chengyongru 86858cfcb8 fix(image-generation): let LLM deliver images via message tool instead of runtime media attachment ...

The runtime media-attachment mechanism was broken for streaming channels
(e.g. WebSocket): the _streamed flag caused _send_once to skip the final
OutboundMessage that carried generated media, so images were never delivered.

Rather than adding complex coordination between streaming and media delivery,
delegate image delivery to the LLM: after generate_image returns artifact
paths, the next_step prompt now instructs the LLM to call the message tool
with the paths in the media parameter. This works uniformly across all
channels, streaming or not.

Remove generated_media from TurnContext, _assemble_outbound, and _state_save.
Update prompts in identity.md, SKILL.md, message tool description, and
artifacts.py to reflect the new flow.

2026-05-19 00:42:56 +08:00

..

agent

fix(image-generation): let LLM deliver images via message tool instead of runtime media attachment

2026-05-19 00:42:56 +08:00

channels

feat(webui): persist agent activity events

2026-05-17 23:51:52 +08:00

cli

Merge PR #3877: feat(webui+agent): optimize streaming, activity rendering, and runtime sync

2026-05-18 02:04:36 +08:00

command

feat(goal): /goal command & long-running tasks (long_task)

2026-05-16 01:14:11 +08:00

config

fix(config): reduce max_tokens and context_window_tokens in schema

2026-05-15 17:19:47 +00:00

cron

feat(tools): introduce plugin-based tool discovery and runtime context protocol

2026-05-12 11:28:20 +08:00

heartbeat

fix(heartbeat): prevent internal reasoning leaks and finalization fallback in delivery

2026-04-27 18:14:13 +08:00

pairing

docs(pairing): address reviewer comments — comments, error msg, __all__ test

2026-05-15 15:46:44 +08:00

providers

feat(image-generation): add Gemini provider support

2026-05-18 15:28:58 +08:00

security

fix(security): add ssrfWhitelist config to unblock Tailscale/CGNAT (#2669)

2026-04-04 19:43:18 +08:00

session

fix(agent): align LLM wall timeout with sustained goals for main + subagents

2026-05-16 16:33:49 +08:00

tools

refactor(image-generation): introduce provider registry to eliminate manual wiring

2026-05-18 17:20:54 +08:00

utils

fix(image-generation): let LLM deliver images via message tool instead of runtime media attachment

2026-05-19 00:42:56 +08:00

test_api_attachment.py

fix: two bugs in document extraction pipeline

2026-04-14 13:15:04 +00:00

test_api_stream.py

Fix API stream lifecycle for tool-backed requests

2026-05-01 19:42:52 +08:00

test_build_status.py

fix(status): correct context percentage calculation and sync consolidator

2026-04-16 20:30:39 +08:00

test_context_documents.py

fix: two bugs in document extraction pipeline

2026-04-14 13:15:04 +00:00

test_docker.sh

docs: add core agent line count script and update README with real-time stats

2026-02-06 07:28:39 +00:00

test_document_parsing.py

fix(utils): recurse into PPTX groups and tables when extracting text (#3250)

2026-04-18 12:30:42 +08:00

test_msteams.py

chore: remove dead code identified by vulture + coverage cross-validation

2026-05-12 20:52:48 +08:00

test_nanobot_facade.py

refactor(tools): remove GlobTool

2026-05-15 17:19:00 +08:00

test_openai_api.py

feat(api): add SSE streaming for /v1/chat/completions Wire up the existing on_stream/on_stream_end callbacks from process_direct() to emit OpenAI-compatible SSE chunks when stream=true. Non-streaming path is untouched.

2026-04-17 01:54:49 +08:00

test_package_version.py

fix(version): fall back to pyproject in source checkouts

2026-04-08 23:47:36 +08:00

test_tool_contextvars.py

feat(tools): introduce plugin-based tool discovery and runtime context protocol

2026-05-12 11:28:20 +08:00

test_truncate_text_shadowing.py

fix(agent): avoid truncate_text name shadowing

2026-04-10 17:36:31 +08:00