE_RE.finditer(protected):
before = protected[last_end : m.start()]
if before.strip():
@@ -1490,8 +1416,8 @@ class FeishuChannel(BaseChannel):
@staticmethod
def _split_elements_by_table_limit(
elements: list[dict[str, Any]], max_tables: int = 1
) -> list[list[dict[str, Any]]]:
elements: list[dict], max_tables: int = 1
) -> list[list[dict]]:
"""Split card elements into groups with at most *max_tables* table elements each.
Feishu cards have a hard limit of one table per card (API error 11310).
@@ -1500,8 +1426,8 @@ class FeishuChannel(BaseChannel):
"""
if not elements:
return [[]]
groups: list[list[dict[str, Any]]] = []
current: list[dict[str, Any]] = []
groups: list[list[dict]] = []
current: list[dict] = []
table_count = 0
for el in elements:
if el.get("tag") == "table":
@@ -1518,15 +1444,15 @@ class FeishuChannel(BaseChannel):
groups.append(current)
return groups or [[]]
def _split_headings(self, content: str) -> list[dict[str, Any]]:
def _split_headings(self, content: str) -> list[dict]:
"""Split content by headings, converting headings to div elements."""
protected = content
code_blocks: list[str] = []
code_blocks = []
for m in self._CODE_BLOCK_RE.finditer(content):
code_blocks.append(m.group(1))
protected = protected.replace(m.group(1), f"\x00CODE{len(code_blocks) - 1}\x00", 1)
elements: list[dict[str, Any]] = []
elements = []
last_end = 0
for m in self._HEADING_RE.finditer(protected):
before = protected[last_end : m.start()].strip()
@@ -1634,10 +1560,10 @@ class FeishuChannel(BaseChannel):
Each line becomes a paragraph (row) in the post body.
"""
lines = content.strip().split("\n")
paragraphs: list[list[dict[str, Any]]] = []
paragraphs: list[list[dict]] = []
for line in lines:
elements: list[dict[str, Any]] = []
elements: list[dict] = []
last_end = 0
for m in cls._MD_LINK_RE.finditer(line):
@@ -1829,7 +1755,7 @@ class FeishuChannel(BaseChannel):
return candidate
async def _download_and_save_media(
self, msg_type: str, content_json: dict[str, Any], message_id: str | None = None
self, msg_type: str, content_json: dict, message_id: str | None = None
) -> tuple[str | None, str]:
"""
Download media from Feishu and save to local disk.
@@ -2277,7 +2203,6 @@ class FeishuChannel(BaseChannel):
stream_id: str | None = None,
stream_end: bool = False,
resuming: bool = False,
merge_next: bool = False,
) -> None:
"""Progressive streaming via CardKit: create card on first delta, stream-update on subsequent.
@@ -2293,10 +2218,6 @@ class FeishuChannel(BaseChannel):
rid_type = "chat_id" if chat_id.startswith("oc_") else "open_id"
# --- stream end: final update or fallback ---
if stream_end and merge_next:
if not delta:
return
stream_end = False
if stream_end:
message_id = meta.get("message_id")
# Only finalize the OnIt -> DONE reaction transition on the truly
@@ -2367,11 +2288,8 @@ class FeishuChannel(BaseChannel):
fallback_msg_id = self._thread_reply_target(meta)
if fallback_msg_id:
await loop.run_in_executor(
None, partial(
self._reply_message_sync,
fallback_msg_id,
"interactive",
card,
None, lambda: self._reply_message_sync(
fallback_msg_id, "interactive", card,
reply_in_thread=self._should_use_reply_in_thread(meta),
),
)
@@ -2627,9 +2545,6 @@ class FeishuChannel(BaseChannel):
return
try:
event = data.event
if event is None or event.message is None or event.sender is None:
self.logger.warning("Ignoring incomplete Feishu message event")
return
message = event.message
sender = event.sender
@@ -2646,20 +2561,6 @@ class FeishuChannel(BaseChannel):
chat_id = message.chat_id
chat_type = message.chat_type
msg_type = message.message_type
if not all(isinstance(value, str) and value for value in (
message_id,
sender_id,
chat_id,
chat_type,
msg_type,
)):
self.logger.warning("Ignoring Feishu message event with missing routing fields")
return
message_id = cast(str, message_id)
sender_id = cast(str, sender_id)
chat_id = cast(str, chat_id)
chat_type = cast(str, chat_type)
msg_type = cast(str, msg_type)
if chat_type == "group" and not self._is_group_message_for_bot(message):
self.logger.debug("skipping group message (not mentioned)")
@@ -2697,19 +2598,17 @@ class FeishuChannel(BaseChannel):
task.add_done_callback(lambda t: self._on_reaction_added(message_id, t))
# Parse content
content_parts: list[str] = []
media_paths: list[str] = []
content_parts = []
media_paths = []
try:
raw_content = message.content if isinstance(message.content, str) else ""
content_json = _as_json_object(json.loads(raw_content)) if raw_content else {}
content_json = json.loads(message.content) if message.content else {}
except json.JSONDecodeError:
content_json = {}
content_json = content_json or {}
if msg_type == "text":
text = content_json.get("text", "")
if isinstance(text, str) and text:
if text:
mentions = getattr(message, "mentions", None)
text = self._strip_leading_bot_mention(text, mentions)
text = self._resolve_mentions(text, mentions)
@@ -2759,12 +2658,9 @@ class FeishuChannel(BaseChannel):
content_parts.append(MSG_TYPE_MAP.get(msg_type, f"[{msg_type}]"))
# Extract reply context (parent/root message IDs)
parent_id = getattr(message, "parent_id", None)
root_id = getattr(message, "root_id", None)
thread_id = getattr(message, "thread_id", None)
parent_id = parent_id if isinstance(parent_id, str) else None
root_id = root_id if isinstance(root_id, str) else None
thread_id = thread_id if isinstance(thread_id, str) else None
parent_id = getattr(message, "parent_id", None) or None
root_id = getattr(message, "root_id", None) or None
thread_id = getattr(message, "thread_id", None) or None
# Prepend quoted message text when the user replied to another message
if parent_id and self._client:
@@ -1,122 +0,0 @@
from __future__ import annotations
import asyncio
import threading
from typing import Any
import pytest
from nanobot.channels.feishu import runtime as feishu
from nanobot.channels.feishu.connect import FeishuConnectStore
@pytest.mark.asyncio
async def test_feishu_cancel_wins_over_inflight_confirmation(
monkeypatch: pytest.MonkeyPatch,
) -> None:
poll_started = threading.Event()
release_poll = threading.Event()
saved_results: list[dict[str, Any]] = []
monkeypatch.setattr(feishu, "_init_registration", lambda _domain: None)
monkeypatch.setattr(
feishu,
"_begin_registration",
lambda _domain: {
"device_code": "device-cancel",
"qr_url": "https://qr.example/cancel",
"expire_in": 600,
"interval": 2,
},
)
def fake_poll_registration_once(**_kwargs: Any) -> dict[str, str]:
poll_started.set()
assert release_poll.wait(timeout=5)
return {
"status": "succeeded",
"domain": "feishu",
"app_id": "late-app",
"app_secret": "late-secret",
}
def fake_save_registration_result(
result: dict[str, Any],
**_kwargs: Any,
) -> str:
saved_results.append(result)
return "default"
monkeypatch.setattr(feishu, "poll_registration_once", fake_poll_registration_once)
monkeypatch.setattr(feishu, "save_registration_result", fake_save_registration_result)
store = FeishuConnectStore()
started = await store.handle("start", {})
query = {"session_id": [started["session_id"]]}
poll_task = asyncio.create_task(store.handle("poll", query))
assert await asyncio.to_thread(poll_started.wait, 5)
cancelled = await store.handle("cancel", query)
release_poll.set()
completed = await poll_task
assert cancelled["status"] == "cancelled"
assert completed["status"] == "cancelled"
assert saved_results == []
@pytest.mark.asyncio
async def test_feishu_cancel_does_not_interleave_with_registration_save(
monkeypatch: pytest.MonkeyPatch,
) -> None:
save_started = threading.Event()
release_save = threading.Event()
monkeypatch.setattr(feishu, "_init_registration", lambda _domain: None)
monkeypatch.setattr(
feishu,
"_begin_registration",
lambda _domain: {
"device_code": "device-lock",
"qr_url": "https://qr.example/lock",
"expire_in": 600,
"interval": 2,
},
)
monkeypatch.setattr(
feishu,
"poll_registration_once",
lambda **_kwargs: {
"status": "succeeded",
"domain": "feishu",
"app_id": "saved-app",
"app_secret": "saved-secret",
},
)
def fake_save_registration_result(
_result: dict[str, Any],
**_kwargs: Any,
) -> str:
save_started.set()
assert release_save.wait(timeout=5)
return "default"
monkeypatch.setattr(feishu, "save_registration_result", fake_save_registration_result)
store = FeishuConnectStore()
started = await store.handle("start", {})
query = {"session_id": [started["session_id"]]}
poll_task = asyncio.create_task(store.handle("poll", query))
assert await asyncio.to_thread(save_started.wait, 5)
cancel_task = asyncio.create_task(store.handle("cancel", query))
await asyncio.sleep(0)
assert not cancel_task.done()
release_save.set()
completed = await poll_task
cancelled = await cancel_task
assert completed["status"] == "succeeded"
assert cancelled["status"] == "cancelled"
@@ -1,10 +1,6 @@
import json
from nanobot.channels.feishu.runtime import (
_extract_element_content,
_extract_post_content,
_extract_share_card_content,
)
from nanobot.channels.feishu.runtime import _extract_share_card_content
def test_extract_interactive_card_reads_user_dsl_body_elements() -> None:
@@ -41,48 +37,3 @@ def test_extract_interactive_card_reads_table_rows() -> None:
}
assert _extract_share_card_content(content, "interactive") == "Name | Score\nAlice | 98"
def test_extract_post_content_tolerates_null_fields() -> None:
text, images = _extract_post_content(
{
"title": None,
"content": [
[
{"tag": "text", "text": None},
{"tag": "a", "text": None},
{"tag": "at", "user_name": None},
{"tag": "text", "text": "ok"},
{"tag": "code_block", "language": None, "text": None},
]
],
}
)
assert "@user" in text
assert "ok" in text
assert images == []
def test_extract_button_tolerates_null_multi_url() -> None:
element = {"tag": "button", "text": {"content": "Go"}, "multi_url": None}
assert _extract_element_content(element) == ["Go"]
def test_extract_column_set_tolerates_null_columns_and_elements() -> None:
assert _extract_element_content({"tag": "column_set", "columns": None}) == []
assert _extract_element_content(
{"tag": "column_set", "columns": [{"elements": None}]}
) == []
def test_extract_div_tolerates_null_fields() -> None:
assert _extract_element_content(
{"tag": "div", "text": {"content": "hi"}, "fields": None}
) == ["hi"]
def test_interactive_card_button_null_multi_url() -> None:
content = {
"elements": [{"tag": "button", "text": {"content": "Go"}, "multi_url": None}]
}
assert _extract_share_card_content(content, "interactive") == "Go"
@@ -285,27 +285,6 @@ class TestSendDelta:
settings_call = ch._client.cardkit.v1.card.settings.call_args[0][0]
assert settings_call.body.sequence == 5 # after final content seq 4
@pytest.mark.asyncio
async def test_stream_end_merge_next_preserves_buffer(self):
ch = _make_channel()
ch._stream_bufs["oc_chat1"] = _FeishuStreamBuf(
text="first-",
card_id="card_1",
sequence=3,
last_edit=time.monotonic(),
)
await ch.send_delta(
"oc_chat1",
"boundary",
stream_end=True,
merge_next=True,
)
assert ch._stream_bufs["oc_chat1"].text == "first-boundary"
ch._client.cardkit.v1.card_element.content.assert_not_called()
ch._client.cardkit.v1.card.settings.assert_not_called()
@pytest.mark.asyncio
async def test_stream_end_fallback_when_no_card_id(self):
"""If card creation failed, stream_end falls back to a plain card message."""
+6 -7
View File
@@ -1,4 +1,3 @@
# pyright: reportMissingTypeStubs=false, reportPrivateUsage=false
"""Shared Feishu/Lark WebSocket runtime.
The official lark_oapi websocket client stores an asyncio loop in a module-level
@@ -149,7 +148,7 @@ class FeishuWsRunner:
async def _client_main(
self, key: str, client: _LarkWsClient, stop_event: asyncio.Event
) -> None:
ping_task: asyncio.Task[None] | None = None
ping_task: asyncio.Task | None = None
while not stop_event.is_set():
try:
await client._connect()
@@ -172,12 +171,12 @@ class FeishuWsRunner:
await client._disconnect()
_runner: FeishuWsRunner | None = None
_RUNNER: FeishuWsRunner | None = None
def get_feishu_ws_runner() -> FeishuWsRunner:
"""Return the process-wide Feishu WebSocket runner."""
global _runner
if _runner is None:
_runner = FeishuWsRunner()
return _runner
global _RUNNER
if _RUNNER is None:
_RUNNER = FeishuWsRunner()
return _RUNNER
+16 -42
View File
@@ -4,11 +4,10 @@ from __future__ import annotations
import asyncio
import hashlib
import inspect
from collections.abc import Callable, Iterable
from contextlib import suppress
from pathlib import Path
from typing import TYPE_CHECKING, Any, cast
from typing import TYPE_CHECKING, Any
from loguru import logger
@@ -41,9 +40,7 @@ from nanobot.utils.restart import (
)
if TYPE_CHECKING:
from nanobot.cron.service import CronService
from nanobot.session.manager import SessionManager
from nanobot.triggers.local_store import LocalTriggerStore
def _default_webui_dist() -> Path | None:
@@ -92,15 +89,14 @@ class ChannelManager:
bus: MessageBus,
*,
session_manager: "SessionManager | None" = None,
cron_service: CronService | None = None,
local_trigger_store: LocalTriggerStore | None = None,
cron_service: Any | None = None,
local_trigger_store: Any | None = None,
webui_runtime_model_name: Callable[[], str | None] | None = None,
webui_cron_pending_job_ids: Callable[[str], set[str]] | None = None,
webui_local_trigger_pending_ids: Callable[[str], set[str]] | None = None,
webui_static_dist: bool = True,
webui_runtime_surface: str = "browser",
webui_runtime_capabilities: dict[str, Any] | None = None,
webui_skill_state_action: Callable[[set[str]], None] | None = None,
):
self.config = config
self.bus = bus
@@ -113,13 +109,12 @@ class ChannelManager:
self._webui_static_dist = webui_static_dist
self._webui_runtime_surface = webui_runtime_surface
self._webui_runtime_capabilities = dict(webui_runtime_capabilities or {})
self._webui_skill_state_action = webui_skill_state_action
self.channels: dict[str, BaseChannel] = {}
self._channel_owners: dict[str, str] = {}
self._channel_runtime_specs: dict[str, tuple[str, str]] = {}
self._channel_errors: dict[str, str] = {}
self._channel_tasks: dict[str, asyncio.Task[None]] = {}
self._dispatch_task: asyncio.Task[None] | None = None
self._channel_tasks: dict[str, asyncio.Task] = {}
self._dispatch_task: asyncio.Task | None = None
self._started = False
self._origin_reply_fingerprints: dict[tuple[str, str, str], str] = {}
@@ -180,7 +175,6 @@ class ChannelManager:
local_trigger_pending_ids=self._webui_local_trigger_pending_ids,
channel_feature_action=self.apply_channel_feature_action,
channel_runtime_status=self.get_status,
skill_state_action=self._webui_skill_state_action,
logger=logger,
)
kwargs["gateway"] = gateway
@@ -296,11 +290,10 @@ class ChannelManager:
for name, ch in self.channels.items():
cfg = ch.config
if isinstance(cfg, dict):
config_data = cast(dict[str, Any], cfg)
if "allow_from" in config_data:
allow = config_data.get("allow_from")
if "allow_from" in cfg:
allow = cfg.get("allow_from")
else:
allow = config_data.get("allowFrom")
allow = cfg.get("allowFrom")
else:
allow = getattr(cfg, "allow_from", None)
if allow is None:
@@ -327,12 +320,11 @@ class ChannelManager:
Pydantic models.
"""
if isinstance(section, dict):
section_data = cast(dict[str, Any], section)
value = section_data.get(key)
value = section.get(key)
if value is None:
camel = _BOOL_CAMEL_ALIASES.get(key)
if camel:
value = section_data.get(camel)
value = section.get(camel)
return value if isinstance(value, bool) else default
value = getattr(section, key, None)
return value if isinstance(value, bool) else default
@@ -351,7 +343,7 @@ class ChannelManager:
errors[name] = "Channel failed to start. Check gateway logs."
logger.exception("Failed to start channel {}", name)
def _start_channel_task(self, name: str, channel: BaseChannel) -> asyncio.Task[None]:
def _start_channel_task(self, name: str, channel: BaseChannel) -> asyncio.Task:
logger.info("Starting {} channel...", name)
task = asyncio.create_task(self._start_channel(name, channel))
self._channel_tasks[name] = task
@@ -368,8 +360,7 @@ class ChannelManager:
await channel.stop()
logger.info("Stopped {} channel", name)
except asyncio.CancelledError:
current_task = asyncio.current_task()
if current_task is not None and current_task.cancelling():
if asyncio.current_task() and asyncio.current_task().cancelling():
raise
logger.debug("Channel {} stop task was already cancelled", name)
except Exception:
@@ -561,7 +552,7 @@ class ChannelManager:
self._dispatch_task = asyncio.create_task(self._dispatch_outbound())
# Start channels
tasks: list[asyncio.Task[None]] = []
tasks = []
for name, channel in self.channels.items():
tasks.append(self._start_channel_task(name, channel))
@@ -772,29 +763,13 @@ class ChannelManager:
msg: OutboundMessage,
event: StreamDeltaEvent | StreamEndEvent,
) -> None:
kwargs: dict[str, Any] = {
"stream_id": event.stream_id,
"stream_end": isinstance(event, StreamEndEvent),
"resuming": event.resuming if isinstance(event, StreamEndEvent) else False,
}
if isinstance(event, StreamEndEvent) and event.merge_next:
try:
signature = inspect.signature(channel.send_delta)
if (
"merge_next" in signature.parameters
or any(
parameter.kind is inspect.Parameter.VAR_KEYWORD
for parameter in signature.parameters.values()
)
):
kwargs["merge_next"] = True
except (TypeError, ValueError):
pass
await channel.send_delta(
msg.chat_id,
msg.content,
msg.metadata,
**kwargs,
stream_id=event.stream_id,
stream_end=isinstance(event, StreamEndEvent),
resuming=event.resuming if isinstance(event, StreamEndEvent) else False,
)
@staticmethod
@@ -875,7 +850,6 @@ class ChannelManager:
final_event = StreamEndEvent(
stream_id=next_stream_id,
resuming=next_event.resuming,
merge_next=next_event.merge_next,
)
# Stream ended - stop coalescing this stream
break
+41 -118
View File
@@ -1,7 +1,5 @@
"""Matrix (Element) channel — inbound sync + outbound message/media delivery."""
# pyright: reportMissingTypeStubs=false
import asyncio
import html
import json
@@ -12,7 +10,7 @@ import time
from contextlib import suppress
from dataclasses import dataclass
from pathlib import Path
from typing import Any, Callable, Literal, Protocol, TypeAlias, cast
from typing import Any, Literal, TypeAlias
from urllib.parse import quote, unquote, urlparse
from pydantic import Field
@@ -77,18 +75,6 @@ MATRIX_MEDIA_EVENT_FILTER = (RoomMessageMedia, RoomEncryptedMedia)
MatrixMediaEvent: TypeAlias = RoomMessageMedia | RoomEncryptedMedia
class _MatrixCallbackRegistrar(Protocol):
"""Runtime callback surface whose upstream stubs reject valid filtered handlers."""
def add_event_callback(self, callback: Callable[..., Any], event_filter: Any) -> None: ...
def add_to_device_callback(
self,
callback: Callable[..., Any],
event_filter: Any,
) -> None: ...
def add_response_callback(self, callback: Callable[..., Any], response_filter: Any) -> None: ...
class _MediaTooLargeError(Exception):
"""Raised when an inbound Matrix media download exceeds the configured cap."""
