17 Commits

Author SHA1 Message Date
chengyongru
584072cf63 refactor: restrict fallback_models to preset-only and clean up provider factory
- Restrict fallback_models to only reference preset names in model_presets.
- Add schema validation to reject unknown preset names in fallback_models.
- Remove build_provider_for_model() since bare model fallback is no longer supported.
- Simplify make_provider_factory() to only look up presets by name.
- Update onboard UI to remove "Add custom model" option from fallback chain.
- Update tests to use preset names instead of bare model strings in fallback chains.
- Fix test imports referencing deleted _make_provider function.
2026-05-08 20:16:06 +08:00
Tim O'Brien
7d3337a98e fix: wire toolHintMaxLength through AgentLoop constructors
The config field was added but never passed from config to AgentLoop.
The value was always falling back to the default (40) regardless of
what was set in config.json.

Now passes tool_hint_max_length through all AgentLoop() call sites:
- nanobot/nanobot.py (main bot)
- nanobot/cli/commands.py (CLI agent, dev, webui commands)

Also adds documentation in docs/configuration.md.
2026-05-06 13:45:47 +08:00
chengyongru
3baa869fdb refactor(agent): simplify subagent concurrency with rejection over semaphore
Replace the asyncio.Semaphore queueing approach with a simple count
check in SpawnTool.execute(). When the concurrency limit is reached,
the tool returns an error string so the agent can perceive the reason
and adjust its behavior instead of silently queueing.

- Remove max_concurrent_subagents parameter threading through
  AgentLoop, commands.py, and nanobot.py
- SubagentManager reads the limit directly from AgentDefaults
- SpawnTool checks get_running_count() before calling spawn()
- Simplify tests to verify rejection behavior
2026-05-05 21:17:15 +08:00
MrBob
2103cd5602 feat(agent): limit subagent concurrency 2026-05-05 21:17:15 +08:00
Xubin Ren
861fbb0dde fix(provider): correct LongCat OpenAI base URL
Use the SDK-ready /v1 base so LongCat chat completions hit the documented endpoint.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-02 01:52:04 +08:00
moranfong
051037ff08 feat(provider): add LongCat via OpenAI-compatible backend 2026-05-02 01:52:04 +08:00
Xubin Ren
306958d6e6 add native Bedrock Converse provider
Made-with: Cursor
2026-05-01 18:52:03 +08:00
hanyuanling
0b111a0e0c fix(channels): support per-channel progress controls 2026-04-29 16:43:09 +08:00
chengyongru
28f9bbff31 feat(web_search): add olostep provider
Adds Olostep (https://www.olostep.com) as an optional web_search backend
using the official olostep Python SDK (client.answers.create()).

Changes:
- pyproject.toml: adds olostep>=0.1.0 optional dependency
- schema.py: adds olostep to provider comment in WebSearchConfig
- web.py: adds _search_olostep() with lazy import and provider branching
- docs/configuration.md: documents Olostep setup under web search config
- tests: unit tests for the new provider

Backward compatible: existing users see no behavior change unless they
opt into provider: "olostep". No hard dependency at runtime path.

Co-authored-by: umerkay <umerkk164@gmail.com>
2026-04-28 19:09:38 +08:00
Xubin Ren
278ef22776 docs(config): document provider extra body
Show how to configure OpenAI-compatible request body extensions such as sampling and chat template parameters.

Made-with: Cursor
2026-04-28 15:56:13 +08:00
Xubin Ren
18432c313f Merge origin/main into web-tools
Made-with: Cursor
2026-04-28 07:17:05 +00:00
Celina Hanouti
2b455b1e14 feat(providers): add Hugging Face inference provider 2026-04-28 14:55:28 +08:00
Mizarka
4c25b739b5
docs: add new web tool settings 2026-04-22 09:42:03 +00:00
Mizarka
ec2f0ccfdb
feat(web-tools): add configurable User-Agent
Assisted-by: Jo'Zahir:Qwen3.6-35B-A3B
2026-04-22 09:11:57 +00:00
k
123d69bfb7 fix: allow specifying transcription language 2026-04-22 12:41:32 +08:00
Xubin Ren
6c24f24e9e feat(models): add support for kimi-k2.6 with temperature override and update documentation 2026-04-20 18:18:06 +00:00
Xubin Ren
8ff7b56cb2 docs: refactor README into a docs-first landing page 2026-04-19 19:25:05 +08:00