Commit graph

1003 commits

Author SHA1 Message Date
I Putu Eddy Irawan
bfdf8a1c69 Merge remote-tracking branch 'origin/feat/telegram-chunking' into deploy/pi-integration 2026-03-03 22:28:59 +07:00
I Putu Eddy Irawan
82074be630 Merge remote-tracking branch 'origin/feat/kimi-opencode-providers' into deploy/pi-integration 2026-03-03 22:28:54 +07:00
I Putu Eddy Irawan
2700e5cea3 merge: resolve conflict with upstream/main in provider_test.go
Keep both KimiCodeUserAgent test (from this branch) and
serializeMessages tests (from upstream) — no overlap.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-03 22:18:20 +07:00
I Putu Eddy Irawan
878e141359 fix: add LiteLLM to env overrides and fix malformed .env test
- Add missing LITELLM entry to loadProviderEnvOverrides so
  PICOCLAW_PROVIDERS_LITELLM_API_KEY/API_BASE env vars work
- Replace valid .env content in TestLoadConfig_MalformedDotenv_NonFatal
  with genuinely malformed content (bare key without '=') to actually
  exercise the non-fatal error path

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-03 22:14:25 +07:00
I Putu Eddy Irawan
5e20580d57 test: use guardCommand directly and improve assertions in DiskWiping test
Address Copilot review feedback:
- Use guardCommand() instead of Execute() to avoid running dangerous
  commands (format, mkfs, diskpart) on the host if regex regresses
- Assert error message contains "blocked" for blocked commands
- Replace "go fmt ./..." with "echo go fmt ./..." to avoid accidental
  file modification

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-03 22:05:32 +07:00
I Putu Eddy Irawan
40f4c833db Merge upstream/main into feat/dotenv-loading
Resolve go.mod conflict: keep h2non/filetype from upstream,
tcell/v2 stays in direct deps only (not duplicated in indirect).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-03 22:01:04 +07:00
I Putu Eddy Irawan
4a33efcfc5 Merge upstream/main into fix/bugfixes
Resolve conflicts:
- provider.go: keep upstream's serializeMessages (supersedes stripSystemParts)
- provider_test.go: keep upstream's serializeMessages tests
- loop_test.go: add slices import needed by upstream tests
- shell.go: merge PR's --format deny fix with upstream's block device
  pattern, safePaths, and absolutePathPattern
- shell_test.go: include tests from both branches

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-03 21:55:26 +07:00
I Putu Eddy Irawan
4555c5fbb3 refactor: parse Kimi API hostname once in constructor instead of per-call
Avoid re-parsing apiBase URL on every Chat() invocation by computing
isKimiAPI once in NewProvider(). Also document why the KimiCLI/0.77
User-Agent string is required.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-03 21:34:31 +07:00
Mauro
4f1610e5f1 Merge pull request #1024 from wangyanfu2/fix-TavilySearch-response
fix: add HTTP status code check in BraveSearchProvider
2026-03-03 11:42:05 +01:00
nayihz
50cadb7fb5 Merge remote-tracking branch 'origin/main' into feat_discord_proxy 2026-03-03 18:38:57 +08:00
daming大铭
d0f9140d3c Merge pull request #1020 from shikihane/feat/agent-vision-pipeline-v2
feat(agent): add vision/image support with streaming base64 and filetype detection
2026-03-03 18:35:23 +08:00
daming大铭
213f2e9daf Merge pull request #1000 from alexhoshina/main
feat(feishu): enhance channel with markdown cards, media, mentions, and editing
2026-03-03 18:30:14 +08:00
pikaxinge
37cfb6d51d fix(agent): invalidate system prompt cache for global/builtin skills (#845)
* fix(agent): invalidate system prompt cache for global/builtin skills

* test(agent): avoid os.Chdir in builtin skill cache test

* fix(agent): harden skill cache invalidation checks
2026-03-03 18:25:00 +08:00
wangyanfu2
27d71951aa fix: add HTTP status code check in BraveSearchProvider
- Add status code validation after reading response body, consistent
  with TavilySearchProvider and PerplexitySearchProvider
2026-03-03 17:54:43 +08:00
Guoguo
3c1e08774b feat(telegram): add base_url support for custom Telegram Bot API server (#1021)
* feat(telegram): add base_url support for custom Telegram Bot API server

Allow users to specify a custom Telegram Bot API server URL via
config field `base_url` or env var `PICOCLAW_CHANNELS_TELEGRAM_BASE_URL`.
Defaults to the official https://api.telegram.org when left empty.