@@ -201,7 +187,7 @@ def _render_markdown_html(text: str) -> str | None:
"""Render markdown to sanitized HTML; returns None for plain text."""
try:
masked_text = _mask_mxc_markdown_image_sources(text)
rendered = _mask_mxc_image_sources(cast(str, MATRIX_MARKDOWN(masked_text)))
rendered = _mask_mxc_image_sources(MATRIX_MARKDOWN(masked_text))
formatted = _unmask_mxc_image_sources(MATRIX_HTML_CLEANER.clean(rendered).strip())
except Exception:
return None
@@ -243,17 +229,16 @@ def _build_matrix_text_content(
content["format"] = MATRIX_HTML_FORMAT
content["formatted_body"] = html
if event_id:
new_content: dict[str, object] = {
content["m.new_content"] = {
"body": text,
"msgtype": "m.text",
}
content["m.new_content"] = new_content
content["m.relates_to"] = {
"rel_type": "m.replace",
"event_id": event_id,
}
if thread_relates_to:
new_content["m.relates_to"] = thread_relates_to
content["m.new_content"]["m.relates_to"] = thread_relates_to
elif thread_relates_to:
content["m.relates_to"] = thread_relates_to
@@ -291,7 +276,7 @@ class MatrixChannel(BaseChannel):
name = "matrix"
display_name = "Matrix"
_STREAM_EDIT_INTERVAL = 2 # min seconds between edit_message_text calls
monotonic_time: Callable[[], float] = staticmethod(time.monotonic)
monotonic_time = time.monotonic
@classmethod
def default_config(cls) -> dict[str, Any]:
@@ -309,8 +294,8 @@ class MatrixChannel(BaseChannel):
config = MatrixConfig.model_validate(config)
super().__init__(config, bus)
self.client: AsyncClient | None = None
self._sync_task: asyncio.Task[None] | None = None
self._typing_tasks: dict[str, asyncio.Task[None]] = {}
self._sync_task: asyncio.Task | None = None
self._typing_tasks: dict[str, asyncio.Task] = {}
self._restrict_to_workspace = bool(restrict_to_workspace)
self._workspace = (
Path(workspace).expanduser().resolve(strict=False) if workspace is not None else None
@@ -340,7 +325,7 @@ class MatrixChannel(BaseChannel):
self.client = AsyncClient(
homeserver=self.config.homeserver,
user=self.config.user_id,
store_path=str(self.store_path),
store_path=self.store_path,
config=AsyncClientConfig(
store_sync_tokens=True,
encryption_enabled=self.config.e2ee_enabled,
@@ -401,16 +386,6 @@ class MatrixChannel(BaseChannel):
self._sync_task = asyncio.create_task(self._sync_loop())
def _require_client(self) -> AsyncClient:
if self.client is None:
raise RuntimeError("Matrix client is not started")
return self.client
def _callback_registrar(self) -> _MatrixCallbackRegistrar:
# matrix-nio's callback annotations do not model filtered subtype or
# async handlers, although the runtime API supports both.
return cast(_MatrixCallbackRegistrar, self._require_client())
async def stop(self) -> None:
"""Stop the Matrix channel with graceful sync shutdown."""
self._running = False
@@ -453,10 +428,9 @@ class MatrixChannel(BaseChannel):
seen: set[str] = set()
candidates: list[Path] = []
for raw in media:
raw_value = cast(object, raw)
if not isinstance(raw_value, str) or not raw_value.strip():
if not isinstance(raw, str) or not raw.strip():
continue
path = Path(raw_value.strip()).expanduser()
path = Path(raw.strip()).expanduser()
try:
key = str(path.resolve(strict=False))
except OSError:
@@ -561,13 +535,8 @@ class MatrixChannel(BaseChannel):
self.logger.error("Matrix media upload failed for %s", filename, exc_info=True)
return fail
is_tuple_result = isinstance(cast(object, upload_result), tuple)
upload_response = upload_result[0] if is_tuple_result else upload_result
encryption_info = (
upload_result[1]
if is_tuple_result and isinstance(cast(object, upload_result[1]), dict)
else None
)
upload_response = upload_result[0] if isinstance(upload_result, tuple) else upload_result
encryption_info = upload_result[1] if isinstance(upload_result, tuple) and isinstance(upload_result[1], dict) else None
if isinstance(upload_response, UploadError):
return fail
mxc_url = getattr(upload_response, "content_uri", None)
@@ -629,14 +598,9 @@ class MatrixChannel(BaseChannel):
stream_id: str | None = None,
stream_end: bool = False,
resuming: bool = False,
merge_next: bool = False,
) -> None:
relates_to = self._build_thread_relates_to(metadata)
if stream_end and merge_next:
if not delta:
return
stream_end = False
if stream_end:
stream_key = _matrix_stream_key(chat_id, stream_id)
buf = self._stream_bufs.pop(stream_key, None)
@@ -676,31 +640,28 @@ class MatrixChannel(BaseChannel):
buf.last_edit = now
if not buf.event_id:
# we are editing the same message all the time, so only the first time the event id needs to be set
buf.event_id = cast(RoomSendResponse, response).event_id
buf.event_id = response.event_id
except Exception:
self.logger.error("Stream send/edit failed for chat_id=%s", chat_id, exc_info=True)
await self._stop_typing_keepalive(chat_id, clear_typing=True)
def _register_event_callbacks(self) -> None:
client = self._callback_registrar()
client.add_event_callback(self._on_message, RoomMessageText)
client.add_event_callback(self._on_media_message, MATRIX_MEDIA_EVENT_FILTER)
client.add_event_callback(self._on_room_invite, InviteEvent)
self.client.add_event_callback(self._on_message, RoomMessageText)
self.client.add_event_callback(self._on_media_message, MATRIX_MEDIA_EVENT_FILTER)
self.client.add_event_callback(self._on_room_invite, InviteEvent)
def _register_to_device_callbacks(self) -> None:
if self.config.e2ee_enabled and self.config.sas_verification:
client = self._callback_registrar()
client.add_to_device_callback(
self.client.add_to_device_callback(
self._on_key_verification_event,
(KeyVerificationEvent,),
)
def _register_response_callbacks(self) -> None:
client = self._callback_registrar()
client.add_response_callback(self._on_sync_error, SyncError)
client.add_response_callback(self._on_join_error, JoinError)
client.add_response_callback(self._on_send_error, RoomSendError)
self.client.add_response_callback(self._on_sync_error, SyncError)
self.client.add_response_callback(self._on_join_error, JoinError)
self.client.add_response_callback(self._on_send_error, RoomSendError)
def _is_sas_sender_allowed(self, sender: str) -> bool:
return bool(sender and self.is_allowed(sender))
@@ -825,8 +786,7 @@ class MatrixChannel(BaseChannel):
backoff = 2.0
while self._running:
try:
client = self._require_client()
await client.sync_forever(timeout=30000, full_state=True)
await self.client.sync_forever(timeout=30000, full_state=True)
backoff = 2.0
except asyncio.CancelledError:
break
@@ -838,8 +798,7 @@ class MatrixChannel(BaseChannel):
async def _on_room_invite(self, room: MatrixRoom, event: InviteEvent) -> None:
if self.is_allowed(event.sender):
client = self._require_client()
await client.join(room.room_id)
await self.client.join(room.room_id)
def _is_direct_room(self, room: MatrixRoom) -> bool:
count = getattr(room, "member_count", None)
@@ -850,19 +809,13 @@ class MatrixChannel(BaseChannel):
source = getattr(event, "source", None)
if not isinstance(source, dict):
return False
source_data = cast(dict[str, Any], source)
content = cast(dict[str, Any], source_data.get("content") or {})
mentions = cast(object, content.get("m.mentions"))
mentions = (source.get("content") or {}).get("m.mentions")
if not isinstance(mentions, dict):
return False
mentions_data = cast(dict[str, Any], mentions)
user_ids = cast(object, mentions_data.get("user_ids"))
user_ids = mentions.get("user_ids")
if isinstance(user_ids, list) and self.config.user_id in user_ids:
return True
return bool(
self.config.allow_room_mentions
and mentions_data.get("room") is True
)
return bool(self.config.allow_room_mentions and mentions.get("room") is True)
def _is_pre_startup_event(self, event: RoomMessage) -> bool:
"""Skip events that landed in the timeline before this process started.
@@ -897,21 +850,14 @@ class MatrixChannel(BaseChannel):
source = getattr(event, "source", None)
if not isinstance(source, dict):
return {}
source_data = cast(dict[str, Any], source)
content = cast(object, source_data.get("content"))
return cast(dict[str, Any], content) if isinstance(content, dict) else {}
content = source.get("content")
return content if isinstance(content, dict) else {}
def _event_thread_root_id(self, event: RoomMessage) -> str | None:
relates_to = cast(
object,
self._event_source_content(event).get("m.relates_to"),
)
if not isinstance(relates_to, dict):
relates_to = self._event_source_content(event).get("m.relates_to")
if not isinstance(relates_to, dict) or relates_to.get("rel_type") != "m.thread":
return None
relation = cast(dict[str, Any], relates_to)
if relation.get("rel_type") != "m.thread":
return None
root_id = cast(object, relation.get("event_id"))
root_id = relates_to.get("event_id")
return root_id if isinstance(root_id, str) and root_id else None
def _thread_metadata(self, event: RoomMessage) -> dict[str, str] | None:
@@ -937,7 +883,7 @@ class MatrixChannel(BaseChannel):
def _event_attachment_type(self, event: MatrixMediaEvent) -> str:
msgtype = self._event_source_content(event).get("msgtype")
return _MSGTYPE_MAP.get(cast(str, msgtype), "file")
return _MSGTYPE_MAP.get(msgtype, "file")
@staticmethod
def _is_encrypted_media_event(event: MatrixMediaEvent) -> bool:
@@ -946,27 +892,16 @@ class MatrixChannel(BaseChannel):
and isinstance(getattr(event, "iv", None), str))
def _event_declared_size_bytes(self, event: MatrixMediaEvent) -> int | None:
info = cast(object, self._event_source_content(event).get("info"))
size = (
cast(dict[str, Any], info).get("size")
if isinstance(info, dict)
else None
)
info = self._event_source_content(event).get("info")
size = info.get("size") if isinstance(info, dict) else None
return size if type(size) is int and size >= 0 else None # noqa: E721
def _event_mime(self, event: MatrixMediaEvent) -> str | None:
info = cast(object, self._event_source_content(event).get("info"))
if (
isinstance(info, dict)
and isinstance(
mime := cast(dict[str, Any], info).get("mimetype"),
str,
)
and mime
):
return mime
mime = getattr(event, "mimetype", None)
return mime if isinstance(mime, str) and mime else None
info = self._event_source_content(event).get("info")
if isinstance(info, dict) and isinstance(m := info.get("mimetype"), str) and m:
return m
m = getattr(event, "mimetype", None)
return m if isinstance(m, str) and m else None
def _event_filename(self, event: MatrixMediaEvent, attachment_type: str) -> str:
body = getattr(event, "body", None)
@@ -1033,21 +968,9 @@ class MatrixChannel(BaseChannel):
def _decrypt_media_bytes(self, event: MatrixMediaEvent, ciphertext: bytes) -> bytes | None:
key_obj, hashes, iv = getattr(event, "key", None), getattr(event, "hashes", None), getattr(event, "iv", None)
key = (
cast(dict[str, Any], key_obj).get("k")
if isinstance(key_obj, dict)
else None
)
sha256 = (
cast(dict[str, Any], hashes).get("sha256")
if isinstance(hashes, dict)
else None
)
if (
not isinstance(key, str)
or not isinstance(sha256, str)
or not isinstance(iv, str)
):
key = key_obj.get("k") if isinstance(key_obj, dict) else None
sha256 = hashes.get("sha256") if isinstance(hashes, dict) else None
if not all(isinstance(v, str) for v in (key, sha256, iv)):
return None
try:
return decrypt_attachment(ciphertext, key, sha256, iv)
@@ -1937,29 +1937,6 @@ async def test_send_delta_stream_end_replaces_existing_message() -> None:
}
@pytest.mark.asyncio
async def test_send_delta_merge_next_preserves_buffer() -> None:
channel = MatrixChannel(_make_config(), MessageBus())
client = _FakeAsyncClient("", "", "", None)
channel.client = client
channel._stream_bufs["!room:matrix.org"] = matrix_module._StreamBuf(
text="first-",
event_id="event-1",
last_edit=100.0,
)
channel.monotonic_time = lambda: 100.1
await channel.send_delta(
"!room:matrix.org",
"boundary",
stream_end=True,
merge_next=True,
)
assert channel._stream_bufs["!room:matrix.org"].text == "first-boundary"
assert client.room_send_calls == []
@pytest.mark.asyncio
async def test_send_delta_keeps_same_room_stream_ids_independent(monkeypatch) -> None:
channel = MatrixChannel(_make_config(), MessageBus())
+42 -73
View File
@@ -6,7 +6,7 @@ import asyncio
import json
import re
from pathlib import Path
from typing import Any, cast
from typing import Any
import httpx
from pydantic import Field
@@ -56,7 +56,7 @@ class MattermostConfig(Base):
react_emoji: str = "eyes"
done_emoji: str = "white_check_mark"
send_progress: bool = True
send_tool_hints: bool = True
send_tool_hints: bool = False
dm: MattermostDMConfig = Field(default_factory=MattermostDMConfig)
@@ -86,7 +86,7 @@ class MattermostChannel(BaseChannel):
self._server_url = config.server_url.rstrip("/")
self._ws_url = _server_url_to_ws_url(self._server_url)
self._http_client: httpx.AsyncClient | None = None
self._ws_task: asyncio.Task[None] | None = None
self._ws_task: asyncio.Task | None = None
self._self_id: str | None = None
self._self_username: str | None = None
self._self_email: str | None = None
@@ -118,7 +118,7 @@ class MattermostChannel(BaseChannel):
try:
resp = await self._http_client.get("/api/v4/users/me")
resp.raise_for_status()
me = cast(dict[str, Any], resp.json())
me = resp.json()
self._self_id = me.get("id")
self._self_username = me.get("username")
self._self_email = me.get("email", "")
@@ -169,7 +169,7 @@ class MattermostChannel(BaseChannel):
self.logger.debug("websocket connected")
delay = MATTERMOST_WS_RECONNECT_BASE_DELAY
async for raw in ws:
await self._handle_ws_message(cast(dict[str, Any], json.loads(raw)))
await self._handle_ws_message(json.loads(raw))
except asyncio.CancelledError:
break
except Exception as e:
@@ -191,15 +191,12 @@ class MattermostChannel(BaseChannel):
# Event: posted ------------------------------------------------------------
async def _handle_posted_event(self, msg: dict[str, Any]) -> None:
data = cast(dict[str, Any], msg.get("data", {}))
broadcast = cast(dict[str, Any], msg.get("broadcast", {}))
data = msg.get("data", {})
broadcast = msg.get("broadcast", {})
raw_post = data.get("post", "{}")
try:
post = cast(
dict[str, Any],
json.loads(raw_post) if isinstance(raw_post, str) else raw_post,
)
post = json.loads(raw_post) if isinstance(raw_post, str) else raw_post
except json.JSONDecodeError:
self.logger.warning("failed to parse post json")
return
@@ -209,7 +206,7 @@ class MattermostChannel(BaseChannel):
message_text = post.get("message", "")
root_id = post.get("root_id", "") or ""
post_id = post.get("id", "")
file_ids = cast(list[str], post.get("file_ids", []))
file_ids: list[str] = post.get("file_ids", [])
if self._self_id and sender_id == self._self_id:
return
@@ -295,11 +292,11 @@ class MattermostChannel(BaseChannel):
# Event: action ------------------------------------------------------------
async def _handle_action_event(self, msg: dict[str, Any]) -> None:
data = cast(dict[str, Any], msg.get("data", {}))
data = msg.get("data", {})
sender_id = data.get("user_id", "")
channel_id = data.get("channel_id", "")
context = cast(dict[str, Any], data.get("context", {}) or {})
value = cast(str, context.get("selected_option", ""))
context = data.get("context", {}) or {}
value = context.get("selected_option", "")
if not sender_id or not channel_id or not value:
return
@@ -322,13 +319,10 @@ class MattermostChannel(BaseChannel):
# Event: post_deleted ------------------------------------------------------
async def _handle_post_deleted_event(self, msg: dict[str, Any]) -> None:
data = cast(dict[str, Any], msg.get("data", {}))
data = msg.get("data", {})
raw_post = data.get("post", "{}")
try:
post = cast(
dict[str, Any],
json.loads(raw_post) if isinstance(raw_post, str) else raw_post,
)
post = json.loads(raw_post) if isinstance(raw_post, str) else raw_post
except json.JSONDecodeError:
return
post_id = post.get("id", "")
@@ -369,15 +363,15 @@ class MattermostChannel(BaseChannel):
return chat_id in self.config.group_allow_from
return False
_bot_mention_re: re.Pattern[str] | None = None
_BOT_MENTION_RE: re.Pattern | None = None
def _is_mentioned(self, text: str) -> bool:
if not self._self_username:
return False
if self._bot_mention_re is None:
if self._BOT_MENTION_RE is None:
pat = r"(?<![@\w])@" + re.escape(self._self_username) + r"(?![@\w])"
self._bot_mention_re = re.compile(pat)
return bool(self._bot_mention_re.search(text))
self._BOT_MENTION_RE = re.compile(pat)
return bool(self._BOT_MENTION_RE.search(text))
def _strip_bot_mention(self, text: str) -> str:
if not text or not self._self_username:
@@ -438,8 +432,8 @@ class MattermostChannel(BaseChannel):
self.logger.warning("thread context unavailable for {}: {}", key, e)
return text
posts = cast(dict[str, dict[str, Any]], data.get("posts", {}))
order = cast(list[str], data.get("order", []))
posts = data.get("posts", {})
order = data.get("order", [])
if not order:
return text
@@ -473,11 +467,8 @@ class MattermostChannel(BaseChannel):
try:
chat_id = msg.chat_id
meta = msg.metadata or {}
mm_meta = cast(dict[str, Any], meta.get("mattermost", {}) or {})
root_id = cast(
str | None,
mm_meta.get("root_id") or mm_meta.get("thread_ts") or meta.get("root_id"),
)
mm_meta = meta.get("mattermost", {}) or {}
root_id = mm_meta.get("root_id") or mm_meta.get("thread_ts") or meta.get("root_id")
file_ids: list[str] = []
for media_path in msg.media or []:
@@ -524,13 +515,12 @@ class MattermostChannel(BaseChannel):
stream_id: str | None = None,
stream_end: bool = False,
resuming: bool = False,
merge_next: bool = False,
) -> None:
if not self._http_client:
return
meta = metadata or {}
stream_id = cast(str, stream_id or meta.get("_stream_id") or chat_id)
stream_id = stream_id or meta.get("_stream_id") or chat_id
stream_end = stream_end or bool(meta.get("_stream_end"))
resuming = resuming or bool(meta.get("_resuming"))
@@ -542,25 +532,17 @@ class MattermostChannel(BaseChannel):
final += delta
if resuming:
if merge_next:
self._stream_buffers[stream_id] = final
self._stream_committed[stream_id] = final
else:
self._clear_stream_state(stream_id)
self._clear_stream_state(stream_id)
return
if final and not meta.get("_progress"):
mm_meta = (
cast(dict[str, Any], meta.get("mattermost", {}) or {})
if isinstance(meta.get("mattermost"), dict)
else {}
)
root_id = cast(str | None, (
mm_meta = (meta.get("mattermost", {}) or {}) if isinstance(meta.get("mattermost"), dict) else {}
root_id = (
mm_meta.get("root_id")
or mm_meta.get("thread_ts")
or meta.get("root_id")
or self._stream_root_ids.get(stream_id)
))
)
chunks = split_message(final, MATTERMOST_MAX_MESSAGE_LEN)
first_post_id: str | None = None
try:
@@ -592,15 +574,8 @@ class MattermostChannel(BaseChannel):
if not delta.strip():
return
mm_meta = (
cast(dict[str, Any], meta.get("mattermost", {}) or {})
if isinstance(meta.get("mattermost"), dict)
else {}
)
root_id = cast(
str | None,
mm_meta.get("root_id") or mm_meta.get("thread_ts") or meta.get("root_id"),
)
mm_meta = (meta.get("mattermost", {}) or {}) if isinstance(meta.get("mattermost"), dict) else {}
root_id = mm_meta.get("root_id") or mm_meta.get("thread_ts") or meta.get("root_id")
if root_id:
self._stream_root_ids[stream_id] = root_id
committed = self._stream_committed.get(stream_id, "")
@@ -618,25 +593,20 @@ class MattermostChannel(BaseChannel):
# API helpers ---------------------------------------------------------------
def _require_http_client(self) -> httpx.AsyncClient:
if self._http_client is None:
raise RuntimeError("Mattermost client is not started")
return self._http_client
async def _api_get(self, path: str) -> dict[str, Any]:
resp = await self._require_http_client().get(path)
resp = await self._http_client.get(path)
resp.raise_for_status()
return cast(dict[str, Any], resp.json())
return resp.json()
async def _api_post(self, path: str, json_data: dict[str, Any]) -> dict[str, Any]:
resp = await self._require_http_client().post(path, json=json_data)
resp = await self._http_client.post(path, json=json_data)
resp.raise_for_status()
return cast(dict[str, Any], resp.json())
return resp.json()
async def _api_put(self, path: str, json_data: dict[str, Any]) -> dict[str, Any]:
resp = await self._require_http_client().put(path, json=json_data)
resp = await self._http_client.put(path, json=json_data)
resp.raise_for_status()
return cast(dict[str, Any], resp.json())
return resp.json()
async def _create_post(
self,
@@ -667,14 +637,14 @@ class MattermostChannel(BaseChannel):
try:
files = {"files": (path.name, path.read_bytes())}
resp = await self._require_http_client().post(
resp = await self._http_client.post(
"/api/v4/files",
data={"channel_id": channel_id},
files=files,
)
resp.raise_for_status()
data = cast(dict[str, Any], resp.json())
infos = cast(list[dict[str, Any]], data.get("file_infos", []))
data = resp.json()
infos = data.get("file_infos", [])
if infos:
return infos[0].get("id")
except Exception as e:
@@ -683,15 +653,14 @@ class MattermostChannel(BaseChannel):
async def _download_file(self, file_id: str) -> str | None:
try:
client = self._require_http_client()
info_resp = await client.get(f"/api/v4/files/{file_id}/info")
info_resp = await self._http_client.get(f"/api/v4/files/{file_id}/info")
info_resp.raise_for_status()
info = cast(dict[str, Any], info_resp.json())
info = info_resp.json()
name = Path(info.get("name", file_id)).name
out = Path(get_media_dir("mattermost")) / safe_filename(f"{file_id}_{name}")
out.parent.mkdir(parents=True, exist_ok=True)
dl = await client.get(f"/api/v4/files/{file_id}")
dl = await self._http_client.get(f"/api/v4/files/{file_id}")
dl.raise_for_status()
out.write_bytes(dl.content)
return str(out)
@@ -711,7 +680,7 @@ class MattermostChannel(BaseChannel):
async def _remove_reaction(self, post_id: str, emoji: str) -> None:
if not self._self_id or not emoji:
return
resp = await self._require_http_client().delete(
resp = await self._http_client.delete(
f"/api/v4/users/{self._self_id}/posts/{post_id}/reactions/{emoji}",
)
if resp.status_code >= 400:
@@ -119,7 +119,6 @@ def test_config_defaults():
assert config.token == ""
assert config.streaming is True
assert config.streaming_max_chars == 16000
assert config.send_tool_hints is True
assert config.dm.enabled is True
assert config.dm.policy == "open"
assert config.reply_in_thread is True
@@ -132,7 +131,6 @@ def test_config_camelcase_aliases():
"allowFromMatchMode": "username",
"streamingMaxChars": 8000,
"replyInThread": False,
"sendToolHints": False,
}
config = MattermostConfig.model_validate(raw)
assert config.server_url == "https://mm.example.com"
@@ -140,13 +138,11 @@ def test_config_camelcase_aliases():
assert config.allow_from_match_mode == "username"
assert config.streaming_max_chars == 8000
assert config.reply_in_thread is False
assert config.send_tool_hints is False
def test_config_default_config_classmethod():
d = MattermostChannel.default_config()
assert d["enabled"] is False
assert d["sendToolHints"] is True
assert d["serverUrl"] == ""
assert d["token"] == ""
@@ -582,33 +578,6 @@ async def test_stream_end_keyword_resuming_does_not_post_or_mark_done():
assert "s1" not in channel._stream_buffers
@pytest.mark.asyncio
async def test_stream_end_merge_next_preserves_buffer_until_final_end():
channel, fake = _make_channel()
channel._self_id = "bot_id"
fake.set_post_response("/api/v4/posts", {"id": "stream_post_1"})
await channel.send_delta("chan_1", "first ", stream_id="s1")
await channel.send_delta(
"chan_1",
"boundary ",
stream_id="s1",
stream_end=True,
resuming=True,
merge_next=True,
)
assert channel._stream_buffers["s1"] == "first boundary "
await channel.send_delta("chan_1", "second", stream_id="s1")
await channel.send_delta("chan_1", "", stream_id="s1", stream_end=True)
posts = [call for call in fake.post_calls if call["path"] == "/api/v4/posts"]
assert len(posts) == 1
assert posts[0]["json"]["message"] == "first boundary second"
assert "s1" not in channel._stream_buffers
@pytest.mark.asyncio
async def test_stream_end_failure_keeps_buffer_for_retry():
channel, fake = _make_channel()
+54 -107
View File
@@ -1,4 +1,3 @@
# pyright: reportConstantRedefinition=false, reportMissingTypeStubs=false
"""Mochat channel implementation using Socket.IO with HTTP polling fallback."""
