Commit Graph

1349 Commits

Author SHA1 Message Date
afjcjsbx a7e52e8a25 fix(agent): drain scoped follow-up queue when pending stop skips turn startup 2026-05-05 19:24:15 +02:00
afjcjsbx d63430ab33 fix(agent): don't arm pending stop when /stop targets idle session 2026-05-04 13:10:02 +02:00
afjcjsbx 7a1f5fe8b9 fix test 2026-05-04 09:06:39 +02:00
afjcjsbx a0245c7b02 feat(agent): stop command 2026-05-04 08:41:29 +02:00
afjcjsbx f3ef7090c5 feat(agent): stop command 2026-05-04 08:41:17 +02:00
Mauro be67aed4dc Merge pull request #2677 from alexhoshina/feat/runtime-events-plan
Feat/runtime events
2026-05-03 23:15:25 +02:00
Mauro 828a7cba70 Merge pull request #2681 from afjcjsbx/fix/gemini-mcp-schema-sanitization
fix(mcp): sanitize MCP tool schemas for Gemini function calling
2026-05-03 20:25:35 +02:00
Mauro 490d90749c Merge pull request #2717 from LiusCraft/feat/deepseek-vision-unsupported-error
feat: add DeepSeek vision unsupported error detection
2026-05-03 20:24:56 +02:00
Mauro 272dee3fca Merge pull request #2669 from david1gp/fix/network-error-retry
feat(agent): add network error retry with configurable max retries and backoff
2026-05-03 20:18:18 +02:00
LC dbf5d9ce1f fix(seahorse): persist reasoning_content in sqlite history (#2707)
* fix(seahorse): persist reasoning_content in sqlite history

* fix(openai_compat): clarify DeepSeek reasoning replay rules

* style(seahorse): format files of seahorse

* fix(openai_compat): cover DeepSeek replay requirements

* fix(seahorse): repair missing reasoning_content during bootstrap

* fix(seahorse): repair reasoning_content on bootstrap prefix
2026-04-30 16:07:38 +08:00
Guoguo 5db008f384 fix(channels): dismiss tool feedback animation when turn ends via ResponseHandled (#2713)
* fix(channels): dismiss tool feedback animation when turn ends via ResponseHandled

When a tool sets ResponseHandled=true (e.g., send_file), the turn ends
without producing a final assistant response. This meant no outbound
message triggered FinalizeToolFeedbackMessage, leaving the animation
goroutine running indefinitely — editing the Feishu card every 3 seconds
with "." / ".." suffixes long after the tool had finished.

Fix: call DismissToolFeedback at "Tool output satisfied delivery" so the
tracker is cleared and the animation goroutine is stopped immediately.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(adapters): add DismissToolFeedback to channelManagerAdapter

The adapter must implement the new interface method added in the
previous commit, otherwise the package fails to compile.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(channels): pass InboundContext to DismissToolFeedback for topic-aware keys

Telegram forum topics use scoped tracker keys like "chatID/topicID",
resolved via ToolFeedbackMessageChatID with the InboundContext. The
previous nil context caused the lookup to fall back to the raw chatID,
missing the topic-scoped entry and leaving the animation goroutine
orphaned in forum-topic conversations.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* style: wrap long function signatures for golines

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-30 11:17:55 +08:00
Guoguo cb1e1a3595 fix(feishu): fix image download with API fallback and post image support (#2708)
* fix(feishu): fix image download with API fallback and post image support

- Add Image.Get API fallback when MessageResource.Get fails (different
  permission scope: im:resource vs im:message:readonly)
- Extract and download images from post (rich text) messages
- Extract images from interactive card messages
- Deduplicate post image keys across locales
- Add comprehensive tests for new helpers

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat(media): add image path tags alongside base64 for LLM file access

Images are still base64-encoded into msg.Media for multimodal LLMs,
but now also get [image:path] tags injected into message content so
the LLM knows the local file path for save/forward operations.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor(media): only auto-inject images for tool results, not user messages

Channel-received images (role=user) now get path tags only, letting
the LLM decide whether to view via load_image or just operate on
the file. Tool result images (role=tool, e.g. load_image) are
base64-encoded into a synthetic user message appended after the tool
message, since many LLM APIs don't support image_url in tool messages.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(media): preserve tool-message ordering for multi-tool-call scenarios

Move synthetic user message (carrying base64 tool images) to after the
entire contiguous tool-message block instead of immediately after each
tool message. This preserves the assistant→tool→tool ordering required
by OpenAI-compatible APIs.

Also fix load_image to use generic [image: photo] placeholder so
injectPathTags can properly replace it with the actual path.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(test): update load_image test for [image: photo] placeholder

The test was checking ForLLM for the media:// ref, but load_image now
emits the generic [image: photo] placeholder instead.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(media): match all channel image placeholders in injectPathTags

Different channels emit different placeholder formats — Telegram/Feishu
use [image: photo], WeCom/WeChat/Line use bare [image], QQ/Discord use
[image: <filename>]. The previous string-match code only handled
[image: photo], so for the other channels the path tag was appended as
a duplicate, producing content like "[image] [image:/path]".