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

* fix(telegram): trim whitespace and trailing slash from base_url

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

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-03 17:27:57 +08:00
shikihane
c74e9703ee 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
Hoshina
9eeeb83f66 fix(feishu): address PR #1000 review comments from @xiaket
- Consolidate extractImageKey/extractFileKey/extractFileName into shared
  extractJSONStringField helper to reduce code duplication
- Move mentionPlaceholderRegex to package-level position after imports
- Rename feishuCfg field to config for clarity within FeishuChannel
- Replace @_user_1 heuristic with GET /open-apis/bot/v3/info API call
  at startup for reliable bot @mention detection
- Fix double close on file handle in downloadResource by removing defer
  and using explicit close in both success and error paths
- Add unit tests for common.go and feishu_64.go helpers (53 test cases)
2026-03-03 16:44:24 +08:00
shikihane
daaa9442a2 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
b263dff3d6 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
6ea5f2fc48 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
d8b7b2637b 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
cd5def55c2 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
41f1e67cff 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
aaf721a0b8 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
bbdfa5628f Merge pull request #1002 from afjcjsbx/docs/mcp-http-server-example
docs(mcp): http server example
2026-03-03 14:44:07 +08:00
xiaoen
4493899ae6 merge: resolve conflict with main in loop.go
Main reformatted the fallback.Execute call to multi-line (golines);
our branch renamed agent.Candidates → activeCandidates for routing.
Kept both: multi-line formatting + routing variable.
2026-03-03 12:22:45 +08:00
lxowalle
1c124f8b57 * 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
23a2fd5ee2 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
2ece3dd339 Revert "feat(agent): add vision/image support to agent pipeline" 2026-03-03 11:38:32 +08:00
Orgmar
1b8dab21e2 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
7590e53322 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
I Putu Eddy Irawan
63a656ade4 fix: tighten HTML-expansion test to stay under chunk size
Reduce markdown input from 700 to 600 repeats (3600 runes) so it stays
under the 4000-rune chunk threshold. This ensures the test actually
exercises the HTML-expansion re-splitting logic rather than being split
at the markdown level first.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-03 09:20:16 +07:00
I Putu Eddy Irawan
b4f950b0c3 fix: add kimi-code migration alias and User-Agent test
- Add "kimi-code" to the moonshot provider's providerNames in
  ConvertProvidersToModelList so configs using
  agents.defaults.provider: "kimi-code" migrate correctly.
- Add TestProviderChat_KimiCodeUserAgent verifying that
  User-Agent: KimiCLI/0.77 is set when apiBase hostname is
  api.kimi.com and not set for other hosts.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-03 09:18:26 +07:00
I Putu Eddy Irawan
fb6a82cc58 fix: format long lines in telegram_test.go to satisfy golines linter
Break function signatures and assert calls that exceed the 120-char
golines limit onto multiple lines.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-03 09:11:24 +07:00
Alfonso
426fd1b361 feat: add LiteLLM provider alias support (#930) 2026-03-03 08:23:55 +11:00
afjcjsbx
514c41cb0d mcp http server example 2026-03-02 19:50:34 +01:00
Hoshina
22e6a597a1 fix(feishu): remove dead fetchBotOpenID stub and fix misleading comment 2026-03-03 01:39:33 +08:00
Hoshina
9e584f306e fix(feishu): address review findings
- Remove stale "falls back to plain text" comment on Send
- Add empty ChatID validation in SendMedia to match Send
- Use messageID+fileKey as local filename to avoid write collisions
- Check allowlist before downloading inbound media to avoid wasted I/O
- Return errUnsupported consistently from all 32-bit stub methods
2026-03-03 01:27:46 +08:00
Hoshina
d21fd1492c fix(feishu): resolve lint issues 2026-03-03 01:04:11 +08:00
Hoshina
b81c8411c2 feat(feishu): enhance channel with markdown cards, media, mentions, and editing
Upgrade the Feishu channel from basic text-only to full feature parity with
Telegram/Discord: interactive card messages with markdown rendering, message
editing (MessageEditor), placeholder messages (PlaceholderCapable), emoji
reactions (ReactionCapable), and inbound/outbound media support (MediaSender).

Also add @mention detection with lazy bot open_id discovery, group trigger
filtering with mention awareness, and multi-type inbound message parsing
(text, post, image, file, audio, video).
2026-03-03 00:49:32 +08:00
yinwm
c04e808c65 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
04002ccb96 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
a5fc8eec1d Merge branch 'main' into mcp-tools-support 2026-03-03 00:17:39 +08:00
daming大铭
4544e3dd63 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
2b0c8b9a35 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
I Putu Eddy Irawan
73f20dc30b Address Copilot review feedback for .env loading
- Add migrateChannelConfigs() and ValidateModelList() to the fresh-
  install path (no config.json) so legacy env vars are migrated and
  model list is validated consistently with the normal loading path
- Use os.LookupEnv instead of os.Getenv in loadProviderEnvOverrides
  so explicitly empty env vars (e.g. PICOCLAW_PROVIDERS_X_API_BASE=)
  can clear values from config.json
- Guard .env loading with sync.Once to avoid repeated disk I/O and
  noisy log messages when LoadConfig is called from polling handlers
- Add tests: .env file loading, missing config.json with env vars,
  malformed .env non-fatal behavior, and LookupEnv empty-override

Note: go.mod tcell/v2 and tview are correctly listed as direct deps
(they are imported by the launcher TUI); upstream go.mod was stale.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-02 22:50:59 +07:00
esubaalew
96ddc359bc 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
f0ed128dea 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
56af138837 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
15d9c9599b 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