from __future__ import annotations
@@ -6,11 +5,10 @@ from __future__ import annotations
import asyncio
import json
from collections import deque
from collections.abc import Awaitable, Callable
from contextlib import suppress
from dataclasses import dataclass, field
from datetime import datetime
from typing import Any, cast
from typing import Any
import httpx
from pydantic import Field
@@ -29,7 +27,7 @@ except ImportError:
SOCKETIO_AVAILABLE = False
try:
import msgpack # noqa: F401 # pyright: ignore[reportUnusedImport]
import msgpack # noqa: F401
MSGPACK_AVAILABLE = True
except ImportError:
MSGPACK_AVAILABLE = False
@@ -59,7 +57,7 @@ class DelayState:
"""Per-target delayed message state."""
entries: list[MochatBufferedEntry] = field(default_factory=list)
lock: asyncio.Lock = field(default_factory=asyncio.Lock)
timer: asyncio.Task[None] | None = None
timer: asyncio.Task | None = None
@dataclass
@@ -73,12 +71,12 @@ class MochatTarget:
# Pure helpers
# ---------------------------------------------------------------------------
def _safe_dict(value: Any) -> dict[str, Any]:
def _safe_dict(value: Any) -> dict:
"""Return *value* if it's a dict, else empty dict."""
return cast(dict[str, Any], value) if isinstance(value, dict) else {}
return value if isinstance(value, dict) else {}
def _str_field(src: dict[str, Any], *keys: str) -> str:
def _str_field(src: dict, *keys: str) -> str:
"""Return the first non-empty str value found for *keys*, stripped."""
for k in keys:
v = src.get(k)
@@ -102,7 +100,7 @@ def _make_synthetic_event(
payload["authorInfo"] = _safe_dict(author_info)
return {
"type": "message.add",
"timestamp": timestamp or datetime.utcnow().isoformat(), # pyright: ignore[reportDeprecated]
"timestamp": timestamp or datetime.utcnow().isoformat(),
"payload": payload,
}
@@ -143,12 +141,11 @@ def extract_mention_ids(value: Any) -> list[str]:
if not isinstance(value, list):
return []
ids: list[str] = []
for item in cast(list[object], value):
for item in value:
if isinstance(item, str):
if item.strip():
ids.append(item.strip())
elif isinstance(item, dict):
item = cast(dict[str, Any], item)
for key in ("id", "userId", "_id"):
candidate = item.get(key)
if isinstance(candidate, str) and candidate.strip():
@@ -161,7 +158,6 @@ def resolve_was_mentioned(payload: dict[str, Any], agent_user_id: str) -> bool:
"""Resolve mention state from payload metadata and text fallback."""
meta = payload.get("meta")
if isinstance(meta, dict):
meta = cast(dict[str, Any], meta)
if meta.get("mentioned") is True or meta.get("wasMentioned") is True:
return True
for f in ("mentions", "mentionIds", "mentionedUserIds", "mentionedUsers"):
@@ -282,7 +278,7 @@ class MochatChannel(BaseChannel):
self._state_dir = get_runtime_subdir("mochat")
self._cursor_path = self._state_dir / "session_cursors.json"
self._session_cursor: dict[str, int] = {}
self._cursor_save_task: asyncio.Task[None] | None = None
self._cursor_save_task: asyncio.Task | None = None
self._session_set: set[str] = set()
self._panel_set: set[str] = set()
@@ -296,9 +292,9 @@ class MochatChannel(BaseChannel):
self._delay_states: dict[str, DelayState] = {}
self._fallback_mode = False
self._session_fallback_tasks: dict[str, asyncio.Task[None]] = {}
self._panel_fallback_tasks: dict[str, asyncio.Task[None]] = {}
self._refresh_task: asyncio.Task[None] | None = None
self._session_fallback_tasks: dict[str, asyncio.Task] = {}
self._panel_fallback_tasks: dict[str, asyncio.Task] = {}
self._refresh_task: asyncio.Task | None = None
self._target_locks: dict[str, asyncio.Lock] = {}
# ---- lifecycle ---------------------------------------------------------
@@ -356,11 +352,7 @@ class MochatChannel(BaseChannel):
parts = ([msg.content.strip()] if msg.content and msg.content.strip() else [])
if msg.media:
parts.extend(
m
for m in msg.media
if isinstance(cast(object, m), str) and m.strip()
)
parts.extend(m for m in msg.media if isinstance(m, str) and m.strip())
content = "\n".join(parts).strip()
if not content:
return
@@ -412,8 +404,7 @@ class MochatChannel(BaseChannel):
else:
self.logger.warning("msgpack not installed but socket_disable_msgpack=false; using JSON")
socketio_module = cast(Any, socketio)
client: Any = socketio_module.AsyncClient(
client = socketio.AsyncClient(
reconnection=True,
reconnection_attempts=self.config.max_retry_attempts or None,
reconnection_delay=max(0.1, self.config.socket_reconnect_delay_ms / 1000.0),
@@ -421,6 +412,7 @@ class MochatChannel(BaseChannel):
logger=False, engineio_logger=False, serializer=serializer,
)
@client.event
async def connect() -> None:
self._ws_connected, self._ws_ready = True, False
self.logger.info("websocket connected")
@@ -428,6 +420,7 @@ class MochatChannel(BaseChannel):
self._ws_ready = subscribed
await (self._stop_fallback_workers() if subscribed else self._ensure_fallback_workers())
@client.event
async def disconnect() -> None:
if not self._running:
return
@@ -435,21 +428,18 @@ class MochatChannel(BaseChannel):
self.logger.warning("websocket disconnected")
await self._ensure_fallback_workers()
@client.event
async def connect_error(data: Any) -> None:
self.logger.error("websocket connect error: {}", data)
@client.on("claw.session.events")
async def on_session_events(payload: dict[str, Any]) -> None:
await self._handle_watch_payload(payload, "session")
@client.on("claw.panel.events")
async def on_panel_events(payload: dict[str, Any]) -> None:
await self._handle_watch_payload(payload, "panel")
client.event(connect)
client.event(disconnect)
client.event(connect_error)
client.on("claw.session.events", on_session_events)
client.on("claw.panel.events", on_panel_events)
for ev in ("notify:chat.inbox.append", "notify:chat.message.add",
"notify:chat.message.update", "notify:chat.message.recall",
"notify:chat.message.delete"):
@@ -473,10 +463,7 @@ class MochatChannel(BaseChannel):
self._socket = None
return False
def _build_notify_handler(
self,
event_name: str,
) -> Callable[[Any], Awaitable[None]]:
def _build_notify_handler(self, event_name: str):
async def handler(payload: Any) -> None:
if event_name == "notify:chat.inbox.append":
await self._handle_notify_inbox_append(payload)
@@ -511,20 +498,11 @@ class MochatChannel(BaseChannel):
data = ack.get("data")
items: list[dict[str, Any]] = []
if isinstance(data, list):
items = [
cast(dict[str, Any], item)
for item in cast(list[object], data)
if isinstance(item, dict)
]
items = [i for i in data if isinstance(i, dict)]
elif isinstance(data, dict):
data = cast(dict[str, Any], data)
sessions = data.get("sessions")
if isinstance(sessions, list):
items = [
cast(dict[str, Any], item)
for item in cast(list[object], sessions)
if isinstance(item, dict)
]
items = [i for i in sessions if isinstance(i, dict)]
elif "sessionId" in data:
items = [data]
for p in items:
@@ -547,11 +525,7 @@ class MochatChannel(BaseChannel):
raw = await self._socket.call(event_name, payload, timeout=10)
except Exception as e:
return {"result": False, "message": str(e)}
return (
cast(dict[str, Any], raw)
if isinstance(raw, dict)
else {"result": True, "data": raw}
)
return raw if isinstance(raw, dict) else {"result": True, "data": raw}
# ---- refresh / discovery -----------------------------------------------
@@ -584,11 +558,10 @@ class MochatChannel(BaseChannel):
return
new_ids: list[str] = []
for session_value in cast(list[object], sessions):
if not isinstance(session_value, dict):
for s in sessions:
if not isinstance(s, dict):
continue
session = cast(dict[str, Any], session_value)
sid = _str_field(session, "sessionId")
sid = _str_field(s, "sessionId")
if not sid:
continue
if sid not in self._session_set:
@@ -596,7 +569,7 @@ class MochatChannel(BaseChannel):
new_ids.append(sid)
if sid not in self._session_cursor:
self._cold_sessions.add(sid)
cid = _str_field(session, "converseId")
cid = _str_field(s, "converseId")
if cid:
self._session_by_converse[cid] = sid
@@ -619,14 +592,13 @@ class MochatChannel(BaseChannel):
return
new_ids: list[str] = []
for panel_value in cast(list[object], raw_panels):
if not isinstance(panel_value, dict):
for p in raw_panels:
if not isinstance(p, dict):
continue
panel = cast(dict[str, Any], panel_value)
pt = panel.get("type")
pt = p.get("type")
if isinstance(pt, int) and pt != 0:
continue
pid = _str_field(panel, "id", "_id")
pid = _str_field(p, "id", "_id")
if pid and pid not in self._panel_set:
self._panel_set.add(pid)
new_ids.append(pid)
@@ -686,19 +658,16 @@ class MochatChannel(BaseChannel):
})
msgs = resp.get("messages")
if isinstance(msgs, list):
for message_value in reversed(cast(list[object], msgs)):
if not isinstance(message_value, dict):
for m in reversed(msgs):
if not isinstance(m, dict):
continue
message = cast(dict[str, Any], message_value)
evt = _make_synthetic_event(
message_id=str(message.get("messageId") or ""),
author=str(message.get("author") or ""),
content=message.get("content"),
meta=message.get("meta"),
group_id=str(resp.get("groupId") or ""),
converse_id=panel_id,
timestamp=message.get("createdAt"),
author_info=message.get("authorInfo"),
message_id=str(m.get("messageId") or ""),
author=str(m.get("author") or ""),
content=m.get("content"),
meta=m.get("meta"), group_id=str(resp.get("groupId") or ""),
converse_id=panel_id, timestamp=m.get("createdAt"),
author_info=m.get("authorInfo"),
)
await self._process_inbound_event(panel_id, evt, "panel")
except asyncio.CancelledError:
@@ -710,7 +679,7 @@ class MochatChannel(BaseChannel):
# ---- inbound event processing ------------------------------------------
async def _handle_watch_payload(self, payload: dict[str, Any], target_kind: str) -> None:
if not isinstance(cast(object, payload), dict):
if not isinstance(payload, dict):
return
target_id = _str_field(payload, "sessionId")
if not target_id:
@@ -730,10 +699,9 @@ class MochatChannel(BaseChannel):
self._cold_sessions.discard(target_id)
return
for event_value in cast(list[object], raw_events):
if not isinstance(event_value, dict):
for event in raw_events:
if not isinstance(event, dict):
continue
event = cast(dict[str, Any], event_value)
seq = event.get("seq")
if target_kind == "session" and isinstance(seq, int) and seq > self._session_cursor.get(target_id, prev):
self._mark_session_cursor(target_id, seq)
@@ -744,7 +712,6 @@ class MochatChannel(BaseChannel):
payload = event.get("payload")
if not isinstance(payload, dict):
return
payload = cast(dict[str, Any], payload)
author = _str_field(payload, "author")
if not author or (self.config.agent_user_id and author == self.config.agent_user_id):
@@ -854,7 +821,6 @@ class MochatChannel(BaseChannel):
async def _handle_notify_chat_message(self, payload: Any) -> None:
if not isinstance(payload, dict):
return
payload = cast(dict[str, Any], payload)
group_id = _str_field(payload, "groupId")
panel_id = _str_field(payload, "converseId", "panelId")
if not group_id or not panel_id:
@@ -872,15 +838,11 @@ class MochatChannel(BaseChannel):
await self._process_inbound_event(panel_id, evt, "panel")
async def _handle_notify_inbox_append(self, payload: Any) -> None:
if not isinstance(payload, dict):
return
payload = cast(dict[str, Any], payload)
if payload.get("type") != "message":
if not isinstance(payload, dict) or payload.get("type") != "message":
return
detail = payload.get("payload")
if not isinstance(detail, dict):
return
detail = cast(dict[str, Any], detail)
if _str_field(detail, "groupId"):
return
converse_id = _str_field(detail, "converseId")
@@ -924,14 +886,9 @@ class MochatChannel(BaseChannel):
except Exception as e:
self.logger.warning("Failed to read cursor file: {}", e)
return
data_object = cast(object, data)
cursors = (
cast(dict[str, Any], data_object).get("cursors")
if isinstance(data_object, dict)
else None
)
cursors = data.get("cursors") if isinstance(data, dict) else None
if isinstance(cursors, dict):
for sid, cur in cast(dict[object, object], cursors).items():
for sid, cur in cursors.items():
if isinstance(sid, str) and isinstance(cur, int) and cur >= 0:
self._session_cursor[sid] = cur
@@ -939,8 +896,7 @@ class MochatChannel(BaseChannel):
try:
self._state_dir.mkdir(parents=True, exist_ok=True)
self._cursor_path.write_text(json.dumps({
"schemaVersion": 1,
"updatedAt": datetime.utcnow().isoformat(), # pyright: ignore[reportDeprecated]
"schemaVersion": 1, "updatedAt": datetime.utcnow().isoformat(),
"cursors": self._session_cursor,
}, ensure_ascii=False, indent=2) + "\n", "utf-8")
except Exception as e:
@@ -961,22 +917,13 @@ class MochatChannel(BaseChannel):
parsed = response.json()
except Exception:
parsed = response.text
if isinstance(parsed, dict):
parsed_dict = cast(dict[str, Any], parsed)
if isinstance(parsed_dict.get("code"), int):
if parsed_dict["code"] != 200:
msg = str(
parsed_dict.get("message")
or parsed_dict.get("name")
or "request failed"
)
raise RuntimeError(
f"Mochat API error: {msg} (code={parsed_dict['code']})"
)
data = parsed_dict.get("data")
return cast(dict[str, Any], data) if isinstance(data, dict) else {}
return parsed_dict
return {}
if isinstance(parsed, dict) and isinstance(parsed.get("code"), int):
if parsed["code"] != 200:
msg = str(parsed.get("message") or parsed.get("name") or "request failed")
raise RuntimeError(f"Mochat API error: {msg} (code={parsed['code']})")
data = parsed.get("data")
return data if isinstance(data, dict) else {}
return parsed if isinstance(parsed, dict) else {}
async def _api_send(self, path: str, id_key: str, id_val: str,
content: str, reply_to: str | None, group_id: str | None = None) -> dict[str, Any]:
@@ -990,7 +937,7 @@ class MochatChannel(BaseChannel):
@staticmethod
def _read_group_id(metadata: dict[str, Any]) -> str | None:
if not isinstance(cast(object, metadata), dict):
if not isinstance(metadata, dict):
return None
value = metadata.get("group_id") or metadata.get("groupId")
return value.strip() if isinstance(value, str) and value.strip() else None
+39 -60
View File
@@ -23,8 +23,7 @@ import time
from contextlib import contextmanager, suppress
from dataclasses import dataclass
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from pathlib import Path
from typing import TYPE_CHECKING, Any, Generator, cast
from typing import TYPE_CHECKING, Any
from urllib.parse import urlparse
try: # pragma: no cover - Windows fallback path
@@ -48,11 +47,9 @@ MSTEAMS_AVAILABLE = (
if TYPE_CHECKING:
import jwt
from jwt.algorithms import RSAAlgorithm
if MSTEAMS_AVAILABLE:
import jwt
from jwt.algorithms import RSAAlgorithm
MSTEAMS_REF_TTL_DAYS = 30
MSTEAMS_WEBCHAT_HOST = "webchat.botframework.com"
@@ -185,10 +182,9 @@ class MSTeamsChannel(BaseChannel):
auth_header = self.headers.get("Authorization", "")
if channel.config.validate_inbound_auth:
try:
loop = cast(asyncio.AbstractEventLoop, channel._loop)
fut = asyncio.run_coroutine_threadsafe(
channel._validate_inbound_auth(auth_header, payload),
loop,
channel._loop,
)
fut.result(timeout=15)
except Exception as e:
@@ -199,10 +195,9 @@ class MSTeamsChannel(BaseChannel):
self.wfile.write(b'{"error":"unauthorized"}')
return
try:
loop = cast(asyncio.AbstractEventLoop, channel._loop)
fut = asyncio.run_coroutine_threadsafe(
channel._handle_activity(payload),
loop,
channel._loop,
)
fut.result(timeout=15)
except Exception as e:
@@ -274,7 +269,7 @@ class MSTeamsChannel(BaseChannel):
"text": msg.content or " ",
}
if use_thread_reply:
payload["replyToId"] = cast(str, ref.activity_id)
payload["replyToId"] = ref.activity_id
try:
resp = await self._http.post(base_url, headers=headers, json=payload)
@@ -290,10 +285,10 @@ class MSTeamsChannel(BaseChannel):
if activity.get("type") != "message":
return
conversation = cast(dict[str, Any], activity.get("conversation") or {})
from_user = cast(dict[str, Any], activity.get("from") or {})
recipient = cast(dict[str, Any], activity.get("recipient") or {})
channel_data = cast(dict[str, Any], activity.get("channelData") or {})
conversation = activity.get("conversation") or {}
from_user = activity.get("from") or {}
recipient = activity.get("recipient") or {}
channel_data = activity.get("channelData") or {}
sender_id = str(from_user.get("aadObjectId") or from_user.get("id") or "").strip()
conversation_id = str(conversation.get("id") or "").strip()
@@ -341,16 +336,7 @@ class MSTeamsChannel(BaseChannel):
bot_id=str(recipient.get("id") or "") or None,
activity_id=activity_id or None,
conversation_type=conversation_type or None,
tenant_id=(
str(
cast(
dict[str, Any],
channel_data.get("tenant") or {},
).get("id")
or ""
)
or None
),
tenant_id=str((channel_data.get("tenant") or {}).get("id") or "") or None,
updated_at=time.time(),
)
self._save_refs_locked()
@@ -375,7 +361,7 @@ class MSTeamsChannel(BaseChannel):
text = self._strip_possible_bot_mention(text)
text = self._normalize_html_whitespace(text)
channel_data = cast(dict[str, Any], activity.get("channelData") or {})
channel_data = activity.get("channelData") or {}
reply_to_id = str(activity.get("replyToId") or "").strip()
normalized_preview = html.unescape(text).replace("&rsquo", "").strip()
normalized_preview = normalized_preview.replace("\xa0", " ")
@@ -487,15 +473,15 @@ class MSTeamsChannel(BaseChannel):
raise ValueError("missing token kid")
jwks = await self._get_botframework_jwks()
keys = cast(list[dict[str, Any]], jwks.get("keys") or [])
keys = jwks.get("keys") or []
jwk = next((key for key in keys if key.get("kid") == kid), None)
if not jwk:
raise ValueError(f"signing key not found for kid={kid}")
public_key = RSAAlgorithm.from_jwk(json.dumps(jwk))
public_key = jwt.algorithms.RSAAlgorithm.from_jwk(json.dumps(jwk))
claims = jwt.decode(
token,
key=cast(Any, public_key),
key=public_key,
algorithms=["RS256"],
audience=self.config.app_id,
issuer="https://api.botframework.com",
@@ -523,10 +509,9 @@ class MSTeamsChannel(BaseChannel):
resp = await self._http.get(self._botframework_openid_config_url)
resp.raise_for_status()
openid_config = cast(dict[str, Any], resp.json())
self._botframework_openid_config = openid_config
self._botframework_openid_config = resp.json()
self._botframework_openid_config_expires_at = now + 3600
return openid_config
return self._botframework_openid_config
async def _get_botframework_jwks(self) -> dict[str, Any]:
"""Fetch and cache Bot Framework JWKS."""
