Commit Graph

791 Commits

Author SHA1 Message Date
shikihane 6ccb68c63e fix: resolve linter issues (gci import grouping, gofumpt, govet shadow)
- Separate third-party imports from local module imports (gci)
- Fix byte slice literal formatting (gofumpt)
- Rename shadowed err variable to ftErr (govet)
- Remove trailing blank lines in test files

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-03 17:04:54 +08:00
shikihane 43227411ee feat(agent): wire media refs through agent pipeline to LLM provider
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-03 16:28:20 +08:00
shikihane 03f7ae494f feat(openai_compat): implement serializeMessages with multipart media support
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-03 16:28:20 +08:00
shikihane 6fd65825e7 feat(agent): implement resolveMediaRefs with streaming base64 and filetype detection
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-03 16:28:20 +08:00
shikihane 559cef3d5b chore: add h2non/filetype dependency for magic-bytes MIME detection
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-03 16:28:20 +08:00
shikihane 4c6c05a251 feat(config): add configurable max_media_size with 20MB default
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-03 16:27:29 +08:00
shikihane 6689c0b1c0 feat(providers): add Media field to Message struct for vision support
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-03 16:27:29 +08:00
daming大铭 de2ccb5da4 Merge pull request #999 from yinwm/fix/mcp-race-condition-and-resource-leak
fix(mcp): resolve TOCTOU race condition and resource leak
2026-03-03 15:06:57 +08:00
daming大铭 227f22d28a Merge pull request #1002 from afjcjsbx/docs/mcp-http-server-example
docs(mcp): http server example
2026-03-03 14:44:07 +08:00
lxowalle 435223f500 * Add new style banner for picoclaw and picoclaw-launcher-tui (#1008)
* Add new style banner for picoclaw and picoclaw-launcher-tui
2026-03-03 12:04:28 +08:00
Caize Wu 3bb4f4ecc6 Merge pull request #1010 from sipeed/revert-990-feat/agent-vision-pipeline
revert: "feat(agent): add vision/image support to agent pipeline"
2026-03-03 11:41:58 +08:00
Guoguo 407707a7cc Revert "feat(agent): add vision/image support to agent pipeline" 2026-03-03 11:38:32 +08:00
Orgmar 12d4570a36 Merge pull request #990 from shikihane/feat/agent-vision-pipeline
feat(agent): add vision/image support to agent pipeline
2026-03-03 11:32:07 +08:00
shikihane 8ebeefc59f fix(agent,openai_compat): address review feedback on vision pipeline
- serializeMessages: preserve ToolCallID/ToolCalls when Media is present
- resolveMediaRefs: add 20MB file size limit to prevent OOM
- mimeFromExtension: return empty string for unknown extensions
- Add 11 unit tests for serializeMessages, resolveMediaRefs, mimeFromExtension

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-03 11:13:22 +08:00
Alfonso 946af6b53d feat: add LiteLLM provider alias support (#930) 2026-03-03 08:23:55 +11:00
afjcjsbx 23bb0828b1 mcp http server example 2026-03-02 19:50:34 +01:00
yinwm 78aba700d5 fix(mcp): resolve TOCTOU race condition and resource leak
- Use atomic.Bool for closed flag to prevent TOCTOU race between
  CallTool and Close operations
- Add double-check pattern in CallTool for thread-safe closed state
- Use atomic Swap in Close to ensure no new calls can start after
  closed flag is set
- Move MCP manager cleanup defer before initialization to handle
  partial initialization failures
- Update tests to use atomic.Bool operations

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-03 00:47:25 +08:00
daming大铭 0150947e61 Merge pull request #282 from yuchou87/mcp-tools-support
feat: Add mcp tools support
2026-03-03 00:18:14 +08:00
daming大铭 4e348e39ac Merge branch 'main' into mcp-tools-support 2026-03-03 00:17:39 +08:00
daming大铭 475d8f948b Merge pull request #727 from Esubaalew/fix/wecom-dedupe-race
fix(wecom): remove message-dedupe data races and fix amnesia cliff
2026-03-02 23:57:42 +08:00
esubaalew 2e0be92776 fix(wecom): resolve upstream rebase conflicts after channel refactor
Rebase onto latest upstream/main, keep ring-buffer dedupe behavior, move dedupe tests to pkg/channels/wecom, and ensure wecom/channels race tests pass.
2026-03-02 18:54:11 +03:00
esubaalew 29e9b6b4b5 fix(wecom): replace dedupe map rotation with circular queue
The previous dedupe map rotation logic completely cleared the map when it reached max size, causing an 'amnesia cliff' where immediately arriving duplicates of just-forgotten messages would be processed.

This change replaces that with a MessageDeduplicator struct that uses a circular queue (ring buffer) to track insertions. When the limit is reached, it only evicts the absolute oldest message from the map, completely resolving the cliff issue.

This also cleans up the WeCom Bot and App webhook handlers by encapsulating the mutex and map state.
2026-03-02 18:50:51 +03:00
esubaalew 8640c8177c fix(wecom): correctly retain boundary message during dedupe map rotation
When the dedupe map rotates, the previous logic entirely cleared the map, meaning the message that triggered the rotation was immediately forgotten and could be duplicated immediately.

