* refactor: remove the legacy picoclaw-launcher
* feat: create initial web frontend and backend structure
* feat(packaging): add desktop entry for PicoClaw Launcher (#1062)
- Add .desktop file with Terminal=true, named "PicoClaw Launcher"
- Install to /usr/share/applications/ for app menu visibility
- Add 512x512 PNG icon to /usr/share/icons/hicolor/
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* `make dev`: If you haven't built it before, you need to run `build` first.
* feat(web): comprehensive web UI and backend refactoring
This commit introduces a major overhaul of both the frontend web UI and the Go backend API, transitioning to a highly modular architecture and integrating new core features.
Backend:
- Refactored monolithic API endpoints into domain-specific modules (config, gateway, log, models, pico, session).
- Cleaned up obsolete files (`server.go`, `status.go`, WebSocket handlers) and outdated tests.
- Implemented Gateway process lifecycle management (start/stop/restart) and real-time log streaming.
Frontend:
- Integrated Shadcn UI components to establish a modern, consistent design system.
- Introduced a new application layout featuring a responsive sidebar (`app-sidebar`) and header.
- Implemented internationalization (i18n) with initial support for English and Chinese.
- Restructured API clients, hooks, and Zustand stores into logical domains.
- Added new management pages for Settings, Logs, Models, Providers, and Credentials.
- Upgraded the Pico chat interface with session history management and dynamic model selection.
Build & Config:
- Updated frontend dependencies, Vite configuration, and lockfiles.
- Refined routing setup and overarching application stylesheets.
* feat(web): enhance model management, sorting, and deletion logic
- Implement model sorting in UI (default > configured > unconfigured)
- Prevent deletion of default models in the frontend
- Update backend to clear default settings when a model is deleted
- Add existence validation when setting a default model via API
- Group models in chat UI by type (API Key, OAuth, Local)
- Conditionally display model selector in chat based on configuration status
* refactor(web): refactor chat page into modular components/hooks and update i18n
- split chat route into dedicated chat components (page, composer, empty state, messages, history, model selector)
- extract model/session logic into use-chat-models and use-session-history hooks
- update chat locale keys in en/zh and add empty-state/history-related translations
* refactor(models): refactor models page into modular components and improve UX
- split /models route into dedicated components (page, provider section, card, add/edit sheets, delete dialog)
- add provider grouping/sorting, provider labels/icons, and a no-default hint in the models page
- add "Set as default model" toggle to add/edit flows with safer defaults
- introduce shared form helpers and new UI primitives (field, label, switch)
- update i18n strings (en/zh) for models and gateway header text usage
- apply minor UI polish (models nav icon, separator client directive)
* fix(web): add SPA index fallback for embedded frontend routes
Serve existing static assets as-is, keep /api/* and missing asset paths returning 404, and add tests for SPA fallback behavior on refresh.
* fix(frontend/chat): normalize message timestamp units to prevent invalid far-future dates
* chore: delete TestSPARouteFallsBackToIndex
* feat: update build for web-based launcher (#1186)
- Makefile: add build-launcher target (builds frontend + Go backend)
- GoReleaser: point picoclaw-launcher build to web/backend, add frontend
build hook, restore winres hook with updated paths
- Restore icon.ico and winres config from main for Windows builds
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat(credentials): add multi-provider OAuth credential management
- add backend `/api/oauth/*` endpoints for provider status, browser/device-code/token login, flow query/polling, and logout
- extend API handler with OAuth flow/state tracking and route registration, plus OAuth unit tests
- implement frontend credentials page/components for OpenAI, Anthropic, and Google Antigravity login/logout
- add OAuth API client and `useCredentialsPage` hook, with new EN/ZH i18n strings
* chore: remove placeholder index.html from dist (#1188)
The .gitkeep is sufficient for go:embed to find the dist directory.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix(frontend): polish model and credential UX; remove Providers nav
- remove the Providers item from sidebar navigation and locale keys
- simplify chat composer by dropping attach/voice action buttons
- support ReactNode titles in credential cards and add provider brand icons
- refine sheet header/footer styling and device-code footer button hierarchy
- disable “Set default” when a model is unconfigured or already default
* feat(web): Update config page (#1173)
* feat(web): Update config page
* fix(web): useEffect resets editorValue whenever config changes
* fix(web): react-hooks/set-state-in-effect error & pnpm lint #1173
* feat(web): add channel management page for web console (#1190)
* feat(web): add channel management page for web console
Add a complete channel management UI that allows users to configure
messaging channels (Telegram, Discord, Slack, Feishu, etc.) directly
from the web console instead of manually editing config.json.
Backend: GET/PUT/PATCH API endpoints for listing, updating, and
toggling channels with secret field masking.