@@ -545,38 +530,36 @@ class MSTeamsChannel(BaseChannel):
resp = await self._http.get(jwks_uri)
resp.raise_for_status()
jwks = cast(dict[str, Any], resp.json())
self._botframework_jwks = jwks
self._botframework_jwks = resp.json()
self._botframework_jwks_expires_at = now + 3600
return jwks
return self._botframework_jwks
@staticmethod
def _safe_float(value: object) -> float | None:
def _safe_float(value: Any) -> float | None:
try:
out = float(cast(Any, value))
out = float(value)
if out > 0:
return out
except (TypeError, ValueError):
return None
return None
def _normalize_ref_record(self, value: object) -> ConversationRef | None:
def _normalize_ref_record(self, value: Any) -> ConversationRef | None:
"""Normalize a stored ref record from legacy/current schema."""
if not isinstance(value, dict):
return None
record = cast(dict[str, Any], value)
service_url = str(record.get("service_url") or "").strip()
conversation_id = str(record.get("conversation_id") or "").strip()
service_url = str(value.get("service_url") or "").strip()
conversation_id = str(value.get("conversation_id") or "").strip()
if not service_url or not conversation_id:
return None
return ConversationRef(
service_url=service_url,
conversation_id=conversation_id,
bot_id=str(record.get("bot_id") or "") or None,
activity_id=str(record.get("activity_id") or "") or None,
conversation_type=str(record.get("conversation_type") or "") or None,
tenant_id=str(record.get("tenant_id") or "") or None,
updated_at=self._safe_float(cast(object, record.get("updated_at"))),
bot_id=str(value.get("bot_id") or "") or None,
activity_id=str(value.get("activity_id") or "") or None,
conversation_type=str(value.get("conversation_type") or "") or None,
tenant_id=str(value.get("tenant_id") or "") or None,
updated_at=self._safe_float(value.get("updated_at")),
)
def _load_refs_raw(self) -> tuple[dict[str, Any], dict[str, Any], bool]:
@@ -587,19 +570,17 @@ class MSTeamsChannel(BaseChannel):
if self._refs_path.exists():
try:
loaded: object = json.loads(self._refs_path.read_text(encoding="utf-8"))
loaded = json.loads(self._refs_path.read_text(encoding="utf-8"))
if isinstance(loaded, dict):
main_data = cast(dict[str, Any], loaded)
main_data = loaded
except Exception as e:
self.logger.warning("Failed to load conversation refs: {}", e)
if meta_exists:
try:
loaded_meta: object = json.loads(
self._refs_meta_path.read_text(encoding="utf-8")
)
loaded_meta = json.loads(self._refs_meta_path.read_text(encoding="utf-8"))
if isinstance(loaded_meta, dict):
meta_data = cast(dict[str, Any], loaded_meta)
meta_data = loaded_meta
except Exception as e:
self.logger.warning("Failed to load conversation refs metadata: {}", e)
@@ -618,11 +599,10 @@ class MSTeamsChannel(BaseChannel):
if not ref:
continue
meta_entry = cast(object, meta_data.get(key))
meta_ts: float | None = None
meta_entry = meta_data.get(key) if isinstance(meta_data, dict) else None
meta_ts = None
if isinstance(meta_entry, dict):
meta_record = cast(dict[str, Any], meta_entry)
meta_ts = self._safe_float(cast(object, meta_record.get("updated_at")))
meta_ts = self._safe_float(meta_entry.get("updated_at"))
elif meta_entry is not None:
meta_ts = self._safe_float(meta_entry)
@@ -643,7 +623,7 @@ class MSTeamsChannel(BaseChannel):
return self._load_refs_from_disk()
@contextmanager
def _refs_file_lock(self) -> Generator[None, None, None]:
def _refs_file_lock(self):
"""Cross-process lock while merging and writing refs state."""
self._refs_path.parent.mkdir(parents=True, exist_ok=True)
lock_fp = self._refs_lock_path.open("a+", encoding="utf-8")
@@ -762,7 +742,7 @@ class MSTeamsChannel(BaseChannel):
if persist:
self._save_refs_locked()
def _write_json_atomically(self, path: Path, data: dict[str, Any]) -> None:
def _write_json_atomically(self, path, data: dict[str, Any]) -> None:
"""Write refs JSON atomically to reduce corruption risk during crashes."""
payload = json.dumps(data, indent=2)
tmp_path: str | None = None
@@ -836,8 +816,7 @@ class MSTeamsChannel(BaseChannel):
}
resp = await self._http.post(token_url, data=data)
resp.raise_for_status()
payload = cast(dict[str, Any], resp.json())
token = cast(str, payload["access_token"])
self._token = token
payload = resp.json()
self._token = payload["access_token"]
self._token_expires_at = now + int(payload.get("expires_in", 3600))
return token
return self._token
+18 -27
View File
@@ -11,7 +11,7 @@ import time
import uuid
from collections import deque
from pathlib import Path
from typing import Annotated, Any, Literal, cast
from typing import Annotated, Any, Literal
import aiohttp
from loguru import logger
@@ -103,7 +103,7 @@ class NapcatChannel(BaseChannel):
await asyncio.sleep(next(backoff, 30))
async def _run_once(self) -> None:
headers: list[tuple[str, str]] = []
headers = []
if self.config.access_token:
headers.append(("Authorization", f"Bearer {self.config.access_token}"))
@@ -132,17 +132,12 @@ class NapcatChannel(BaseChannel):
payload = json.loads(raw)
except json.JSONDecodeError:
continue
if isinstance(payload, dict):
login_payload = cast(dict[str, Any], payload)
else:
login_payload = None
if login_payload is not None and login_payload.get("echo") == echo:
data = login_payload.get("data")
login_data = cast(dict[str, Any], data) if isinstance(data, dict) else {}
if isinstance(payload, dict) and payload.get("echo") == echo:
data = payload.get("data") or {}
logger.info(
"napcat: logged in as {} (user_id={})",
login_data.get("nickname"),
login_data.get("user_id"),
data.get("nickname"),
data.get("user_id"),
)
break
await self._dispatch_frame(raw)
@@ -194,27 +189,26 @@ class NapcatChannel(BaseChannel):
return
if not isinstance(payload, dict):
return
frame = cast(dict[str, Any], payload)
# Action response: identified by `echo` and absence of post_type.
if "echo" in frame and frame.get("post_type") is None:
echo = frame.get("echo")
if "echo" in payload and payload.get("post_type") is None:
echo = payload.get("echo")
fut = self._pending.pop(echo, None) if isinstance(echo, str) else None
if fut and not fut.done():
fut.set_result(frame)
fut.set_result(payload)
return
if (sid := frame.get("self_id")) is not None:
if (sid := payload.get("self_id")) is not None:
try:
self._self_id = int(sid)
except (TypeError, ValueError):
pass
post_type = frame.get("post_type")
post_type = payload.get("post_type")
if post_type == "message":
self._create_background_task(self._on_message(frame), "message")
self._create_background_task(self._on_message(payload), "message")
elif post_type == "notice":
self._create_background_task(self._on_notice(frame), "notice")
self._create_background_task(self._on_notice(payload), "notice")
def _create_background_task(self, coro: Any, kind: str) -> None:
task = asyncio.create_task(coro)
@@ -255,8 +249,7 @@ class NapcatChannel(BaseChannel):
if local := await self._download_image(info):
media_paths.append(local)
sender_raw = ev.get("sender")
sender = cast(dict[str, Any], sender_raw) if isinstance(sender_raw, dict) else {}
sender = ev.get("sender") or {}
nickname = sender.get("card") or sender.get("nickname")
if message_type == "group":
@@ -277,7 +270,7 @@ class NapcatChannel(BaseChannel):
chat_id = f"group:{group_id}"
content = self._format_group_content(
text=text,
nickname=cast(str, nickname),
nickname=nickname,
user_id=user_id,
)
else:
@@ -306,7 +299,7 @@ class NapcatChannel(BaseChannel):
# segment rather than parsing CQ codes — that path is fragile and
# users can configure napcat to emit arrays.
if isinstance(message, list):
return [cast(dict[str, Any], seg) for seg in cast(list[Any], message) if isinstance(seg, dict)]
return [seg for seg in message if isinstance(seg, dict)]
if isinstance(message, str) and message:
return [{"type": "text", "data": {"text": message}}]
return []
@@ -322,8 +315,7 @@ class NapcatChannel(BaseChannel):
for seg in segments:
stype = seg.get("type")
raw_data = seg.get("data")
data = cast(dict[str, Any], raw_data) if isinstance(raw_data, dict) else {}
data = seg.get("data") or {}
if stype == "text":
if txt := data.get("text"):
parts.append(str(txt))
@@ -463,8 +455,7 @@ class NapcatChannel(BaseChannel):
params["user_id"] = int(target)
resp = await self._call_action("send_msg", params)
raw_data = resp.get("data")
data = cast(dict[str, Any], raw_data) if isinstance(raw_data, dict) else {}
data = resp.get("data") or {}
if (mid := data.get("message_id")) is not None:
self._bot_outbound_ids.append(int(mid))
+5 -5
View File
@@ -7,7 +7,7 @@ import re
from dataclasses import dataclass
from functools import lru_cache
from importlib.resources import files
from typing import TYPE_CHECKING, Any, cast
from typing import TYPE_CHECKING, Any
from packaging.requirements import InvalidRequirement, Requirement
@@ -49,12 +49,12 @@ class ChannelPlugin:
_target_parts(self.runtime, label="runtime")
if self.connector is not None:
_target_parts(self.connector, label="connector")
if self.setup is not None and not isinstance(cast(object, self.setup), ChannelSetupSpec):
if self.setup is not None and not isinstance(self.setup, ChannelSetupSpec):
raise TypeError("channel plugin setup must be a ChannelSetupSpec or None")
if not isinstance(cast(object, self.management), ChannelManagementSpec):
if not isinstance(self.management, ChannelManagementSpec):
raise TypeError("channel plugin management must be a ChannelManagementSpec")
if not isinstance(cast(object, self.dependencies), tuple) or not all(
isinstance(cast(object, requirement), str) and requirement.strip()
if not isinstance(self.dependencies, tuple) or not all(
isinstance(requirement, str) and requirement.strip()
for requirement in self.dependencies
):
raise TypeError("channel plugin dependencies must be a tuple of requirements")
+39 -55
View File
@@ -16,8 +16,6 @@ Notes:
- Attachment structures differ across botpy versions; we try multiple field candidates.
"""
# pyright: reportConstantRedefinition=false, reportMissingTypeStubs=false, reportPrivateUsage=false
from __future__ import annotations
import asyncio
@@ -29,7 +27,7 @@ import time
from collections import deque
from contextlib import suppress
from pathlib import Path
from typing import Any, BinaryIO, Literal, cast
from typing import TYPE_CHECKING, Any, Literal
from urllib.parse import unquote, urlparse
import aiohttp
@@ -60,6 +58,11 @@ except ImportError: # pragma: no cover
BotWebSocket = None
Route = None
if TYPE_CHECKING:
from botpy.message import BaseMessage, C2CMessage, GroupMessage
from botpy.types.message import Media
# QQ rich media file_type: 1=image, 4=file
# (2=voice, 3=video are restricted; we only use image vs file)
QQ_FILE_TYPE_IMAGE = 1
@@ -115,34 +118,30 @@ def _is_network_error(exc: BaseException) -> bool:
)
def _make_bot_class(channel: QQChannel) -> type[Any]:
def _make_bot_class(channel: QQChannel) -> type[botpy.Client]:
"""Create a botpy client with per-session reconnect backoff."""
botpy_sdk = cast(Any, botpy)
intents = botpy_sdk.Intents(public_messages=True, direct_message=True)
intents = botpy.Intents(public_messages=True, direct_message=True)
class _Bot(botpy_sdk.Client):
class _Bot(botpy.Client):
def __init__(self):
# Disable botpy's file log — nanobot uses loguru; default "botpy.log" fails on read-only fs
super().__init__( # pyright: ignore[reportUnknownMemberType]
intents=intents,
ext_handlers=False,
)
super().__init__(intents=intents, ext_handlers=False)
self._ws_backoff: dict[int, int] = {}
self._ws_retry_at: dict[int, float] = {}
async def on_ready(self):
logger.info("QQ bot ready: {}", self.robot.name)
async def on_c2c_message_create(self, message: object) -> None:
async def on_c2c_message_create(self, message: C2CMessage):
await channel._on_message(message, is_group=False)
async def on_group_at_message_create(self, message: object) -> None:
async def on_group_at_message_create(self, message: GroupMessage):
await channel._on_message(message, is_group=True)
async def on_direct_message_create(self, message: object) -> None:
async def on_direct_message_create(self, message):
await channel._on_message(message, is_group=False)
async def bot_connect(self, session: object) -> None:
async def bot_connect(self, session):
"""Connect a botpy session with exponential retry backoff."""
session_id = id(session)
retry_at = self._ws_retry_at.pop(session_id, None)
@@ -151,8 +150,7 @@ def _make_bot_class(channel: QQChannel) -> type[Any]:
if remaining > 0:
await asyncio.sleep(remaining)
websocket_class = cast(Any, BotWebSocket)
client = websocket_class(session, self._connection)
client = BotWebSocket(session, self._connection)
backoff = self._ws_backoff.get(session_id, _RECONNECT_BACKOFF_START)
try:
await client.ws_connect()
@@ -209,7 +207,7 @@ class QQChannel(BaseChannel):
super().__init__(config, bus)
self.config: QQConfig = config
self._client: Any | None = None
self._client: botpy.Client | None = None
self._http: aiohttp.ClientSession | None = None
self._processed_ids: deque[str] = deque(maxlen=1000)
@@ -262,8 +260,7 @@ class QQChannel(BaseChannel):
max_backoff = 300
while self._running:
try:
client = cast(Any, self._client)
await client.start(appid=self.config.app_id, secret=self.config.secret)
await self._client.start(appid=self.config.app_id, secret=self.config.secret)
backoff = 5
except Exception as e:
if _is_network_error(e):
@@ -493,7 +490,7 @@ class QQChannel(BaseChannel):
file_data: str,
file_name: str | None = None,
srv_send_msg: bool = False,
) -> dict[str, Any]:
) -> Media:
"""Upload base64-encoded file and return Media object."""
if not self._client:
raise RuntimeError("QQ client not initialized")
@@ -517,44 +514,39 @@ class QQChannel(BaseChannel):
if file_type != QQ_FILE_TYPE_IMAGE and file_name:
payload["file_name"] = file_name
route_class = cast(Any, Route)
route = route_class("POST", endpoint, **{id_key: chat_id})
client = self._client
result: object = await client.api._http.request(route, json=payload)
route = Route("POST", endpoint, **{id_key: chat_id})
result = await self._client.api._http.request(route, json=payload)
# Extract only the file_info field to avoid extra fields (file_uuid, ttl, etc.)
# that may confuse QQ client when sending the media object.
if isinstance(result, dict) and "file_info" in result:
result_data = cast(dict[str, Any], result)
return {"file_info": result_data["file_info"]}
return cast(dict[str, Any], result)
return {"file_info": result["file_info"]}
return result
# ---------------------------
# Inbound (receive)
# ---------------------------
async def _on_message(self, data: object, is_group: bool = False) -> None:
async def _on_message(self, data: C2CMessage | GroupMessage, is_group: bool = False) -> None:
"""Parse inbound message, download attachments, and publish to the bus."""
try:
message = cast(Any, data)
if is_group:
chat_id = cast(str, message.group_openid)
user_id = cast(str, message.author.member_openid)
chat_id = data.group_openid
user_id = data.author.member_openid
chat_type = "group"
else:
chat_id = str(
getattr(message.author, "id", None)
or getattr(message.author, "user_openid", "unknown")
getattr(data.author, "id", None)
or getattr(data.author, "user_openid", "unknown")
)
user_id = chat_id
chat_type = "c2c"
content = str(message.content or "").strip()
content = (data.content or "").strip()
message_id = cast(str, message.id)
if message_id in self._processed_ids:
if data.id in self._processed_ids:
return
self._processed_ids.append(message_id)
self._processed_ids.append(data.id)
self._chat_type_cache[chat_id] = chat_type
# Early permission check — avoid attachment downloads and ack side effects
@@ -572,10 +564,7 @@ class QQChannel(BaseChannel):
# the data used by tests don't contain attachments property
# so we use getattr with a default of [] to avoid AttributeError in tests
attachments = cast(
list[object],
getattr(message, "attachments", None) or [],
)
attachments = getattr(data, "attachments", None) or []
media_paths, recv_lines, att_meta = await self._handle_attachments(attachments)
# Compose content that always contains actionable saved paths
@@ -598,7 +587,7 @@ class QQChannel(BaseChannel):
await self._send_text_only(
chat_id=chat_id,
is_group=is_group,
msg_id=message_id,
msg_id=data.id,
content=self.config.ack_message,
)
except Exception:
@@ -610,20 +599,17 @@ class QQChannel(BaseChannel):
content=content,
media=media_paths if media_paths else None,
metadata={
"message_id": message_id,
"message_id": data.id,
"attachments": att_meta,
},
is_dm=not is_group,
)
except Exception:
self.logger.exception(
"Error handling inbound message id={}",
getattr(data, "id", "?"),
)
self.logger.exception("Error handling inbound message id={}", getattr(data, "id", "?"))
async def _handle_attachments(
self,
attachments: list[object],
attachments: list[BaseMessage._Attachments],
) -> tuple[list[str], list[str], list[dict[str, Any]]]:
"""Extract, download (chunked), and format attachments for agent consumption."""
media_paths: list[str] = []
@@ -732,11 +718,9 @@ class QQChannel(BaseChannel):
1024 * 1024, int(self.config.download_max_bytes or (200 * 1024 * 1024))
)
active_tmp_path = tmp_path
def _open_tmp() -> BinaryIO:
active_tmp_path.parent.mkdir(parents=True, exist_ok=True)
return active_tmp_path.open("wb") # noqa: SIM115
def _open_tmp():
tmp_path.parent.mkdir(parents=True, exist_ok=True)
return open(tmp_path, "wb") # noqa: SIM115
f = await asyncio.to_thread(_open_tmp)
try:
@@ -756,7 +740,7 @@ class QQChannel(BaseChannel):
await asyncio.to_thread(f.close)
# Atomic rename
await asyncio.to_thread(os.replace, active_tmp_path, target)
await asyncio.to_thread(os.replace, tmp_path, target)
tmp_path = None # mark as moved
self.logger.info("file saved: {}", str(target))
return str(target)
+19
View File
@@ -3,6 +3,8 @@
from __future__ import annotations
import pkgutil
from functools import cache
from importlib.metadata import entry_points
from typing import TYPE_CHECKING
from loguru import logger
@@ -17,6 +19,22 @@ if TYPE_CHECKING:
from nanobot.channels.base import BaseChannel
@cache
def _warn_legacy_channel_entry_points() -> None:
# TODO(v0.3.1): Remove this detection and warning. v0.3.0 is the final
# migration window for installed legacy channel entry points.
names = sorted({entry_point.name for entry_point in entry_points(group="nanobot.channels")})
if not names:
return
logger.warning(
"Legacy channel entry points were detected but will not be loaded: {}. "
"The '{}' entry-point group is no longer supported; use a built-in channel or "
"migrate it into nanobot/channels/<channel>/.",
", ".join(names),
"nanobot.channels",
)
def _channel_package_names() -> list[str]:
import nanobot.channels as package
@@ -31,6 +49,7 @@ def discover_plugins(
enabled_names: set[str] | None = None,
) -> dict[str, ChannelPlugin]:
"""Load dependency-free descriptors from self-contained channel packages."""