This change seeds the new map with the current message to prevent that. Also adds a defensive nil check.
2026-03-02 18:50:29 +03:00
esubaalew 1e2ab4a5e5 test(wecom): add dedupe helper coverage and align constant usage
Use wecomMaxProcessedMessages in tests and add a concurrent same-message test
to lock in race-safety behavior for markMessageProcessed.
2026-03-02 18:50:29 +03:00
esubaalew db17cdc86d test(wecom): align dedupe rotation behavior and add helper tests
Match rotation semantics to prior behavior by fully resetting the dedupe map
once the size limit is exceeded, and add focused tests for duplicate detection
and boundary rotation behavior.
2026-03-02 18:50:29 +03:00
esubaalew 18d89937ad fix(wecom): remove message-dedupe data races in bot/app channels
Centralize dedupe map access behind a mutex-safe helper and use it in both
WeCom bot and WeCom app channels to eliminate concurrent map access races while
preserving current dedupe behavior.
2026-03-02 18:50:29 +03:00
daming大铭 25639168ea Merge pull request #300 from mymmrac/telegram-bot-commands
feat(telegram): Init bot commands on start
2026-03-02 23:43:10 +08:00
daming大铭 8fddbaed4f Merge pull request #682 from Esubaalew/fix/makefile-test-vet-generate
fix: add generate dependency to test and vet Makefile targets
2026-03-02 23:31:03 +08:00
美電球 f2ab1a74da Merge pull request #893 from reevoid/rui-dev
Add WeCom AIBot channel implementation and tests
2026-03-02 21:50:21 +08:00
Caize Wu 929589a025 Merge pull request #987 from lxowalle/doc/update_contribute
* update contributing.md
2026-03-02 21:24:31 +08:00
lxowalle 4402fcf63c * update contributing.md 2026-03-02 21:20:23 +08:00
lxowalle 5fa2e1d1e4 * update contributing.md 2026-03-02 21:17:59 +08:00
daming大铭 faec0261d0 Merge pull request #535 from xiaket/ci-enable-dupl-linter
ci: enable duplication linter in CI
2026-03-02 18:55:35 +08:00
Zhang Rui 23f48d7c4e refactor(aibot): remove downloadAndDecryptImage function to streamline image handling 2026-03-02 18:21:53 +08:00
shikihane 18b36af934 feat(agent): add resolveMediaRefs to convert media:// refs to base64 data URLs
Without this function, media:// refs stored by MediaStore are passed
directly to the LLM API, which rejects them as invalid URLs.

resolveMediaRefs() runs after BuildMessages() and before the LLM call,
converting each media:// ref to a data:image/...;base64,... URL that
vision-capable models can process.

Also adds mimeFromExtension() helper for MIME type inference from
file extensions when ContentType metadata is not available.
2026-03-02 18:08:32 +08:00
Zhang Rui edd339e056 fix(wecom): handle empty response by encrypting and returning a default response 2026-03-02 17:42:54 +08:00
Zhang Rui 619948f8ff fix(wecom): improve error message for response_url delivery failure 2026-03-02 17:42:54 +08:00
Zhang Rui bf4445f1f3 refactor(docs): remove webhook_host and webhook_port from configuration examples 2026-03-02 17:42:54 +08:00
Zhang Rui d4824a00b6 refactor(config): remove WebhookHost and WebhookPort from WeComAIBotConfig 2026-03-02 17:42:54 +08:00
Zhang Rui 55c556a4c5 fix(wecom): update CanonicalID generation to use identity.BuildCanonicalID for consistency 2026-03-02 17:42:54 +08:00
Zhang Rui 79b7fb7792 fix(wecom): improve error handling in sendViaResponseURL and remove task on failure 2026-03-02 17:42:54 +08:00
Zhang Rui 79bc06c0ba refactor(wecom): simplify stream message structure by introducing WeComAIBotMsgItem and WeComAIBotMsgItemImage types 2026-03-02 17:42:54 +08:00
Zhang Rui 880c402ab7 refactor(wecom): streamline AES encryption/decryption and improve task management logic 2026-03-02 17:42:54 +08:00
Zhang Rui 8f3d611a4c refactor(wecom): replace generateSignature with computeSignature and update related tests 2026-03-02 17:42:54 +08:00
Zhang Rui 81f6787dd5 fix(docs): update WeCom AI Bot timeout duration in README and improve streamTask comments 2026-03-02 17:42:54 +08:00
ZHANG RUI e88b39f21e Update pkg/channels/wecom/aibot.go
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-03-02 17:42:54 +08:00
Zhang Rui 4a87090fd9 fix(docs): update WeCom AI Bot task timeout duration in README 2026-03-02 17:42:54 +08:00
Zhang Rui a87e6b0551 feat(wecom-aibot): enhance stream task management with StreamClosedAt and improved cleanup logic 2026-03-02 17:42:54 +08:00
Zhang Rui 4e09c91dda feat(wecom-aibot): add context management for stream tasks to improve agent cancellation 2026-03-02 17:42:54 +08:00
ZHANG RUI 0b6d913dfc Update pkg/channels/wecom/aibot.go
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-03-02 17:42:54 +08:00