Switch to per-type regex that matches all generic placeholder shapes
while leaving path tags ([image:/path]) untouched. Also fixes the same
issue for [audio], [video], [file] tags. Added test coverage for the
various placeholder shapes.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(media): skip path tag append for JSON content (Feishu cards/posts)

When content is structured JSON (interactive cards, post messages),
injectPathTags now skips the fallback append — only placeholder
replacement is attempted. This prevents corrupting JSON payloads
like {"schema":"2.0",...} with appended [image:/path] tags.

Adds looksLikeJSON() helper and three test cases covering JSON
objects, arrays, and an end-to-end resolveMediaRefs scenario with
Feishu card content.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(media): prepend path tags for JSON content, narrow looksLikeJSON

Two fixes from code review:

1. looksLikeJSON now only checks for '{' prefix (not '['), avoiding
   false positives on regular text like "[update] see attached".

2. For JSON content (Feishu cards/posts), path tags are prepended
   before the JSON instead of being silently dropped. This ensures
   the LLM can discover attached images via the path tag while the
   JSON payload stays valid for downstream parsing.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-30 11:08:00 +08:00
LiusCraft 1722cfc282 feat: add DeepSeek vision unsupported error detection
Add detection for 'unknown variant' + 'image_url' error pattern used by
DeepSeek and other strict providers when vision is not supported.
These providers reject the image_url field at the JSON schema level
rather than returning a semantic 'not supported' message.
2026-04-30 02:24:29 +08:00
美電球 db1bc6a1f8 Merge pull request #2689 from afjcjsbx/fix/cron-session-key-propagation
fix(cron): propagate sessionKey to prevent duplicate tool responses
2026-04-28 23:03:09 +08:00
LC 9b109dc7a8 fix(serial_windows): remove unused import (#2697) 2026-04-28 16:19:59 +08:00
Guoguo fc24676924 Add cross-platform serial tool support (#2673)
* feat(tools): add cross-platform serial hardware tool

* feat(config): wire serial tool into runtime and dashboard

* hardware/serial: tighten validation and error handling

* hardware/serial: improve unix cancellation and timeout polling

* hardware/serial: improve windows I/O handling

* hardware/serial: fix darwin cross-compilation build

* docs(design): summarize hardware support and serial limits

* build: keep go generate on host during cross builds

* onboard: drop unrelated go generate change from serial work

* style(tools): wrap serial lines for golines
2026-04-28 13:10:32 +08:00
SiYue-ZO bd867a16cd style(tools): wrap serial lines for golines 2026-04-28 12:58:26 +08:00
SiYue-ZO 893e61dc51 hardware/serial: fix darwin cross-compilation build 2026-04-28 12:57:44 +08:00
SiYue-ZO 64e48163d0 hardware/serial: improve windows I/O handling 2026-04-28 12:57:25 +08:00
SiYue-ZO 1f0a5f4eda hardware/serial: improve unix cancellation and timeout polling 2026-04-28 12:57:09 +08:00
SiYue-ZO 338fa258b3 hardware/serial: tighten validation and error handling 2026-04-28 12:56:47 +08:00
SiYue-ZO 2114e1a53f feat(config): wire serial tool into runtime and dashboard 2026-04-28 12:56:27 +08:00
SiYue-ZO 0f52076762 feat(tools): add cross-platform serial hardware tool 2026-04-28 12:54:28 +08:00
LC c44bd6138c refactor(pico): unify message kind handling of tool_calls and thought (#2680)
* refactor(pico): unify message kind handling of tool_calls and thought

* fix(pico): add legacy compatibility for thought payload in Send method

Co-authored-by: Copilot <copilot@github.com>

---------

Co-authored-by: Copilot <copilot@github.com>
2026-04-28 10:17:12 +08:00
afjcjsbx 87ee76b117 Merge remote-tracking branch 'origin/fix/gemini-mcp-schema-sanitization' into fix/gemini-mcp-schema-sanitization 2026-04-27 21:18:29 +02:00
afjcjsbx 7b3e800407 fix test 2026-04-27 21:18:19 +02:00
Mauro c731ecdc74 Merge branch 'main' into fix/gemini-mcp-schema-sanitization 2026-04-27 21:14:25 +02:00
afjcjsbx cd7717bc15 feat(tool): tool schema semplification 2026-04-27 21:10:30 +02:00
afjcjsbx 0bb0fc429a fix(cron): propagate sessionKey to prevent duplicate tool responses 2026-04-27 13:17:25 +02:00
David Siewert e656ddf5bb fix: align struct tag spacing in AgentDefaults config 2026-04-27 16:47:28 +06:00
Hoshina 78fd080189 fix(events): keep runtime observers non-blocking
Add a non-blocking runtime publish path and switch hot-path publishers to it.