_warn_legacy_channel_entry_points()
plugins: dict[str, ChannelPlugin] = {}
for name in _channel_package_names():
if enabled_names is not None and name not in enabled_names:
+51 -76
View File
@@ -12,7 +12,7 @@ from collections.abc import AsyncIterator, Callable
from contextlib import asynccontextmanager
from dataclasses import dataclass, field
from pathlib import Path
from typing import Any, TypedDict, cast
from typing import Any
import httpx
from pydantic import Field, computed_field, field_validator
@@ -53,7 +53,7 @@ _SIG_TOKEN_RE = re.compile(r"\x00C(\d+)\x00")
# stripper needs a fixed, narrow subset (no single-asterisk italic, no
# single-tilde strikethrough) and benefits from each pattern's group 1 being
# the content directly.
_SIG_CELL_STRIP_PATTERNS: tuple[tuple[re.Pattern[str], str], ...] = (
_SIG_CELL_STRIP_PATTERNS: tuple[tuple[re.Pattern, str], ...] = (
(re.compile(r"\*\*(.+?)\*\*"), r"\1"),
(re.compile(r"__(.+?)__"), r"\1"),
(re.compile(r"~~(.+?)~~"), r"\1"),
@@ -61,27 +61,6 @@ _SIG_CELL_STRIP_PATTERNS: tuple[tuple[re.Pattern[str], str], ...] = (
)
def _as_json_object(value: object) -> dict[str, Any] | None:
"""Return an untrusted JSON value only when it is an object."""
if isinstance(value, dict):
return cast(dict[str, Any], value)
return None
def _as_json_object_list(value: object) -> list[dict[str, Any]]:
"""Return the object members of an untrusted JSON array."""
if not isinstance(value, list):
return []
return [cast(dict[str, Any], item) for item in cast(list[object], value) if isinstance(item, dict)]
class _BufferedMessage(TypedDict):
sender_name: str
sender_number: str
content: str
timestamp: int | None
def _utf16_len(s: str) -> int:
"""UTF-16 code-unit length, matching Signal BodyRange semantics."""
return len(s.encode("utf-16-le")) // 2
@@ -139,7 +118,7 @@ def _markdown_to_signal(text: str) -> tuple[str, list[str]]:
# so they're protected from inline-style processing.
protected: list[str] = []
def save_code(m: re.Match[str]) -> str:
def save_code(m: re.Match) -> str:
protected.append(m.group(1))
return f"\x00C{len(protected) - 1}\x00"
@@ -170,8 +149,8 @@ def _markdown_to_signal(text: str) -> tuple[str, list[str]]:
runs: list[_Run] = [_Run(text)]
def transform(
pattern: re.Pattern[str],
make_runs: Callable[[re.Match[str], frozenset[str]], list[_Run]],
pattern: re.Pattern,
make_runs: Callable[[re.Match, frozenset[str]], list[_Run]],
) -> None:
new_runs: list[_Run] = []
for run in runs:
@@ -210,7 +189,7 @@ def _markdown_to_signal(text: str) -> tuple[str, list[str]]:
transform(_SIG_OLIST_RE, lambda m, s: [_Run(m.group(1) + ". ", s)])
# Links → "text (url)" or bare url when text equals url.
def _link_runs(m: re.Match[str], s: frozenset[str]) -> list[_Run]:
def _link_runs(m: re.Match, s: frozenset) -> list[_Run]:
link_text, url = m.group(1), m.group(2)
def _norm(u: str) -> str:
@@ -378,15 +357,15 @@ class SignalChannel(BaseChannel):
self.config: SignalConfig = config
self._http: httpx.AsyncClient | None = None
self._request_id = 0
self._sse_task: asyncio.Task[None] | None = None
self._typing_tasks: dict[str, asyncio.Task[None]] = {}
self._sse_task: asyncio.Task | None = None
self._typing_tasks: dict[str, asyncio.Task] = {}
self._typing_uuid_warnings: set[str] = set()
self._account_id_aliases: set[str] = set()
self._remember_account_id_alias(self.config.phone_number)
# Rolling message buffer for group context (group_id -> deque of messages)
# Each message is a dict with: sender_name, sender_number, content, timestamp
self._group_buffers: dict[str, deque[_BufferedMessage]] = {}
self._group_buffers: dict[str, deque] = {}
def is_allowed(self, sender_id: str) -> bool:
"""Override base check to normalize and split pipe-joined identifiers.
@@ -430,7 +409,6 @@ class SignalChannel(BaseChannel):
metadata: dict[str, Any] | None = None,
session_key: str | None = None,
is_dm: bool = False,
authorization_id: str | None = None,
) -> None:
"""Handle an inbound message whose policy has already been checked.
@@ -440,7 +418,6 @@ class SignalChannel(BaseChannel):
``super()._handle_message`` instead, which goes through
``is_allowed`` and issues a pairing code.
"""
del authorization_id
meta = metadata or {}
if self.supports_streaming:
meta = {**meta, "_wants_stream": True}
@@ -617,7 +594,7 @@ class SignalChannel(BaseChannel):
self.logger.info("Subscribed to Signal messages via SSE")
# Buffer for accumulating SSE data across multiple lines
event_buffer: list[str] = []
event_buffer = []
async for line in response.aiter_lines():
if not self._running:
@@ -628,7 +605,7 @@ class SignalChannel(BaseChannel):
self.logger.debug("SSE line received: {}", line[:200])
# SSE format handling
if isinstance(line, str): # pyright: ignore[reportUnnecessaryIsInstance]
if isinstance(line, str):
# Empty line signals end of event
if not line or line == ":":
if event_buffer:
@@ -636,10 +613,7 @@ class SignalChannel(BaseChannel):
data_str = ""
try:
data_str = "\n".join(event_buffer)
data = _as_json_object(json.loads(data_str))
if data is None:
self.logger.warning("Ignoring non-object SSE event: {}", data_str[:200])
continue
data = json.loads(data_str)
self.logger.debug("SSE event parsed: {}", data)
await self._handle_receive_notification(data)
except json.JSONDecodeError as e:
@@ -670,7 +644,7 @@ class SignalChannel(BaseChannel):
self.logger.error("Error in SSE receive loop: {}", e)
raise
@asynccontextmanager # pyright: ignore[reportDeprecated]
@asynccontextmanager
async def _safe_handle(self, action: str, payload: Any = None) -> AsyncIterator[None]:
"""Swallow and log any exception from a top-level handler block.
@@ -692,18 +666,17 @@ class SignalChannel(BaseChannel):
self.logger.debug("_handle_receive_notification called with: {}", params)
async with self._safe_handle("receive notification", params):
# Extract envelope from SSE notification: {"envelope": {...}}
envelope = _as_json_object(params.get("envelope"))
envelope = params.get("envelope", {})
self.logger.debug("Extracted envelope: {}", envelope)
if envelope is None:
if not envelope:
self.logger.debug("No envelope found in params")
return
# Extract sender information
sender_parts = self._collect_sender_id_parts(envelope)
source_name_value = envelope.get("sourceName")
source_name = source_name_value if isinstance(source_name_value, str) else None
source_name = envelope.get("sourceName")
if not sender_parts:
self.logger.debug("Received message without source, skipping")
@@ -718,10 +691,10 @@ class SignalChannel(BaseChannel):
self._remember_account_id_alias(part)
# Check different message types
data_message = _as_json_object(envelope.get("dataMessage"))
sync_message = _as_json_object(envelope.get("syncMessage"))
typing_message = _as_json_object(envelope.get("typingMessage"))
receipt_message = _as_json_object(envelope.get("receiptMessage"))
data_message = envelope.get("dataMessage")
sync_message = envelope.get("syncMessage")
typing_message = envelope.get("typingMessage")
receipt_message = envelope.get("receiptMessage")
# Ignore receipt messages (delivery/read receipts)
if receipt_message:
@@ -732,7 +705,8 @@ class SignalChannel(BaseChannel):
await self._handle_data_message(sender_id, sender_number, data_message, source_name)
# Handle sync messages (messages sent from another device)
elif sync_message and (sent_msg := _as_json_object(sync_message.get("sentMessage"))):
elif sync_message and sync_message.get("sentMessage"):
sent_msg = sync_message["sentMessage"]
destination = sent_msg.get("destination") or sent_msg.get("destinationNumber")
if destination:
self.logger.debug(
@@ -751,12 +725,10 @@ class SignalChannel(BaseChannel):
sender_name: str | None,
) -> None:
"""Handle a data message (text, attachments, etc.)."""
message_value = data_message.get("message")
message_text = message_value if isinstance(message_value, str) else ""
attachments = _as_json_object_list(data_message.get("attachments"))
mentions = _as_json_object_list(data_message.get("mentions"))
timestamp_value = data_message.get("timestamp")
timestamp = timestamp_value if isinstance(timestamp_value, int) else None
message_text = data_message.get("message") or ""
attachments = data_message.get("attachments", [])
mentions = data_message.get("mentions", [])
timestamp = data_message.get("timestamp")
self.logger.info(
"Data message from {}: groupInfo={}, groupV2={}, keys={}",
@@ -843,7 +815,7 @@ class SignalChannel(BaseChannel):
group_id: str | None,
is_group_message: bool,
message_text: str,
mentions: list[dict[str, Any]],
mentions: list,
sender_name: str | None,
timestamp: int | None,
) -> tuple[bool, str]:
@@ -905,8 +877,8 @@ class SignalChannel(BaseChannel):
sender_name: str | None,
sender_number: str,
message_text: str,
attachments: list[dict[str, Any]],
mentions: list[dict[str, Any]],
attachments: list,
mentions: list,
is_group_message: bool,
chat_id: str,
) -> tuple[str, list[str]]:
@@ -980,9 +952,7 @@ class SignalChannel(BaseChannel):
"""
# Create buffer for this group if it doesn't exist
if group_id not in self._group_buffers:
self._group_buffers[group_id] = deque[_BufferedMessage](
maxlen=self.config.group_message_buffer_size
)
self._group_buffers[group_id] = deque(maxlen=self.config.group_message_buffer_size)
# Add message to buffer (deque will automatically drop oldest when full)
self._group_buffers[group_id].append(
@@ -1022,7 +992,7 @@ class SignalChannel(BaseChannel):
# We want to show context BEFORE the mention
context_messages = list(buffer)[:-1] # Exclude the last (current) message
lines: list[str] = []
lines = []
for msg in context_messages:
sender = msg["sender_name"]
content = msg["content"][:200] # Limit to 200 chars per message
@@ -1083,6 +1053,8 @@ class SignalChannel(BaseChannel):
"""Remember known bot identifiers for mention matching."""
if not value:
return
if not isinstance(value, str):
return
for candidate in self._normalize_signal_id(value):
self._account_id_aliases.add(candidate)
@@ -1090,6 +1062,8 @@ class SignalChannel(BaseChannel):
"""Return True when an identifier refers to the bot account."""
if not value:
return False
if not isinstance(value, str):
return False
return any(
candidate in self._account_id_aliases for candidate in self._normalize_signal_id(value)
)
@@ -1123,14 +1097,13 @@ class SignalChannel(BaseChannel):
return sender_parts[0] if sender_parts else ""
@staticmethod
def _extract_group_id(group_info: object, group_v2: object) -> str | None:
def _extract_group_id(group_info: Any, group_v2: Any) -> str | None:
"""Extract group ID from groupInfo/groupV2 payloads across signal-cli variants."""
for group_obj in (group_info, group_v2):
if not isinstance(group_obj, dict):
continue
group = cast(dict[str, Any], group_obj)
for key in ("groupId", "id", "groupID"):
value = group.get(key)
value = group_obj.get(key)
if isinstance(value, str) and value:
return value
return None
@@ -1140,19 +1113,18 @@ class SignalChannel(BaseChannel):
"""Extract possible identifier fields from a mention payload."""
ids: list[str] = []
def _walk(value: object, depth: int = 0) -> None:
def _walk(value: dict[str, Any] | Any, depth: int = 0) -> None:
if depth > 2:
return
if not isinstance(value, dict):
return
object_value = cast(dict[str, Any], value)
for key, child in object_value.items():
key_lower = key.lower()
for key, child in value.items():
key_lower = str(key).lower()
if isinstance(child, str) and child:
if any(token in key_lower for token in ("number", "uuid", "serviceid", "aci")):
ids.append(child)
elif isinstance(child, dict):
_walk(cast(object, child), depth + 1)
_walk(child, depth + 1)
_walk(mention)
return list(dict.fromkeys(ids))
@@ -1215,6 +1187,8 @@ class SignalChannel(BaseChannel):
# If mention is required, check if bot was mentioned.
for mention in mentions:
if not isinstance(mention, dict):
continue
for mention_id in self._mention_id_candidates(mention):
if self._id_matches_account(mention_id):
return True
@@ -1223,13 +1197,15 @@ class SignalChannel(BaseChannel):
# (for handle-style mentions). Accept a leading identifier-less mention
# as a mention of the bot to avoid false negatives.
for mention in mentions:
if not isinstance(mention, dict):
continue
if self._mention_id_candidates(mention):
continue
span = self._mention_span(mention)
if not span:
continue
start, _ = span
if not message_text[:start].strip():
if message_text is not None and not message_text[:start].strip():
self.logger.debug("Accepting identifier-less leading mention as bot mention")
return True
@@ -1265,8 +1241,10 @@ class SignalChannel(BaseChannel):
return text
# Build a list of (start, length) tuples for our bot's mentions
bot_mentions: list[tuple[int, int]] = []
bot_mentions = []
for mention in mentions:
if not isinstance(mention, dict):
continue
mention_ids = self._mention_id_candidates(mention)
span = self._mention_span(mention)
if not span:
@@ -1404,7 +1382,7 @@ class SignalChannel(BaseChannel):
request_id = self._request_id
# Build JSON-RPC request
request: dict[str, Any] = {"jsonrpc": "2.0", "method": method, "id": request_id}
request = {"jsonrpc": "2.0", "method": method, "id": request_id}
if params:
request["params"] = params
@@ -1419,10 +1397,7 @@ class SignalChannel(BaseChannel):
try:
response = await self._http.post("/api/v1/rpc", json=request)
response.raise_for_status()
response_json = _as_json_object(response.json())
if response_json is None:
return {"error": {"message": "signal-cli returned a non-object JSON-RPC response"}}
return response_json
return response.json()
except Exception as e:
self.logger.error("HTTP request failed: {}", e)
return {"error": {"message": str(e)}}
+54 -155
View File
@@ -3,16 +3,15 @@
import asyncio
import re
from pathlib import Path
from typing import Any, Protocol, cast
from typing import Any
import httpx
from pydantic import Field
from slack_sdk.socket_mode.async_client import AsyncBaseSocketModeClient
from slack_sdk.socket_mode.request import SocketModeRequest
from slack_sdk.socket_mode.response import SocketModeResponse
from slack_sdk.socket_mode.websockets import SocketModeClient
from slack_sdk.web.async_client import AsyncWebClient
from slackify_markdown import slackify_markdown # pyright: ignore[reportMissingTypeStubs]
from slackify_markdown import slackify_markdown
from nanobot.bus.events import OutboundMessage
from nanobot.bus.outbound_events import ProgressEvent
@@ -24,30 +23,6 @@ from nanobot.pairing import is_approved
from nanobot.utils.helpers import safe_filename, split_message
def _as_json_object(value: Any) -> dict[str, Any] | None:
"""Narrow Slack's untyped Socket Mode payloads at the boundary."""
return cast(dict[str, Any], value) if isinstance(value, dict) else None
def _as_json_list(value: Any) -> list[Any] | None:
"""Narrow Slack's untyped Socket Mode arrays at the boundary."""
return cast(list[Any], value) if isinstance(value, list) else None
class _SlackWebAPI(Protocol):
"""Subset of slack-sdk's dynamically typed Web API used by this channel."""
async def auth_test(self, **kwargs: Any) -> Any: ...
async def chat_postMessage(self, **kwargs: Any) -> Any: ... # noqa: N802
async def conversations_list(self, **kwargs: Any) -> Any: ...
async def conversations_open(self, **kwargs: Any) -> Any: ...
async def conversations_replies(self, **kwargs: Any) -> Any: ...
async def files_upload_v2(self, **kwargs: Any) -> Any: ...
async def reactions_add(self, **kwargs: Any) -> Any: ...
async def reactions_remove(self, **kwargs: Any) -> Any: ...
async def users_list(self, **kwargs: Any) -> Any: ...
class SlackDMConfig(Base):
"""Slack DM policy configuration."""
@@ -115,13 +90,6 @@ class SlackChannel(BaseChannel):
self._target_cache: dict[str, str] = {}
self._thread_context_attempted: set[str] = set()
def _require_web_api(self) -> _SlackWebAPI:
if self._web_client is None:
raise RuntimeError("Slack Web API client is not started")
# slack-sdk's public methods are runtime-stable but its annotations do
# not expose a useful shared interface, so narrow once at the SDK edge.
return cast(_SlackWebAPI, self._web_client)
async def start(self) -> None:
"""Start the Slack Socket Mode client."""
if not self.config.bot_token or not self.config.app_token:
@@ -143,8 +111,7 @@ class SlackChannel(BaseChannel):
# Resolve bot user ID for mention handling
try:
web_api = self._require_web_api()
auth = await web_api.auth_test()
auth = await self._web_client.auth_test()
self._bot_user_id = auth.get("user_id")
self.logger.info("bot connected as {}", self._bot_user_id)
except Exception as e:
@@ -188,17 +155,10 @@ class SlackChannel(BaseChannel):
self.logger.warning("client not running")
return
try:
web_api = self._require_web_api()
target_chat_id = await self._resolve_target_chat_id(msg.chat_id)
raw_slack_meta: Any = msg.metadata.get("slack", {}) if msg.metadata else {}
slack_meta: dict[str, Any] = (
cast(dict[str, Any], raw_slack_meta)
if isinstance(raw_slack_meta, dict)
else {}
)
slack_meta = msg.metadata.get("slack", {}) if msg.metadata else {}
thread_ts = slack_meta.get("thread_ts")
event_meta = cast(dict[str, Any], slack_meta.get("event", {}) or {})
origin_chat_id = str(event_meta.get("channel") or msg.chat_id)
origin_chat_id = str((slack_meta.get("event", {}) or {}).get("channel") or msg.chat_id)
# Reply in the same thread the inbound message belongs to (works
# for both real channel threads and DM threads). When the agent
# is forwarding to a different channel, drop thread_ts because it
@@ -210,20 +170,7 @@ class SlackChannel(BaseChannel):
pass # skip empty progress messages (e.g. tool-event-only updates)
elif msg.content or not (msg.media or []):
mrkdwn = self._to_mrkdwn(msg.content) if msg.content else " "
raw_buttons = getattr(msg, "buttons", None)
buttons: list[list[str]] = (
cast(list[list[str]], raw_buttons)
if isinstance(raw_buttons, list)
and all(
isinstance(row, list)
and all(
isinstance(label, str)
for label in cast(list[object], row)
)
for row in cast(list[object], raw_buttons)
)
else []
)
buttons = getattr(msg, "buttons", None) or []
chunks = split_message(mrkdwn, SLACK_MAX_MESSAGE_LEN)
for index, chunk in enumerate(chunks):
kwargs: dict[str, Any] = dict(
@@ -231,11 +178,11 @@ class SlackChannel(BaseChannel):
)
if buttons and index == len(chunks) - 1:
kwargs["blocks"] = self._build_button_blocks(chunk, buttons)
await web_api.chat_postMessage(**kwargs)
await self._web_client.chat_postMessage(**kwargs)
for media_path in msg.media or []:
try:
await web_api.files_upload_v2(
await self._web_client.files_upload_v2(
channel=target_chat_id,
file=media_path,
thread_ts=thread_ts_param,
@@ -245,16 +192,8 @@ class SlackChannel(BaseChannel):
# Update reaction emoji when the final (non-progress) response is sent
if not is_progress:
raw_event = slack_meta.get("event", {})
event = (
cast(dict[str, Any], raw_event)
if isinstance(raw_event, dict)
else {}
)
await self._update_react_emoji(
origin_chat_id,
cast(str | None, event.get("ts")),
)
event = slack_meta.get("event", {})
await self._update_react_emoji(origin_chat_id, event.get("ts"))
except Exception:
self.logger.exception("Error sending message")
@@ -298,26 +237,20 @@ class SlackChannel(BaseChannel):
return self._target_cache[cache_key]
cursor: str | None = None
web_api = self._require_web_api()
while True:
response = cast(dict[str, Any], await web_api.conversations_list(
response = await self._web_client.conversations_list(
types="public_channel,private_channel",
exclude_archived=True,
limit=200,
cursor=cursor,
))
for channel_value in cast(list[object], response.get("channels", [])):
channel = cast(dict[str, Any], channel_value)
)
for channel in response.get("channels", []):
if self._normalize_target_name(str(channel.get("name") or "")) == normalized:
channel_id = str(channel.get("id") or "")
if channel_id:
self._target_cache[cache_key] = channel_id
return channel_id
response_metadata = cast(
dict[str, Any],
response.get("response_metadata") or {},
)
cursor = str(response_metadata.get("next_cursor") or "").strip()
cursor = ((response.get("response_metadata") or {}).get("next_cursor") or "").strip()
if not cursor:
break
@@ -336,14 +269,9 @@ class SlackChannel(BaseChannel):
return self._target_cache[cache_key]
cursor: str | None = None
web_api = self._require_web_api()
while True:
response = cast(
dict[str, Any],
await web_api.users_list(limit=200, cursor=cursor),
)
for member_value in cast(list[object], response.get("members", [])):
member = cast(dict[str, Any], member_value)
response = await self._web_client.users_list(limit=200, cursor=cursor)
for member in response.get("members", []):
if self._member_matches_handle(member, normalized):
user_id = str(member.get("id") or "")
if not user_id:
@@ -351,11 +279,7 @@ class SlackChannel(BaseChannel):
dm_id = await self._open_dm_for_user(user_id)
self._target_cache[cache_key] = dm_id
return dm_id
response_metadata = cast(
dict[str, Any],
response.get("response_metadata") or {},
)
cursor = str(response_metadata.get("next_cursor") or "").strip()
cursor = ((response.get("response_metadata") or {}).get("next_cursor") or "").strip()
if not cursor:
break
@@ -364,13 +288,8 @@ class SlackChannel(BaseChannel):
)
async def _open_dm_for_user(self, user_id: str) -> str:
web_api = self._require_web_api()
response = cast(
dict[str, Any],
await web_api.conversations_open(users=user_id),
)
channel = cast(dict[str, Any], response.get("channel") or {})
channel_id = str(channel.get("id") or "")
response = await self._web_client.conversations_open(users=user_id)
channel_id = str(((response.get("channel") or {}).get("id")) or "")
if not channel_id:
raise ValueError(f"Slack DM target for user '{user_id}' could not be opened.")
return channel_id
@@ -381,7 +300,7 @@ class SlackChannel(BaseChannel):
@classmethod
def _member_matches_handle(cls, member: dict[str, Any], normalized: str) -> bool:
profile = cast(dict[str, Any], member.get("profile") or {})
profile = member.get("profile") or {}
candidates = {
str(member.get("name") or ""),
str(profile.get("display_name") or ""),
@@ -393,7 +312,7 @@ class SlackChannel(BaseChannel):
async def _on_socket_request(
self,
client: AsyncBaseSocketModeClient,
client: SocketModeClient,
req: SocketModeRequest,
) -> None:
"""Handle incoming Socket Mode requests."""
@@ -408,8 +327,8 @@ class SlackChannel(BaseChannel):
SocketModeResponse(envelope_id=req.envelope_id)
)
payload = _as_json_object(cast(Any, req).payload) or {}
event = _as_json_object(payload.get("event")) or {}
payload = req.payload or {}
event = payload.get("event") or {}
event_type = event.get("type")
# Handle app mentions or plain messages
@@ -430,8 +349,6 @@ class SlackChannel(BaseChannel):
# Avoid double-processing: Slack sends both `message` and `app_mention`
# for mentions in channels. Prefer `app_mention`.
text = event.get("text") or ""
if not isinstance(text, str):
return
if event_type == "message" and self._bot_user_id and f"<@{self._bot_user_id}>" in text:
return
@@ -445,12 +362,10 @@ class SlackChannel(BaseChannel):
event.get("channel_type"),
text[:80],
)
if not isinstance(sender_id, str) or not sender_id or not isinstance(chat_id, str) or not chat_id:
if not sender_id or not chat_id:
return
channel_type = event.get("channel_type") or ""
if not isinstance(channel_type, str):
channel_type = ""
if not self._is_allowed(sender_id, chat_id, channel_type):
if channel_type == "im" and self.config.dm.enabled:
@@ -468,9 +383,7 @@ class SlackChannel(BaseChannel):
text = self._strip_bot_mention(text)
event_ts = event.get("ts")
event_ts = event_ts if isinstance(event_ts, str) else None
raw_thread_ts = event.get("thread_ts")
raw_thread_ts = raw_thread_ts if isinstance(raw_thread_ts, str) else None
thread_ts = raw_thread_ts
# In DMs we don't auto-open a thread on top-level messages (it would
# bury replies under "1 reply"). But if the user explicitly opened a
@@ -483,28 +396,27 @@ class SlackChannel(BaseChannel):
thread_ts = event_ts
# Add :eyes: reaction to the triggering message (best-effort)
try:
if self._web_client and event_ts:
web_api = self._require_web_api()
await web_api.reactions_add(
if self._web_client and event.get("ts"):
await self._web_client.reactions_add(
channel=chat_id,
name=self.config.react_emoji,
timestamp=event_ts,
timestamp=event.get("ts"),
)
except Exception as e:
self.logger.debug("reactions_add failed: {}", e)
# Thread-scoped session key whenever the turn lives in a thread: either the
# message arrived inside one (raw_thread_ts) or reply_in_thread opens a new
# thread for this channel message. DM roots have no thread_ts and keep the
# default per-chat session, so context doesn't bleed across thread boundaries.
session_key = f"slack:{chat_id}:{thread_ts}" if thread_ts else None
# Thread-scoped session key whenever the user is in a real thread
# (raw_thread_ts is set). DM threads get their own session, separate
# from the DM root, so context doesn't bleed across thread boundaries.
session_key = (
f"slack:{chat_id}:{thread_ts}" if thread_ts and raw_thread_ts else None
)
media_paths: list[str] = []
file_markers: list[str] = []
for file_info in _as_json_list(event.get("files")) or []:
file_info_object = _as_json_object(file_info)
if file_info_object is None:
for file_info in event.get("files") or []:
if not isinstance(file_info, dict):
continue
file_path, marker = await self._download_slack_file(file_info_object)
file_path, marker = await self._download_slack_file(file_info)
if file_path:
media_paths.append(file_path)
if marker:
@@ -591,30 +503,22 @@ class SlackChannel(BaseChannel):
preview = response.content[:256].lstrip().lower()
return preview.startswith(_HTML_DOWNLOAD_PREFIXES)
async def _on_block_action(
self,
client: AsyncBaseSocketModeClient,
req: SocketModeRequest,
) -> None:
async def _on_block_action(self, client: SocketModeClient, req: SocketModeRequest) -> None:
"""Handle button clicks from inline action buttons."""
await client.send_socket_mode_response(SocketModeResponse(envelope_id=req.envelope_id))
payload = cast(dict[str, Any], cast(Any, req).payload or {})
actions = cast(list[Any], payload.get("actions") or [])
payload = req.payload or {}
actions = payload.get("actions") or []
if not actions:
return
action = cast(dict[str, Any], actions[0])
value = str(action.get("value") or "")
user_info = cast(dict[str, Any], payload.get("user") or {})
value = str(actions[0].get("value") or "")
user_info = payload.get("user") or {}
sender_id = str(user_info.get("id") or "")
channel_info = cast(dict[str, Any], payload.get("channel") or {})
channel_info = payload.get("channel") or {}
chat_id = str(channel_info.get("id") or "")
if not sender_id or not chat_id or not value:
return
message_info = cast(dict[str, Any], payload.get("message") or {})
thread_ts = cast(
str | None,
message_info.get("thread_ts") or message_info.get("ts"),
)
message_info = payload.get("message") or {}
thread_ts = message_info.get("thread_ts") or message_info.get("ts")
channel_type = self._infer_channel_type(chat_id)
if not self._is_allowed(sender_id, chat_id, channel_type):
return
@@ -659,18 +563,17 @@ class SlackChannel(BaseChannel):
self._thread_context_attempted.add(key)
try:
web_api = self._require_web_api()
response = cast(dict[str, Any], await web_api.conversations_replies(
response = await self._web_client.conversations_replies(
channel=chat_id,
ts=thread_ts,
limit=max(1, self.config.thread_context_limit),
))
)
except Exception as e:
self.logger.warning("thread context unavailable for {}: {}", key, e)
return text
lines = self._format_thread_context(
cast(list[dict[str, Any]], response.get("messages", [])),
response.get("messages", []),
current_ts=current_ts,
)
if not lines:
@@ -702,7 +605,7 @@ class SlackChannel(BaseChannel):
blocks: list[dict[str, Any]] = [
{"type": "section", "text": {"type": "mrkdwn", "text": text[:3000]}},
]
elements: list[dict[str, Any]] = []
elements = []
for row in buttons:
for label in row:
elements.append({
@@ -719,9 +622,8 @@ class SlackChannel(BaseChannel):
"""Remove the in-progress reaction and optionally add a done reaction."""
if not self._web_client or not ts:
return
web_api = self._require_web_api()
try:
await web_api.reactions_remove(
await self._web_client.reactions_remove(
channel=chat_id,
name=self.config.react_emoji,
timestamp=ts,
@@ -730,7 +632,7 @@ class SlackChannel(BaseChannel):
self.logger.debug("reactions_remove failed: {}", e)
if self.config.done_emoji:
try:
await web_api.reactions_add(
await self._web_client.reactions_add(
channel=chat_id,
name=self.config.done_emoji,
timestamp=ts,
@@ -801,7 +703,7 @@ class SlackChannel(BaseChannel):
return ""
code_blocks: list[str] = []
def _save_fence(m: re.Match[str]) -> str:
def _save_fence(m: re.Match) -> str:
code_blocks.append(m.group(0))
return f"\x00CB{len(code_blocks) - 1}\x00"
@@ -816,7 +718,7 @@ class SlackChannel(BaseChannel):
"""Fix markdown artifacts that slackify_markdown misses."""
code_blocks: list[str] = []
def _save_code(m: re.Match[str]) -> str:
def _save_code(m: re.Match) -> str:
code_blocks.append(m.group(0))
return f"\x00CB{len(code_blocks) - 1}\x00"
@@ -824,17 +726,14 @@ class SlackChannel(BaseChannel):
text = cls._INLINE_CODE_RE.sub(_save_code, text)
text = cls._LEFTOVER_BOLD_RE.sub(r"*\1*", text)
text = cls._LEFTOVER_HEADER_RE.sub(r"*\1*", text)
text = cls._BARE_URL_RE.sub(
lambda m: m.group(0).replace("&amp;", "&"),
text,
)
text = cls._BARE_URL_RE.sub(lambda m: m.group(0).replace("&amp;", "&"), text)
for i, block in enumerate(code_blocks):
text = text.replace(f"\x00CB{i}\x00", block)
return text
@staticmethod
def _convert_table(match: re.Match[str]) -> str:
def _convert_table(match: re.Match) -> str:
"""Convert a Markdown table to a Slack-readable list."""
lines = [ln.strip() for ln in match.group(0).strip().splitlines() if ln.strip()]
if len(lines) < 2:
@@ -555,113 +555,6 @@ async def test_dm_thread_message_keeps_thread_ts_and_threaded_session() -> None:
assert kwargs["metadata"]["slack"]["thread_ts"] == "1700000000.000100"
def _channel_mention_request(envelope_id: str, ts: str) -> SimpleNamespace:
return SimpleNamespace(
type="events_api",
envelope_id=envelope_id,
payload={
"event": {
"type": "app_mention",
"user": "U1",
"channel": "C123",
"text": "<@UBOT> hello",
"ts": ts,
}
},
)
@pytest.mark.asyncio
async def test_channel_root_message_uses_thread_scoped_session() -> None:
"""A channel mention that opens a thread belongs to that thread's session."""
channel = SlackChannel(SlackConfig(enabled=True), MessageBus())
channel._bot_user_id = "UBOT"
channel._web_client = _FakeAsyncWebClient()
channel._handle_message = AsyncMock() # type: ignore[method-assign]
client = SimpleNamespace(send_socket_mode_response=AsyncMock())
req = _channel_mention_request("env-c1", "1700000000.000100")
await channel._on_socket_request(client, req)
channel._handle_message.assert_awaited_once()
kwargs = channel._handle_message.await_args.kwargs
assert kwargs["session_key"] == "slack:C123:1700000000.000100"
assert kwargs["metadata"]["slack"]["thread_ts"] == "1700000000.000100"
@pytest.mark.asyncio
async def test_channel_root_messages_do_not_share_one_session() -> None:
"""Two threads opened in the same channel must not collapse into one session."""
channel = SlackChannel(SlackConfig(enabled=True), MessageBus())
channel._bot_user_id = "UBOT"
channel._web_client = _FakeAsyncWebClient()
channel._handle_message = AsyncMock() # type: ignore[method-assign]
client = SimpleNamespace(send_socket_mode_response=AsyncMock())
first = _channel_mention_request("env-c1", "1700000000.000100")
second = _channel_mention_request("env-c2", "1700000000.000200")
await channel._on_socket_request(client, first)
await channel._on_socket_request(client, second)
session_keys = [call.kwargs["session_key"] for call in channel._handle_message.await_args_list]
assert session_keys == [
"slack:C123:1700000000.000100",
"slack:C123:1700000000.000200",
]
@pytest.mark.asyncio
async def test_channel_root_message_without_reply_in_thread_uses_channel_session() -> None:
"""With reply_in_thread disabled no thread is opened, so the channel session is used."""
channel = SlackChannel(SlackConfig(enabled=True, reply_in_thread=False), MessageBus())
channel._bot_user_id = "UBOT"
channel._web_client = _FakeAsyncWebClient()
channel._handle_message = AsyncMock() # type: ignore[method-assign]
client = SimpleNamespace(send_socket_mode_response=AsyncMock())
req = _channel_mention_request("env-c3", "1700000000.000300")
await channel._on_socket_request(client, req)
channel._handle_message.assert_awaited_once()
kwargs = channel._handle_message.await_args.kwargs
assert kwargs["session_key"] is None
assert kwargs["metadata"]["slack"]["thread_ts"] is None
@pytest.mark.asyncio
async def test_channel_thread_reply_keeps_thread_session() -> None:
"""A reply inside a channel thread stays in the session opened by the root message."""
channel = SlackChannel(SlackConfig(enabled=True), MessageBus())
channel._bot_user_id = "UBOT"
channel._web_client = _FakeAsyncWebClient()
channel._handle_message = AsyncMock() # type: ignore[method-assign]
channel._with_thread_context = AsyncMock(return_value="hello") # type: ignore[method-assign]
client = SimpleNamespace(send_socket_mode_response=AsyncMock())
req = SimpleNamespace(
type="events_api",
envelope_id="env-c4",
payload={
"event": {
"type": "app_mention",
"user": "U1",
"channel": "C123",
"text": "<@UBOT> follow up",
"ts": "1700000000.000400",
"thread_ts": "1700000000.000100",
}
},
)
await channel._on_socket_request(client, req)
channel._handle_message.assert_awaited_once()
kwargs = channel._handle_message.await_args.kwargs
assert kwargs["session_key"] == "slack:C123:1700000000.000100"
@pytest.mark.asyncio
async def test_slack_slash_command_skips_thread_context() -> None:
channel = SlackChannel(SlackConfig(enabled=True, allow_from=[]), MessageBus())
+55 -103
View File
@@ -8,9 +8,8 @@ import time
import unicodedata
from contextlib import suppress
from dataclasses import dataclass
from datetime import timedelta
from pathlib import Path
from typing import Any, Awaitable, Callable, Literal, TypeAlias, TypeVar, cast
from typing import Any, Literal
from urllib.parse import urlparse
from pydantic import Field, field_validator, model_validator
@@ -18,12 +17,9 @@ from telegram import (
BotCommand,
InlineKeyboardButton,
InlineKeyboardMarkup,
Message,
MessageEntity,
ReactionTypeEmoji,
ReplyParameters,
Update,
User,
)
from telegram.error import BadRequest, NetworkError, TimedOut
from telegram.ext import Application, CallbackQueryHandler, ContextTypes, MessageHandler, filters
@@ -47,12 +43,6 @@ TELEGRAM_MAX_MESSAGE_LEN = 4000 # Telegram message character limit
TELEGRAM_HTML_MAX_LEN = 4096
TELEGRAM_REPLY_CONTEXT_MAX_LEN = TELEGRAM_MAX_MESSAGE_LEN # Max length for reply context in user message
# python-telegram-bot exposes a six-parameter Application generic. Nanobot
# doesn't customize its context/data/job-queue types, so keep that SDK boundary
# explicit rather than allowing unspecialized generics to spread Unknown.
TelegramApplication: TypeAlias = Application[Any, Any, Any, Any, Any, Any]
_T = TypeVar("_T")
def _split_telegram_markdown(content: str, max_len: int) -> list[str]:
"""Split raw Telegram Markdown without leaving fenced code blocks unbalanced."""
@@ -228,7 +218,7 @@ def _markdown_to_telegram_html(text: str) -> str:
# 1. Extract and protect code blocks (preserve content from other processing)
code_blocks: list[str] = []
def save_code_block(m: re.Match[str]) -> str:
def save_code_block(m: re.Match) -> str:
code_blocks.append(m.group(1))
return f"\x00CB{len(code_blocks) - 1}\x00"
@@ -257,7 +247,7 @@ def _markdown_to_telegram_html(text: str) -> str:
# 2. Extract and protect inline code
inline_codes: list[str] = []
def save_inline_code(m: re.Match[str]) -> str:
def save_inline_code(m: re.Match) -> str:
inline_codes.append(m.group(1))
return f"\x00IC{len(inline_codes) - 1}\x00"
@@ -360,7 +350,7 @@ class _QueuedTelegramUpdate:
kind: Literal["command", "message"]
update: Update
context: ContextTypes.DEFAULT_TYPE
context: Any
sort_key: tuple[int, int]
@@ -431,7 +421,7 @@ class TelegramChannel(BaseChannel):
display_name = "Telegram"
# Commands registered with Telegram's command menu
BOT_COMMANDS: list[BotCommand] = [
BOT_COMMANDS = [
BotCommand("start", "Start the bot"),
BotCommand("new", "Start a new conversation"),
BotCommand("stop", "Stop the current task"),
@@ -465,24 +455,19 @@ class TelegramChannel(BaseChannel):
config = TelegramConfig.model_validate(config)
super().__init__(config, bus)
self.config: TelegramConfig = config
self._app: TelegramApplication | None = None
self._app: Application | None = None
self._chat_ids: dict[str, int] = {} # Map sender_id to chat_id for replies
self._typing_tasks: dict[str, asyncio.Task[None]] = {} # chat_id -> typing loop task
self._media_group_buffers: dict[str, dict[str, Any]] = {}
self._media_group_tasks: dict[str, asyncio.Task[None]] = {}
self._typing_tasks: dict[str, asyncio.Task] = {} # chat_id -> typing loop task
self._media_group_buffers: dict[str, dict] = {}
self._media_group_tasks: dict[str, asyncio.Task] = {}
self._message_threads: dict[tuple[str, int], int] = {}
self._bot_user_id: int | None = None
self._bot_username: str | None = None
self._stream_bufs: dict[str, _StreamBuf] = {} # chat_id -> streaming state
self._inbound_buffers: dict[str, list[_QueuedTelegramUpdate]] = {}
self._inbound_workers: dict[str, asyncio.Task[None]] = {}
self._inbound_workers: dict[str, asyncio.Task] = {}
self._rich_send_disabled: bool = False # Latch off if Bot API < 10.1
def _require_app(self) -> TelegramApplication:
if self._app is None:
raise RuntimeError("Telegram application is not started")
return self._app
def is_allowed(self, sender_id: str) -> bool:
"""Preserve Telegram's legacy id|username allowlist matching."""
if super().is_allowed(sender_id):
@@ -610,7 +595,7 @@ class TelegramChannel(BaseChannel):
if self.config.mode == "webhook":
# ``url_path`` is the local HTTP route. ``webhook_url`` is the
# public HTTPS URL Telegram calls; reverse proxies may rewrite it.
await cast(Any, self._app.updater).start_webhook(
await self._app.updater.start_webhook(
listen=self.config.webhook_listen_host,
port=self.config.webhook_listen_port,
url_path=self.config.webhook_path.lstrip("/"),
@@ -622,7 +607,7 @@ class TelegramChannel(BaseChannel):
)
else:
# Start polling (this runs until stopped)
await cast(Any, self._app.updater).start_polling(
await self._app.updater.start_polling(
allowed_updates=allowed_updates,
drop_pending_updates=False, # Process pending messages on startup
error_callback=self._on_polling_error,
@@ -652,7 +637,7 @@ class TelegramChannel(BaseChannel):
if self._app:
self.logger.info("Stopping bot...")
await cast(Any, self._app.updater).stop()
await self._app.updater.stop()
await self._app.stop()
await self._app.shutdown()
self._app = None
@@ -689,9 +674,9 @@ class TelegramChannel(BaseChannel):
self,
chat_id: int,
content: str,
reply_params: ReplyParameters | dict[str, int | bool] | None = None,
thread_kwargs: dict[str, int] | None = None,
reply_markup: InlineKeyboardMarkup | None = None,
reply_params=None,
thread_kwargs: dict | None = None,
reply_markup=None,
) -> bool:
"""Attempt sendRichMessage (Bot API 10.1). Returns True on success."""
if not self._app:
@@ -707,17 +692,13 @@ class TelegramChannel(BaseChannel):
# sendRichMessage uses reply_parameters (object), not reply_to_message_id.
if hasattr(reply_params, "message_id"):
payload["reply_parameters"] = {
"message_id": cast(ReplyParameters, reply_params).message_id,
"message_id": reply_params.message_id,
"allow_sending_without_reply": True,
}
else:
payload["reply_parameters"] = reply_params
if thread_kwargs:
payload.update({
k: v
for k, v in thread_kwargs.items()
if v is not None # pyright: ignore[reportUnnecessaryComparison]
})
payload.update({k: v for k, v in thread_kwargs.items() if v is not None})
if reply_markup is not None:
payload["reply_markup"] = reply_markup
@@ -768,7 +749,7 @@ class TelegramChannel(BaseChannel):
message_thread_id = msg.metadata.get("message_thread_id")
if message_thread_id is None and reply_to_message_id is not None:
message_thread_id = self._message_threads.get((msg.chat_id, reply_to_message_id))
thread_kwargs: dict[str, int] = {}
thread_kwargs = {}
if message_thread_id is not None:
thread_kwargs["message_thread_id"] = message_thread_id
@@ -839,7 +820,7 @@ class TelegramChannel(BaseChannel):
# Send text content
if msg.content and msg.content != "[empty message]":
render_as_blockquote = bool(progress_event and progress_event.tool_hint)
buttons = cast(list[list[str]], getattr(msg, "buttons", None) or [])
buttons = getattr(msg, "buttons", None) or []
reply_markup = self._build_keyboard(buttons) if buttons else None
text = msg.content
# Fallback: no native keyboard → splice labels into the message so the choices survive.
@@ -869,12 +850,7 @@ class TelegramChannel(BaseChannel):
reply_markup=reply_markup if is_last else None,
)
async def _call_with_retry(
self,
fn: Callable[..., Awaitable[_T]],
*args: Any,
**kwargs: Any,
) -> _T:
async def _call_with_retry(self, fn, *args, **kwargs):
"""Call an async Telegram API function with retry on pool/network timeout and RetryAfter."""
from telegram.error import RetryAfter
@@ -893,34 +869,27 @@ class TelegramChannel(BaseChannel):
except RetryAfter as e:
if attempt == _SEND_MAX_RETRIES:
raise
retry_after = e.retry_after
delay = (
retry_after.total_seconds()
if isinstance(retry_after, timedelta)
else float(retry_after)
)
delay = float(e.retry_after)
self.logger.warning(
"Flood Control (attempt {}/{}), retrying in {:.1f}s",
attempt, _SEND_MAX_RETRIES, delay,
)
await asyncio.sleep(delay)
raise RuntimeError("Telegram retry loop exited unexpectedly")
async def _send_text(
self,
chat_id: int,
text: str,
reply_params: ReplyParameters | None = None,
thread_kwargs: dict[str, int] | None = None,
reply_params=None,
thread_kwargs: dict | None = None,
render_as_blockquote: bool = False,
reply_markup: InlineKeyboardMarkup | None = None,
reply_markup=None,
) -> None:
"""Send a plain text message with HTML fallback."""
app = self._require_app()
try:
html = _tool_hint_to_telegram_blockquote(text) if render_as_blockquote else _markdown_to_telegram_html(text)
await self._call_with_retry(
app.bot.send_message,
self._app.bot.send_message,
chat_id=chat_id, text=html, parse_mode="HTML",
reply_parameters=reply_params,
reply_markup=reply_markup,
@@ -930,7 +899,7 @@ class TelegramChannel(BaseChannel):
self.logger.warning("HTML parse failed, falling back to plain text: {}", e)
try:
await self._call_with_retry(
app.bot.send_message,
self._app.bot.send_message,
chat_id=chat_id,
text=text,
reply_parameters=reply_params,
@@ -954,7 +923,6 @@ class TelegramChannel(BaseChannel):
stream_id: str | None = None,
stream_end: bool = False,
resuming: bool = False,
merge_next: bool = False,
) -> None:
"""Progressive message editing: send on first delta, edit on subsequent ones."""
if not self._app:
@@ -962,10 +930,6 @@ class TelegramChannel(BaseChannel):
meta = metadata or {}
int_chat_id = int(chat_id)
if stream_end and merge_next:
if not delta:
return
stream_end = False
if stream_end:
buf = self._stream_bufs.get(chat_id)
if not buf or not buf.message_id or not buf.text:
@@ -976,7 +940,7 @@ class TelegramChannel(BaseChannel):
if reply_to_message_id := meta.get("message_id"):
with suppress(ValueError):
await self._remove_reaction(chat_id, int(reply_to_message_id))
thread_kwargs: dict[str, int] = {}
thread_kwargs = {}
if message_thread_id := meta.get("message_thread_id"):
thread_kwargs["message_thread_id"] = message_thread_id
raw_text = buf.text
@@ -1063,16 +1027,16 @@ class TelegramChannel(BaseChannel):
return
now = time.monotonic()
stream_thread_kwargs: dict[str, int] = {}
thread_kwargs = {}
if message_thread_id := meta.get("message_thread_id"):
stream_thread_kwargs["message_thread_id"] = message_thread_id
thread_kwargs["message_thread_id"] = message_thread_id
if buf.message_id is None:
preview = _strip_md_block(buf.text)
try:
sent = await self._call_with_retry(
self._app.bot.send_message,
chat_id=int_chat_id, text=preview,
**stream_thread_kwargs,
**thread_kwargs,
)
buf.message_id = sent.message_id
buf.last_edit = now
@@ -1081,7 +1045,7 @@ class TelegramChannel(BaseChannel):
raise # Let ChannelManager handle retry
elif (now - buf.last_edit) >= self.config.stream_edit_interval:
if len(buf.text) > TELEGRAM_MAX_MESSAGE_LEN:
await self._flush_stream_overflow(int_chat_id, buf, stream_thread_kwargs)
await self._flush_stream_overflow(int_chat_id, buf, thread_kwargs)
buf.last_edit = now
return
preview = _strip_md_block(buf.text)
@@ -1103,7 +1067,7 @@ class TelegramChannel(BaseChannel):
self,
chat_id: int,
buf: "_StreamBuf",
thread_kwargs: dict[str, int],
thread_kwargs: dict,
) -> None:
"""Split an oversized stream buffer mid-flight.