Enforce subscription timeout boundaries, keep ordered subscriber snapshots up to date on subscribe changes, expose all runtime kinds to process hooks, add safe log attrs for non-agent events, and close the gateway message bus on full shutdown.
2026-04-27 13:09:03 +08:00
Mauro ed687d62ae fix(config): show precise malformed config diagnostics (#2415)
* fix(config): show precise malformed config diagnostics

* fix lint

* fix test
2026-04-27 09:45:52 +08:00
afjcjsbx 4eeb69688e fix lint 2026-04-26 22:33:35 +02:00
afjcjsbx 1ff8a418f6 fix(mcp): sanitize MCP tool schemas for Gemini function calling 2026-04-26 22:23:55 +02:00
lc6464 d6b38c4236 fix(chat): update tool_calls structure and ensure kind is always set 2026-04-26 20:13:13 +08:00
lc6464 1acab59fc7 fix(tests): format error message 2026-04-26 19:48:22 +08:00
lc6464 bfc37b784e fix(channels): bypass placeholder edits for thought and tool calls 2026-04-26 19:43:25 +08:00
Hoshina 4d6337fd26 fix runtime event logger reload and shutdown 2026-04-26 19:28:26 +08:00
Hoshina b3d9f86a01 feat(events): add configurable runtime event logging 2026-04-26 17:41:00 +08:00
Hoshina f4a24614b8 docs(events): remove stale subturn event names
Replace leftover SubTurnOrphanResultEvent and short subturn event references with runtime event kinds in comments, tests, and hook design notes.

Validation: GOCACHE=/tmp/picoclaw-go-cache go test ./pkg/agent -run TestSpawnSubTurn_OrphanResultRouting; make lint
2026-04-26 17:04:38 +08:00
Hoshina e613258fa5 feat(gateway): publish lifecycle runtime events
Emit gateway.start, gateway.ready, and gateway.shutdown on the shared runtime event bus, while keeping reload events on the same helper path.

Update subturn architecture docs to refer to runtime event kinds instead of the removed agent EventBus names.

Validation: GOCACHE=/tmp/picoclaw-go-cache go test ./pkg/gateway ./pkg/events; GOCACHE=/tmp/picoclaw-go-cache go test ./pkg/bus ./pkg/channels ./pkg/mcp ./pkg/tools/integration ./pkg/events ./pkg/gateway; make lint
2026-04-26 17:02:48 +08:00
Hoshina 795ee362ea refactor(events): emit agent runtime events directly
Remove the legacy EventKind/Event envelope mapping and let agent event emission build pkg/events.Event values directly.

Keep HookMeta as the shared hook metadata shape and preserve legacy observe string aliases by mapping them to runtime event kinds.

Validation: GOCACHE=/tmp/picoclaw-go-cache go test ./pkg/agent; make lint
2026-04-26 16:55:02 +08:00
Hoshina b954e6b8dc refactor(events): remove legacy agent event bus
Drop the old agent EventBus, SubscribeEvents/EventDrops public surface, legacy hook observer dispatch, and hook.event process notification path. Agent observations now flow through pkg/events runtime events.

Validation: go test ./pkg/agent; make lint
2026-04-26 16:39:35 +08:00
Hoshina b2249df3ea refactor(events): split agent event payload types
Move agent domain event payload structs out of the legacy event envelope file so the remaining EventKind/Event/EventMeta compatibility layer can be removed independently later.

Validation: go test ./pkg/agent; make lint
2026-04-26 16:31:52 +08:00
Hoshina 6e8a81bfbf test(events): prefer runtime hook observation
Use RuntimeEventObserver for the normal in-process hook observer path and make the process-hook helper assert hook.runtime_event notifications.

Validation: go test ./pkg/agent; make lint
2026-04-26 16:28:41 +08:00
Hoshina dc80e8f5f2 test(events): migrate agent tests to runtime events
Move AgentLoop event assertions to the runtime event stream and keep the legacy SubscribeEvents test only for dual-publish compatibility.

Validation: go test ./pkg/agent; make lint
2026-04-26 16:23:58 +08:00
Hoshina d9717b5632 refactor(events): start runtime event consumer migration
Deprecate the legacy agent event APIs and add a runtime event test helper, then migrate the follow-up queued test to the runtime event stream.

Validation: go test ./pkg/agent; make lint
2026-04-26 16:11:09 +08:00
Hoshina 8caf9aeb2b feat(events): publish runtime service events
Migrate hook observation to runtime events and update the process hook notification protocol. Add runtime event publication for message bus failures, channel lifecycle/outbound flow, gateway reloads, MCP server state, and MCP tool calls.

Validation: go test ./pkg/events/... ./pkg/bus ./pkg/agent ./pkg/channels ./pkg/mcp ./pkg/tools/integration ./pkg/gateway; make lint
2026-04-26 16:05:10 +08:00
Hoshina eedebabbea feat(events): add runtime event bus
Introduce pkg/events with filtered channels, subscription policies, backpressure, and stats. Wire AgentLoop to dual-publish legacy agent events into runtime events while preserving old event APIs.

Validation: go test ./pkg/events/... ./pkg/agent; go test -race ./pkg/events/...; make lint
2026-04-26 15:36:03 +08:00
David Siewert f0dc709b17 fix(config): fix golines max-len for MaxLLMRetries field 2026-04-26 07:07:19 +06:00