@@ -1114,11 +1078,10 @@ class TelegramChannel(BaseChannel):
chunks = _split_telegram_markdown_html_chunks(buf.text, TELEGRAM_HTML_MAX_LEN)
if len(chunks) <= 1:
return
app = self._require_app()
first_markdown, first_html = chunks[0]
try:
await self._call_with_retry(
app.bot.edit_message_text,
self._app.bot.edit_message_text,
chat_id=chat_id, message_id=buf.message_id,
text=first_html,
parse_mode="HTML",
@@ -1130,7 +1093,7 @@ class TelegramChannel(BaseChannel):
)
try:
await self._call_with_retry(
app.bot.edit_message_text,
self._app.bot.edit_message_text,
chat_id=chat_id, message_id=buf.message_id,
text=first_markdown,
)
@@ -1145,7 +1108,7 @@ class TelegramChannel(BaseChannel):
async def send_chunk(markdown: str, html: str) -> Any:
try:
return await self._call_with_retry(
app.bot.send_message,
self._app.bot.send_message,
chat_id=chat_id, text=html, parse_mode="HTML", **thread_kwargs,
)
except BadRequest as e:
@@ -1153,7 +1116,7 @@ class TelegramChannel(BaseChannel):
"Stream overflow HTML send failed, falling back to plain text: {}", e
)
return await self._call_with_retry(
app.bot.send_message,
self._app.bot.send_message,
chat_id=chat_id, text=markdown, **thread_kwargs,
)
@@ -1192,14 +1155,12 @@ class TelegramChannel(BaseChannel):
await update.message.reply_text(build_help_text())
@staticmethod
def _sender_id(user: User) -> str:
def _sender_id(user) -> str:
"""Build sender_id with username for allowlist matching."""
sid = str(user.id)
return f"{sid}|{user.username}" if user.username else sid
async def _send_pairing_code_if_private(
self, sender_id: str, message: Message, user: User
) -> None:
async def _send_pairing_code_if_private(self, sender_id: str, message, user) -> None:
if message.chat.type != "private":
return
await self._handle_message(
@@ -1211,7 +1172,7 @@ class TelegramChannel(BaseChannel):
)
@staticmethod
def _derive_topic_session_key(message: Message) -> str | None:
def _derive_topic_session_key(message) -> str | None:
"""Derive topic-scoped session key for Telegram chats with threads."""
message_thread_id = getattr(message, "message_thread_id", None)
if message_thread_id is None:
@@ -1219,7 +1180,7 @@ class TelegramChannel(BaseChannel):
return f"telegram:{message.chat_id}:topic:{message_thread_id}"
@staticmethod
def _build_message_metadata(message: Message, user: User) -> dict[str, Any]:
def _build_message_metadata(message, user) -> dict:
"""Build common Telegram inbound metadata payload."""
reply_to = getattr(message, "reply_to_message", None)
return {
@@ -1233,7 +1194,7 @@ class TelegramChannel(BaseChannel):
"reply_to_message_id": getattr(reply_to, "message_id", None) if reply_to else None,
}
async def _extract_reply_context(self, message: Message) -> str | None:
async def _extract_reply_context(self, message) -> str | None:
"""Extract text from the message being replied to, if any."""
reply = getattr(message, "reply_to_message", None)
if not reply:
@@ -1258,7 +1219,7 @@ class TelegramChannel(BaseChannel):
return f"[Reply to: {text}]"
async def _download_message_media(
self, msg: Message, *, add_failure_content: bool = False
self, msg, *, add_failure_content: bool = False
) -> tuple[list[str], list[str]]:
"""Download media from a message (current or reply). Returns (media_paths, content_parts)."""
media_file = None
@@ -1289,7 +1250,7 @@ class TelegramChannel(BaseChannel):
try:
file = await self._app.bot.get_file(media_file.file_id)
ext = self._get_extension(
cast(str, media_type),
media_type,
getattr(media_file, "mime_type", None),
getattr(media_file, "file_name", None),
)
@@ -1325,7 +1286,7 @@ class TelegramChannel(BaseChannel):
@staticmethod
def _has_mention_entity(
text: str,
entities: list[MessageEntity] | None,
entities,
bot_username: str,
bot_id: int | None,
) -> bool:
@@ -1348,7 +1309,7 @@ class TelegramChannel(BaseChannel):
return True
return handle in text.lower()
async def _is_group_message_for_bot(self, message: Message) -> bool:
async def _is_group_message_for_bot(self, message) -> bool:
"""Allow group messages when policy is open, @mentioned, or replying to the bot."""
if message.chat.type == "private" or self.config.group_policy == "open":
return True
@@ -1375,7 +1336,7 @@ class TelegramChannel(BaseChannel):
reply_user = getattr(getattr(message, "reply_to_message", None), "from_user", None)
return bool(bot_id and reply_user and reply_user.id == bot_id)
def _remember_thread_context(self, message: Message) -> None:
def _remember_thread_context(self, message) -> None:
"""Cache Telegram thread context by chat/message id for follow-up replies."""
message_thread_id = getattr(message, "message_thread_id", None)
if message_thread_id is None:
@@ -1386,7 +1347,7 @@ class TelegramChannel(BaseChannel):
self._message_threads.pop(next(iter(self._message_threads)))
@staticmethod
def _queue_key_for_message(message: Message) -> str:
def _queue_key_for_message(message) -> str:
"""Return the final nanobot session key used for ordered Telegram ingress."""
return TelegramChannel._derive_topic_session_key(message) or f"telegram:{message.chat_id}"
@@ -1407,8 +1368,6 @@ class TelegramChannel(BaseChannel):
) -> None:
"""Stage a Telegram update behind a short per-session reorder window."""
message = update.message
if message is None:
return
key = self._queue_key_for_message(message)
self._inbound_buffers.setdefault(key, []).append(
_QueuedTelegramUpdate(
@@ -1468,8 +1427,6 @@ class TelegramChannel(BaseChannel):
"""Process a queued slash command."""
message = update.message
user = update.effective_user
if message is None or user is None:
return
sender_id = self._sender_id(user)
if not self.is_allowed(sender_id):
await self._send_pairing_code_if_private(sender_id, message, user)
@@ -1507,8 +1464,6 @@ class TelegramChannel(BaseChannel):
message = update.message
user = update.effective_user
if message is None or user is None:
return
chat_id = message.chat_id
sender_id = self._sender_id(user)
if not self.is_allowed(sender_id):
@@ -1523,8 +1478,8 @@ class TelegramChannel(BaseChannel):
return
# Build content from text and/or media
content_parts: list[str] = []
media_paths: list[str] = []
content_parts = []
media_paths = []
# Text content
if message.text:
@@ -1665,10 +1620,8 @@ class TelegramChannel(BaseChannel):
self.logger.debug("Typing indicator stopped for {}: {}", chat_id, e)
@staticmethod
def _format_telegram_error(exc: Exception | None) -> str:
def _format_telegram_error(exc: Exception) -> str:
"""Return a short, readable error summary for logs."""
if exc is None:
return "None"
text = str(exc).strip()
if text:
return text
@@ -1724,7 +1677,7 @@ class TelegramChannel(BaseChannel):
return ""
def _build_keyboard(self, buttons: list[list[str]]) -> InlineKeyboardMarkup | None:
def _build_keyboard(self, buttons: list) -> InlineKeyboardMarkup | None:
"""Build inline keyboard markup if inline_keyboards is enabled."""
if not buttons or not self.config.inline_keyboards:
return None
@@ -1753,8 +1706,7 @@ class TelegramChannel(BaseChannel):
return
query = update.callback_query
user = update.effective_user
query_message = query.message
chat_id = query_message.chat.id if query_message else None
chat_id = query.message.chat_id if query.message else None
sender_id = self._sender_id(user)
if not chat_id:
self.logger.warning("Callback query without chat_id")
@@ -1763,9 +1715,9 @@ class TelegramChannel(BaseChannel):
return
button_label = query.data or ""
await query.answer()
if isinstance(query_message, Message):
if query.message:
with suppress(Exception):
await query_message.edit_reply_markup(reply_markup=None)
await query.message.edit_reply_markup(reply_markup=None)
self.logger.debug("Inline button tap from {}: {}", sender_id, button_label)
self._start_typing(str(chat_id))
await self._handle_message(
@@ -1,5 +1,4 @@
import asyncio
from datetime import timedelta
from pathlib import Path
from types import SimpleNamespace
from unittest.mock import AsyncMock
@@ -676,33 +675,6 @@ async def test_send_delta_stream_end_raises_and_keeps_buffer_on_failure() -> Non
assert "123" in channel._stream_bufs
@pytest.mark.asyncio
async def test_send_delta_merge_next_preserves_buffer() -> None:
channel = TelegramChannel(
TelegramConfig(enabled=True, token="123:abc", allow_from=["*"]),
MessageBus(),
)
channel._app = _FakeApp(lambda: None)
channel._app.bot.edit_message_text = AsyncMock()
channel._stream_bufs["123"] = _StreamBuf(
text="first-",
message_id=7,
last_edit=float("inf"),
stream_id="s:0",
)
await channel.send_delta(
"123",
"boundary",
stream_id="s:0",
stream_end=True,
merge_next=True,
)
assert channel._stream_bufs["123"].text == "first-boundary"
channel._app.bot.edit_message_text.assert_not_awaited()
@pytest.mark.asyncio
async def test_send_delta_stream_end_treats_not_modified_as_success() -> None:
from telegram.error import BadRequest
@@ -1912,36 +1884,6 @@ async def test_on_message_location_with_text() -> None:
# Tests for retry amplification fix (issue #3050)
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_call_with_retry_accepts_timedelta_retry_after(
monkeypatch: pytest.MonkeyPatch,
) -> None:
from telegram.error import RetryAfter
channel = TelegramChannel(
TelegramConfig(enabled=True, token="123:abc", allow_from=["*"]),
MessageBus(),
)
attempts = 0
async def retry_once() -> str:
nonlocal attempts
attempts += 1
if attempts == 1:
raise RetryAfter(timedelta(seconds=1.5))
return "ok"
sleep = AsyncMock()
monkeypatch.setenv("PTB_TIMEDELTA", "1")
monkeypatch.setattr(
"nanobot.channels.telegram.runtime.asyncio.sleep",
sleep,
)
assert await channel._call_with_retry(retry_once) == "ok"
sleep.assert_awaited_once_with(1.5)
@pytest.mark.asyncio
async def test_send_text_does_not_fallback_on_network_timeout() -> None:
"""TimedOut should propagate immediately, NOT trigger plain-text fallback.
@@ -2349,7 +2291,7 @@ async def test_callback_query_ignores_unauthorized_user_before_side_effects() ->
data="Yes",
answer=AsyncMock(),
message=SimpleNamespace(
chat=SimpleNamespace(id=123),
chat_id=123,
edit_reply_markup=AsyncMock(),
),
)
@@ -2363,35 +2305,3 @@ async def test_callback_query_ignores_unauthorized_user_before_side_effects() ->
query.answer.assert_not_awaited()
query.message.edit_reply_markup.assert_not_awaited()
channel._handle_message.assert_not_awaited()
@pytest.mark.asyncio
async def test_callback_query_handles_inaccessible_message() -> None:
from telegram import Chat, InaccessibleMessage
channel = TelegramChannel(
TelegramConfig(enabled=True, token="123:abc", allow_from=["*"], inline_keyboards=True),
MessageBus(),
)
channel._handle_message = AsyncMock()
channel._start_typing = lambda _chat_id: None
query = SimpleNamespace(
id="cb_inaccessible",
data="Yes",
answer=AsyncMock(),
message=InaccessibleMessage(
chat=Chat(id=123, type="private"),
message_id=456,
),
)
update = SimpleNamespace(
callback_query=query,
effective_user=SimpleNamespace(id=12345, username="alice", first_name="Alice"),
)
await channel._on_callback_query(update, None)
query.answer.assert_awaited_once()
channel._handle_message.assert_awaited_once()
assert channel._handle_message.await_args.kwargs["chat_id"] == "123"
+2 -2
View File
@@ -1,7 +1,7 @@
"""Telegram setup validation owned by the channel package."""
import re
from typing import Any, cast
from typing import Any
from urllib.parse import urlparse
import httpx
@@ -39,7 +39,7 @@ def _get_me(token: str, proxy: str | None) -> dict[str, Any]:
response = client.get(f"https://api.telegram.org/bot{token}/getMe")
response.raise_for_status()
data = response.json()
return cast(dict[str, Any], data) if isinstance(data, dict) else {}
return data if isinstance(data, dict) else {}
def validate(values: dict[str, Any], _context: ChannelValidationContext) -> dict[str, Any]:
+9 -9
View File
@@ -11,7 +11,7 @@ import re
import socket
import ssl
from datetime import UTC, datetime
from typing import Any, cast
from typing import Any
import httpx
@@ -76,7 +76,7 @@ def validate_channel_config(
allow_local_service_access=config.tools.webui_allow_local_service_access,
)
custom_payload = setup_spec.validator(values, context)
if cast(object, custom_payload) is not None:
if custom_payload is not None:
payload = dict(custom_payload)
payload.setdefault("checks", [])
payload.setdefault("missing_fields", [])
@@ -116,7 +116,7 @@ def _channel_config(
if hasattr(section, "model_dump"):
return dict(section.model_dump(mode="json", by_alias=True))
if isinstance(section, dict):
return dict(cast(dict[str, Any], section))
return dict(section)
return {}
@@ -130,9 +130,9 @@ def _merge_form_values(
merged = dict(values)
prefix = f"channels.{name}."
spec = setup_spec
secrets: frozenset[str] = spec.secrets if spec is not None else frozenset()
secrets = spec.secrets if spec is not None else frozenset()
for raw_key, raw_value in raw_values.items():
if not raw_key:
if not isinstance(raw_key, str) or not raw_key:
continue
field = raw_key[len(prefix):] if raw_key.startswith(prefix) else raw_key
if field in secrets and not _str(raw_value):
@@ -281,7 +281,7 @@ def _assign(values: dict[str, Any], field: str, value: Any) -> None:
if not isinstance(current, dict):
current = {}
target[part] = current
target = cast(dict[str, Any], current)
target = current
target[parts[-1]] = value
@@ -290,7 +290,7 @@ def _get(values: dict[str, Any], field: str) -> Any:
for part in field.split("."):
if not isinstance(target, dict):
return None
target = cast(dict[str, Any], target).get(part)
target = target.get(part)
return target
@@ -346,7 +346,7 @@ def _http_get(url: str, *, headers: dict[str, str] | None = None) -> dict[str, A
response = client.get(url, headers=headers)
response.raise_for_status()
data = response.json()
return cast(dict[str, Any], data) if isinstance(data, dict) else {}
return data if isinstance(data, dict) else {}
def _http_post(url: str, *, headers: dict[str, str] | None = None) -> dict[str, Any]:
@@ -354,7 +354,7 @@ def _http_post(url: str, *, headers: dict[str, str] | None = None) -> dict[str,
response = client.post(url, headers=headers)
response.raise_for_status()
data = response.json()
return cast(dict[str, Any], data) if isinstance(data, dict) else {}
return data if isinstance(data, dict) else {}
def _probe_tcp(host: str, port: int, *, allow_loopback: bool = False) -> None:
+62 -274
View File
@@ -11,7 +11,7 @@ import uuid
from collections.abc import Callable
from contextlib import suppress
from pathlib import Path
from typing import Any, Self, TypeGuard, cast
from typing import Any, Self
from pydantic import Field, field_validator, model_validator
from websockets.asyncio.server import ServerConnection, serve, unix_serve
@@ -32,7 +32,6 @@ from nanobot.bus.outbound_events import (
)
from nanobot.bus.queue import MessageBus
from nanobot.channels.base import BaseChannel
from nanobot.command.builtin import builtin_command_starts_agent_turn
from nanobot.config.schema import Base
from nanobot.runtime_context import (
RUNTIME_CONTEXT_INPUT_META,
@@ -44,14 +43,7 @@ from nanobot.security.workspace_access import (
WorkspaceScopeError,
)
from nanobot.session.goal_state import goal_state_ws_blob
from nanobot.session.webui_turns import (
clear_websocket_turn_if_current,
mark_websocket_turn_transcript_persistence_failed,
register_queued_websocket_turn_if_idle,
websocket_turn_id,
websocket_turn_transcript_persistence_failed,
websocket_turn_wall_started_at,
)
from nanobot.session.webui_turns import websocket_turn_wall_started_at
from nanobot.webui.cli_apps_api import normalize_cli_app_mentions
from nanobot.webui.forking import handle_webui_fork_chat
from nanobot.webui.gateway_services import GatewayServices
@@ -65,12 +57,6 @@ from nanobot.webui.http_utils import (
query_first as _query_first,
)
from nanobot.webui.mcp_presets_api import normalize_mcp_preset_mentions
from nanobot.webui.metadata import (
WEBSOCKET_TURN_OWNER_METADATA_KEY,
WEBUI_SYSTEM_COMMAND_TURN_PREFIX,
WEBUI_TURN_METADATA_KEY,
)
from nanobot.webui.transcript import WEBUI_TRANSCRIPT_INCOMPLETE_KEY
from nanobot.webui.transcription_ws import webui_transcription_event
from nanobot.webui.websocket_logging import websockets_server_logger
@@ -192,13 +178,12 @@ def _parse_inbound_payload(raw: str) -> str | None:
return None
if text.startswith("{"):
try:
data = cast(object, json.loads(text))
data = json.loads(text)
except json.JSONDecodeError:
return text
if isinstance(data, dict):
payload = cast(dict[str, Any], data)
for key in ("content", "text", "message"):
value = payload.get(key)
value = data.get(key)
if isinstance(value, str) and value.strip():
return value
return None
@@ -211,7 +196,7 @@ def _parse_inbound_payload(raw: str) -> str | None:
_CHAT_ID_RE = re.compile(r"^[A-Za-z0-9_:-]{1,64}$")
def _is_valid_chat_id(value: Any) -> TypeGuard[str]:
def _is_valid_chat_id(value: Any) -> bool:
return isinstance(value, str) and _CHAT_ID_RE.match(value) is not None
@@ -226,16 +211,15 @@ def _parse_envelope(raw: str) -> dict[str, Any] | None:
if not text.startswith("{"):
return None
try:
data = cast(object, json.loads(text))
data = json.loads(text)
except json.JSONDecodeError:
return None
if not isinstance(data, dict):
return None
envelope = cast(dict[str, Any], data)
t = envelope.get("type")
t = data.get("type")
if not isinstance(t, str):
return None
return envelope
return data
def _is_websocket_upgrade(request: WsRequest) -> bool:
@@ -267,13 +251,13 @@ class WebSocketChannel(BaseChannel):
super().__init__(config, bus)
self.config: WebSocketConfig = config
# chat_id -> connections subscribed to it (fan-out target).
self._subs: dict[str, set[ServerConnection]] = {}
self._subs: dict[str, set[Any]] = {}
# connection -> chat_ids it is subscribed to (O(1) cleanup on disconnect).
self._conn_chats: dict[ServerConnection, set[str]] = {}
self._conn_chats: dict[Any, set[str]] = {}
# connection -> default chat_id for legacy frames that omit routing.
self._conn_default: dict[ServerConnection, str] = {}
self._conn_default: dict[Any, str] = {}
# Connections authenticated with a one-time token from /webui/bootstrap.
self._webui_connections: set[ServerConnection] = set()
self._webui_connections: set[Any] = set()
self._stop_event: asyncio.Event | None = None
self._server_task: asyncio.Task[None] | None = None
@@ -289,43 +273,15 @@ class WebSocketChannel(BaseChannel):
# -- Subscription bookkeeping -------------------------------------------
def _workspace_controls_available(self, connection: ServerConnection) -> bool:
def _workspace_controls_available(self, connection: Any) -> bool:
return self._http_router.workspace_controls_available(connection)
def _attach(self, connection: ServerConnection, chat_id: str) -> None:
def _attach(self, connection: Any, chat_id: str) -> None:
"""Idempotently subscribe *connection* to *chat_id*."""
self._subs.setdefault(chat_id, set()).add(connection)
self._conn_chats.setdefault(connection, set()).add(chat_id)
async def send_webui_protocol_error(
self,
connection: ServerConnection,
detail: str,
) -> None:
"""Send a stable protocol error from a WebUI-owned orchestration helper."""
await self._send_event(connection, "error", detail=detail)
async def attach_webui_fork(
self,
connection: ServerConnection,
*,
fork_id: str,
fork_key: str,
) -> None:
"""Attach and hydrate a newly created WebUI chat fork."""
scope = self._workspaces.scope_for_session_key(fork_key)
self._attach(connection, fork_id)
await self._send_event(connection, "attached", chat_id=fork_id)
await self._send_event(
connection,
"session_updated",
chat_id=fork_id,
scope="metadata",
workspace_scope=scope.payload(),
)
await self._hydrate_after_subscribe(fork_id)
def _cleanup_connection(self, connection: ServerConnection) -> None:
def _cleanup_connection(self, connection: Any) -> None:
"""Remove *connection* from every subscription set; safe to call multiple times."""
chat_ids = self._conn_chats.pop(connection, set())
for cid in chat_ids:
@@ -348,11 +304,10 @@ class WebSocketChannel(BaseChannel):
if self.gateway.session_manager is None:
return
row = self.gateway.session_manager.read_session_file(f"websocket:{chat_id}")
row_data = row if isinstance(row, dict) else {}
meta = row_data.get("metadata", {})
meta = row.get("metadata", {}) if isinstance(row, dict) else {}
if not isinstance(meta, dict):
meta = {}
blob = goal_state_ws_blob(cast(dict[str, Any], meta))
blob = goal_state_ws_blob(meta)
if not blob.get("active"):
return
await self.send_goal_state(chat_id, blob)
@@ -362,24 +317,14 @@ class WebSocketChannel(BaseChannel):
t0 = websocket_turn_wall_started_at(chat_id)
if t0 is None:
return
await self.send_goal_status(
chat_id,
"running",
started_at=t0,
turn_id=websocket_turn_id(chat_id),
)
await self.send_goal_status(chat_id, "running", started_at=t0)
async def _hydrate_after_subscribe(self, chat_id: str) -> None:
"""Replay persisted or actively running per-chat state after subscribe."""
await self._maybe_push_active_goal_state(chat_id)
await self._maybe_push_turn_run_wall_clock(chat_id)
async def _send_event(
self,
connection: ServerConnection,
event: str,
**fields: Any,
) -> None:
async def _send_event(self, connection: Any, event: str, **fields: Any) -> None:
"""Send a control event (attached, error, ...) to a single connection."""
payload: dict[str, Any] = {"event": event}
payload.update(fields)
@@ -414,7 +359,7 @@ class WebSocketChannel(BaseChannel):
# -- HTTP dispatch ------------------------------------------------------
async def _dispatch_http(self, connection: ServerConnection, request: WsRequest) -> Any:
async def _dispatch_http(self, connection: Any, request: WsRequest) -> Any:
"""Route an inbound HTTP request to the HTTP handler or WS upgrade."""
got, query = _parse_request_path(request.path)
@@ -431,11 +376,7 @@ class WebSocketChannel(BaseChannel):
# Everything else goes to the HTTP handler
return await self._http_router.dispatch(connection, request)
def _authorize_websocket_handshake(
self,
connection: ServerConnection,
query: dict[str, list[str]],
) -> Any:
def _authorize_websocket_handshake(self, connection: Any, query: dict[str, list[str]]) -> Any:
supplied = _query_first(query, "token")
static_token = self.config.token.strip()
@@ -455,7 +396,7 @@ class WebSocketChannel(BaseChannel):
self._consume_issued_token(connection, supplied)
return None
def _consume_issued_token(self, connection: ServerConnection, token: str) -> bool:
def _consume_issued_token(self, connection: Any, token: str) -> bool:
audience = self._tokens.take_issued_token_audience(token)
if audience == "webui":
self._webui_connections.add(connection)
@@ -550,7 +491,7 @@ class WebSocketChannel(BaseChannel):
self._server_task = asyncio.create_task(runner())
await self._server_task
async def _connection_loop(self, connection: ServerConnection) -> None:
async def _connection_loop(self, connection: Any) -> None:
request = connection.request
path_part = request.path if request else "/"
_, query = _parse_request_path(path_part)
@@ -615,7 +556,7 @@ class WebSocketChannel(BaseChannel):
async def _dispatch_envelope(
self,
connection: ServerConnection,
connection: Any,
client_id: str,
envelope: dict[str, Any],
) -> None:
@@ -692,40 +633,17 @@ class WebSocketChannel(BaseChannel):
if not _is_valid_chat_id(cid):
await self._send_event(connection, "error", detail="invalid chat_id")
return
raw_turn_id = envelope.get("turn_id")
turn_id = raw_turn_id if isinstance(raw_turn_id, str) and raw_turn_id else None
rejection_fields = {
"chat_id": cid,
**({"turn_id": turn_id} if turn_id else {}),
}
# The allowlist can change while an authenticated websocket stays
# open. Reject the exact application turn before hydration,
# transcript persistence, or an acceptance ACK; BaseChannel's
# silent authorization return must not look like successful ingress.
if not self.is_allowed(client_id):
await self._send_event(
connection,
"error",
detail="access_denied",
**rejection_fields,
)
return
if not isinstance(content, str):
await self._send_event(
connection,
"error",
detail="missing content",
**rejection_fields,
)
await self._send_event(connection, "error", detail="missing content")
return
message_rejection = self._ingress.validate_text(content)
if message_rejection is not None:
await self._send_event(
connection,
"error",
chat_id=cid,
detail="message_rejected",
reason=message_rejection,
**rejection_fields,
)
return
@@ -738,28 +656,21 @@ class WebSocketChannel(BaseChannel):
"error",
detail="attachment_rejected",
reason="malformed",
**rejection_fields,
)
return
media_paths, reason = self._media.store_inbound_attachments(cast(list[Any], raw_media))
media_paths, reason = self._media.store_inbound_attachments(raw_media)
if reason is not None:
await self._send_event(
connection,
"error",
detail="attachment_rejected",
reason=reason,
**rejection_fields,
)
return
# Allow media-only turns (content may be empty when attachments are present).
if not content.strip() and not media_paths:
await self._send_event(
connection,
"error",
detail="missing content",
**rejection_fields,
)
await self._send_event(connection, "error", detail="missing content")
return
# Auto-attach on first use so clients can one-shot without a separate attach.
self._attach(connection, cid)
@@ -775,23 +686,10 @@ class WebSocketChannel(BaseChannel):
controls_available=self._workspace_controls_available(connection),
),
chat_id=cid,
turn_id=turn_id,
)
if scope is None:
return
# Hydration and scope resolution can yield. Re-check immediately
# before transcript/bus mutation so a mid-flight revocation cannot
# fall through BaseChannel's silent deny and still receive an ACK.
if not self.is_allowed(client_id):
await self._send_event(
connection,
"error",
detail="access_denied",
**rejection_fields,
)
return
metadata: dict[str, Any] = {"remote": getattr(connection, "remote_address", None)}
if envelope.get("webui") is True:
metadata["webui"] = True
@@ -804,58 +702,38 @@ class WebSocketChannel(BaseChannel):
metadata["mcp_presets"] = mcp_presets
metadata[WORKSPACE_SCOPE_METADATA_KEY] = scope.metadata()
self._workspaces.persist_scope(cid, scope)
is_webui = metadata.get("webui") is True
queued_owner = None
if is_webui and builtin_command_starts_agent_turn(content):
queued_owner = register_queued_websocket_turn_if_idle(cid, turn_id)
if queued_owner is not None:
metadata[WEBSOCKET_TURN_OWNER_METADATA_KEY] = queued_owner
accepted = False
try:
if is_webui:
self._transcripts.append_user_message(
cid,
content,
metadata=metadata,
media_paths=media_paths or None,
cli_apps=cli_apps or None,
mcp_presets=mcp_presets or None,
)
if is_webui and connection in self._webui_connections:
quote = webui_quote_runtime_context({
WEBUI_QUOTE_METADATA: envelope.get("quoted_context"),
})
if quote is not None:
metadata[RUNTIME_CONTEXT_INPUT_META] = [quote]
await self._handle_message(
sender_id=client_id,
chat_id=cid,
content=content,
media=media_paths or None,
if metadata.get("webui") is True and self.is_allowed(client_id):
self._transcripts.append_user_message(
cid,
content,
metadata=metadata,
is_dm=False,
)
accepted = True
finally:
if not accepted and queued_owner is not None:
clear_websocket_turn_if_current(cid, queued_owner)
if is_webui and turn_id:
await self._send_event(
connection,
"message_accepted",
chat_id=cid,
turn_id=turn_id,
media_paths=media_paths or None,
cli_apps=cli_apps or None,
mcp_presets=mcp_presets or None,
)
if metadata.get("webui") is True and connection in self._webui_connections:
quote = webui_quote_runtime_context({
WEBUI_QUOTE_METADATA: envelope.get("quoted_context"),
})
if quote is not None:
metadata[RUNTIME_CONTEXT_INPUT_META] = [quote]
await self._handle_message(
sender_id=client_id,
chat_id=cid,
content=content,
media=media_paths or None,
metadata=metadata,
is_dm=False,
)
return
await self._send_event(connection, "error", detail=f"unknown type: {t!r}")
async def _workspace_scope_or_error(
self,
connection: ServerConnection,
connection: Any,
resolver: Callable[[], Any],
*,
chat_id: str | None = None,
turn_id: str | None = None,
) -> Any | None:
try:
return resolver()
@@ -866,7 +744,6 @@ class WebSocketChannel(BaseChannel):
detail="workspace_scope_rejected",
reason=exc.message,
**({"chat_id": chat_id} if chat_id else {}),
**({"turn_id": turn_id} if turn_id else {}),
)
return None
@@ -882,8 +759,7 @@ class WebSocketChannel(BaseChannel):
try:
await self._server_task
except asyncio.CancelledError:
current_task = asyncio.current_task()
if current_task is not None and current_task.cancelling():
if asyncio.current_task() and asyncio.current_task().cancelling():
raise
self.logger.debug("server task was already cancelled during shutdown")
except Exception as e:
@@ -895,13 +771,7 @@ class WebSocketChannel(BaseChannel):
self._webui_connections.clear()
self._tokens.clear()
async def _safe_send_to(
self,
connection: ServerConnection,
raw: str,
*,
label: str = "",
) -> None:
async def _safe_send_to(self, connection: Any, raw: str, *, label: str = "") -> None:
"""Send a raw frame to one connection, cleaning up on ConnectionClosed."""
try:
await connection.send(raw)
@@ -912,37 +782,6 @@ class WebSocketChannel(BaseChannel):
self.logger.exception("send failed{}", label)
raise
def _persist_turn_transcript_event(
self,
chat_id: str,
event: dict[str, Any],
*,
metadata: dict[str, Any] | None,
phase: str,
include_source: bool = False,
transcript_overrides: dict[str, Any] | None = None,
) -> bool:
"""Persist one canonical turn event and retain unsafe owners on failure."""
persisted = self._transcripts.prepare_and_append(
chat_id,
event,
metadata=metadata,
phase=phase,
include_source=include_source,
transcript_overrides=transcript_overrides,
)
if (
not persisted
and phase in {"answer", "complete"}
and (metadata or {}).get("webui") is True
):
owner = (metadata or {}).get(WEBSOCKET_TURN_OWNER_METADATA_KEY)
mark_websocket_turn_transcript_persistence_failed(
chat_id,
owner if isinstance(owner, str) else None,
)
return persisted
async def send(self, msg: OutboundMessage) -> None:
event = outbound_event_from_message(msg)
progress_event = event if isinstance(event, ProgressEvent) else None
@@ -979,47 +818,23 @@ class WebSocketChannel(BaseChannel):
await self.send_goal_state(msg.chat_id, event.goal_state or {"active": False})
return
if isinstance(event, GoalStatusEvent):
turn_id = (msg.metadata or {}).get(WEBUI_TURN_METADATA_KEY)
current_turn_id = turn_id if isinstance(turn_id, str) else None
turn_owner = (msg.metadata or {}).get(WEBSOCKET_TURN_OWNER_METADATA_KEY)
current_turn_owner = turn_owner if isinstance(turn_owner, str) else None
try:
if conns and event.status in ("running", "idle"):
if conns:
if event.status in ("running", "idle"):
await self.send_goal_status(
msg.chat_id,
event.status,
started_at=event.started_at,
turn_id=current_turn_id,
)
finally:
if event.status == "idle":
# Cancellation/direct runs may have no turn_end, so idle is
# still terminal. A failed canonical completion write is
# the one case that must remain pending for safe resume.
clear_websocket_turn_if_current(
msg.chat_id,
current_turn_owner,
preserve_persistence_failure=True,
)
return
# Signal that the agent has fully finished processing the current turn.
if isinstance(event, TurnEndEvent):
turn_id = (msg.metadata or {}).get(WEBUI_TURN_METADATA_KEY)
session_update_scope = (
"metadata"
if isinstance(turn_id, str)
and turn_id.startswith(WEBUI_SYSTEM_COMMAND_TURN_PREFIX)
else "thread"
)
turn_owner = (msg.metadata or {}).get(WEBSOCKET_TURN_OWNER_METADATA_KEY)
await self.send_turn_end(
msg.chat_id,
latency_ms=event.latency_ms,
goal_state=event.goal_state,
metadata=msg.metadata,
turn_owner=turn_owner if isinstance(turn_owner, str) else None,
)
await self.send_session_updated(msg.chat_id, scope=session_update_scope)
await self.send_session_updated(msg.chat_id, scope="thread")
return
if isinstance(event, SessionUpdatedEvent):
if conns:
@@ -1069,7 +884,7 @@ class WebSocketChannel(BaseChannel):
elif progress_event:
payload["kind"] = "progress"
phase = "activity" if payload.get("kind") in ("tool_hint", "progress") else "answer"
self._persist_turn_transcript_event(
self._transcripts.prepare_and_append(
msg.chat_id,
payload,
metadata=msg.metadata,
@@ -1107,7 +922,7 @@ class WebSocketChannel(BaseChannel):
}
if stream_id is not None:
body["stream_id"] = stream_id
self._persist_turn_transcript_event(
self._transcripts.prepare_and_append(
chat_id,
body,
metadata=meta,
@@ -1135,7 +950,7 @@ class WebSocketChannel(BaseChannel):
}
if stream_id is not None:
body["stream_id"] = stream_id
self._persist_turn_transcript_event(
self._transcripts.prepare_and_append(
chat_id,
body,
metadata=meta,
@@ -1159,7 +974,7 @@ class WebSocketChannel(BaseChannel):
"chat_id": chat_id,
"edits": edits,
}
self._persist_turn_transcript_event(
self._transcripts.prepare_and_append(
chat_id,
payload,
metadata=metadata,
@@ -1180,18 +995,13 @@ class WebSocketChannel(BaseChannel):
stream_id: str | None = None,
stream_end: bool = False,
resuming: bool = False,
merge_next: bool = False,
) -> None:
conns = list(self._subs.get(chat_id, ()))
meta = metadata or {}
stream_key = (chat_id, str(stream_id or ""))
if stream_end:
body: dict[str, Any] = {"event": "stream_end", "chat_id": chat_id}
buffered = (
self._stream_text_buffers.setdefault(stream_key, [])
if merge_next
else self._stream_text_buffers.pop(stream_key, [])
)
buffered = self._stream_text_buffers.pop(stream_key, [])
if delta:
buffered.append(delta)
full_text = "".join(buffered)
@@ -1209,14 +1019,11 @@ class WebSocketChannel(BaseChannel):
body["stream_id"] = stream_id
if stream_end and resuming:
body["resuming"] = True
if stream_end and merge_next:
body["merge_next"] = True
self._persist_turn_transcript_event(
self._transcripts.prepare_and_append(
chat_id,
body,
metadata=meta,
phase="answer",
include_source=True,
)
raw = json.dumps(body, ensure_ascii=False)
if not conns:
@@ -1231,7 +1038,6 @@ class WebSocketChannel(BaseChannel):
*,
goal_state: dict[str, Any] | None = None,
metadata: dict[str, Any] | None = None,
turn_owner: str | None = None,
) -> None:
"""Signal that the agent has fully finished processing the current turn."""
conns = list(self._subs.get(chat_id, ()))
@@ -1240,27 +1046,12 @@ class WebSocketChannel(BaseChannel):
body["latency_ms"] = int(latency_ms)
if goal_state is not None:
body["goal_state"] = goal_state
canonical_webui_turn = (metadata or {}).get("webui") is True
prior_persistence_failure = (
canonical_webui_turn
and websocket_turn_transcript_persistence_failed(chat_id, turn_owner)
)
persisted = self._persist_turn_transcript_event(
self._transcripts.prepare_and_append(
chat_id,
body,
metadata=metadata,
phase="complete",
transcript_overrides=(
{WEBUI_TRANSCRIPT_INCOMPLETE_KEY: True}
if prior_persistence_failure
else None
),
)
if persisted:
# A successful completion either has a complete transcript or now
# carries a durable incomplete marker. The HTTP replay path can
# recover the latter from session history after a gateway restart.
clear_websocket_turn_if_current(chat_id, turn_owner)
raw = json.dumps(body, ensure_ascii=False)
if not conns:
return
@@ -1283,7 +1074,6 @@ class WebSocketChannel(BaseChannel):
status: str,
*,
started_at: float | None = None,
turn_id: str | None = None,
) -> None:
"""Notify subscribed clients that a turn started or finished (wall-clock hint)."""
conns = list(self._subs.get(chat_id, ()))
@@ -1296,8 +1086,6 @@ class WebSocketChannel(BaseChannel):
}
if status == "running" and started_at is not None:
body["started_at"] = started_at
if turn_id:
body["turn_id"] = turn_id
raw = json.dumps(body, ensure_ascii=False)
for connection in conns:
await self._safe_send_to(connection, raw, label=" goal_status ")
File diff suppressed because it is too large Load Diff
@@ -19,7 +19,6 @@ from nanobot.channels.websocket.runtime import (
WebSocketChannel,
WebSocketConfig,
)
from nanobot.session import webui_turns as wth
from nanobot.webui.gateway_services import build_gateway_services
@@ -60,19 +59,6 @@ def _make_channel() -> WebSocketChannel:
return channel
@pytest.fixture(autouse=True)
def isolate_websocket_turn_state() -> None:
wth._WEBSOCKET_ACTIVE_TURNS.clear()
wth._WEBSOCKET_TURN_WALL_STARTED_AT.clear()
wth._WEBSOCKET_TURN_IDS.clear()
wth._WEBSOCKET_TURN_OWNERS.clear()
yield
wth._WEBSOCKET_ACTIVE_TURNS.clear()
wth._WEBSOCKET_TURN_WALL_STARTED_AT.clear()
wth._WEBSOCKET_TURN_IDS.clear()
wth._WEBSOCKET_TURN_OWNERS.clear()
# -- max_message_bytes bump ----------------------------------------------------
@@ -108,28 +94,6 @@ async def test_message_without_media_backward_compatible() -> None:
assert call.kwargs["media"] is None
@pytest.mark.asyncio
async def test_webui_message_acceptance_echoes_turn_id() -> None:
channel = _make_channel()
mock_conn = AsyncMock()
envelope = {
"type": "message",
"chat_id": "abc123",
"content": "hello",
"webui": True,
"turn_id": "turn-accepted",
}
await channel._dispatch_envelope(mock_conn, "client-1", envelope)
channel._handle_message.assert_awaited_once()
assert json.loads(mock_conn.send.await_args.args[0]) == {
"event": "message_accepted",
"chat_id": "abc123",
"turn_id": "turn-accepted",
}
@pytest.mark.asyncio
async def test_message_text_policy_is_independent_from_transport_limit() -> None:
channel = _make_channel()
@@ -138,7 +102,6 @@ async def test_message_text_policy_is_independent_from_transport_limit() -> None
"type": "message",
"chat_id": "abc123",
"content": "" * 22_000,
"turn_id": "turn-text-policy",
}
await channel._dispatch_envelope(mock_conn, "client-1", envelope)
@@ -150,7 +113,6 @@ async def test_message_text_policy_is_independent_from_transport_limit() -> None
"chat_id": "abc123",
"detail": "message_rejected",
"reason": "text_too_large",
"turn_id": "turn-text-policy",
}
@@ -273,7 +235,6 @@ async def test_message_rejected_when_more_than_four_images(tmp_path) -> None:
"chat_id": "abc123",
"content": "hi",
"media": [{"data_url": _tiny_png_data_url()}] * 5,
"turn_id": "turn-attachments",
}
with patch(
@@ -285,10 +246,8 @@ async def test_message_rejected_when_more_than_four_images(tmp_path) -> None:
mock_conn.send.assert_awaited_once()
err = json.loads(mock_conn.send.call_args[0][0])
assert err["event"] == "error"
assert err["chat_id"] == "abc123"
assert err["detail"] == "attachment_rejected"
assert err["reason"] == "too_many_images"
assert err["turn_id"] == "turn-attachments"
@pytest.mark.asyncio

Some files were not shown because too many files have changed in this diff Show More