Frontend: Channel cards grid with enable/disable toggles, per-channel
configuration sheets with dedicated forms for major platforms and a
generic fallback for others.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(web/channels): move channels to own sidebar group and fix sheet padding
- Channels now has its own navigation group instead of being under Services
- Fix edit sheet form content padding (px-1 -> px-4) to match header/footer
- Fix naked return lint error in extractChannelInfo
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix(web): harden channel config updates and resolve frontend lint issues
- validate channel PUT/PATCH updates before saving and return structured validation errors
- require `enabled` in toggle requests to avoid silent false defaults
- support editing `allow_origins` in the generic channel form and parse string/array inputs on backend
- replace channel form `any` usage with `ChannelConfig` (`Record<string, unknown>`) and add safe value helpers
- add i18n strings for allow-origins fields and apply related frontend formatting cleanups
* fix(frontend): prevent false "Invalid JSON" errors in config editor
* feat: add startup readiness checks and propagate start availability to UI
- add gateway precondition validation for default model and credentials
- auto-start gateway on backend boot when conditions are met
- include gateway_start_allowed and gateway_start_reason in status updates
- prevent frontend start actions when gateway cannot be started
* feat(web): revamp channel config UX with catalog-based routing
- replace legacy channel management endpoints with a backend channel catalog API
- switch frontend channel updates to PATCH /api/config and per-channel config pages
- add dynamic channel items in the sidebar with support for expand/collapse
- migrate /channels to nested routes (/channels/$name) and remove old card/sheet flow
- improve channel forms with clearer hints, required/error states, and reusable switch cards
- fix Discord mention-only toggle to read/write group_trigger.mention_only
* refactor(frontend): move shared-form to components and unify default-model switch with SwitchCardField
* fix(frontend): improve model form validation and unify secret placeholder handling
- block duplicate model aliases when adding a model (with localized error messages)
- share masked secret placeholder logic across model and channel forms
- refresh gateway state after setting the default model
- apply minor UI cleanup to provider icon rendering
* feat(web): add visual system config and launcher/autostart controls
- add launcher config model and persistence (`launcher-config.json`) for port/public/CIDR settings
- add system APIs for launch-at-login and launcher parameters
- apply CIDR-based access-control middleware to backend HTTP routes
- split config routing into visual config and raw JSON config pages
- add frontend system API client and visual config sections for runtime/devices/launcher
- expand i18n strings (en/zh) for new config UI
- improve sidebar active matching and session ID generation fallback
* refactor(frontend): remove i18n fallback strings and drop providers route
- Replace `t(key, defaultValue)` calls with key-only translations across UI pages
- Clean up locale files by pruning unused keys and adding missing shared keys
- Remove the obsolete `/providers` page and update generated route tree
* fix(backend): correct gateway status detection on Windows
* fix(repo): keep web backend dist placeholder tracked
---------
Co-authored-by: Guoguo <16666742+imguoguo@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Dihubopen <dihubcn@gmail.com>
Co-authored-by: Dihubopen <130813726+Dihubopen@users.noreply.github.com>
* fix(tui): fix model selection and enforce unique model_name, also fix model form button highlight
* feat(tui): add footer view with navigation instructions and update menu structure
* fix(tui): update model selection labels for clarity and consistency
* refactor(tui): remove unused rootChannelDescription function
* refactor(tui): simplify rootModelDescription and remove unused 'q' event handling in channel menu
* fix(tui): keep selected model name updated
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Add notarize.macos section to .goreleaser.yaml using anchore/quill
for cross-platform code signing and Apple notarization of darwin
binaries. Covers all three build targets (picoclaw, picoclaw-launcher,
picoclaw-launcher-tui).
Notarization is gated on MACOS_SIGN_P12 being set, so releases
without the secrets configured will skip this step gracefully.
Required GitHub secrets:
- MACOS_SIGN_P12: base64-encoded .p12 certificate
- MACOS_SIGN_PASSWORD: certificate password
- MACOS_NOTARY_ISSUER_ID: App Store Connect issuer UUID
- MACOS_NOTARY_KEY_ID: App Store Connect API key ID
- MACOS_NOTARY_KEY: base64-encoded .p8 API key
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Add s390x and mipsle (softfloat) architecture targets to all three
goreleaser build entries (picoclaw, picoclaw-launcher, picoclaw-launcher-tui).
Go only supports these architectures on Linux, so no additional
ignore entries are needed — goreleaser skips unsupported OS/arch
combinations automatically.
mipsle uses GOMIPS=softfloat for maximum compatibility with
FPU-less MIPS cores (e.g. MT7620 with MIPS 24KEc).
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
WithMaxMessageLength(4000) already ensures msg.Content ≤ 4000 chars
before reaching Send(), making the SplitMessage call redundant.
The HTML expansion safety net (re-split when >4096 after conversion)
is still preserved.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add separate User and RealName config fields (fall back to Nick)
- Make RequestCaps configurable (defaults to server-time, message-tags)
- Refactor isBotMentioned into nickMentionedAt returning position;
stripBotMention now uses nickMentionedAt internally
- Replace custom isAlphanumeric with unicode.IsLetter/unicode.IsDigit
- Update tests for new nickMentionedAt function
- Log job start with name, id, schedule kind, and channel
- Log job completion with duration and next run time
- Log job errors with duration and error message
- Helps diagnose scheduler stalls and connection issues
Fixes#1126
Go type assertions return true for zero values, which caused recurring
cron jobs (every_seconds/cron_expr) to silently become one-time 'at' tasks
when LLMs filled unused optional parameters with default values (0).
Changes:
- Add validity checks after type assertions: atSeconds > 0, everySeconds > 0, cronExpr != ""
- This ensures zero values are treated as 'not set' rather than valid schedule values
- Recurring tasks like "remind me every 2 hours" now correctly create recurring jobs
* feat(auth): add Anthropic OAuth setup-token login flow
Add support for Anthropic's OAuth-based setup tokens (sk-ant-oat01-*)
as an alternative to API keys. This includes:
- New `--setup-token` flag on `auth login` command
- Interactive login menu for Anthropic (setup token vs API key)
- Setup token validation and credential storage with oauth auth method
- Usage endpoint integration to show 5h/7d utilization in `auth status`
- Streaming support for OAuth tokens (required by Anthropic API)
- Model ID normalization (dots to hyphens) for API compatibility
- Remove .env.example (secrets should not be templated)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(auth): update related functionality
* refactor(auth): organize constants and improve header casing in requests fo CI
* fix(auth): fix golint again
* fix(auth): handle nil arguments in tool calls for buildParams function
---------
Co-authored-by: Baller <sharonms3377@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat(feishu): implement SendMedia and add send_file tool
Add outbound media support for the Feishu channel so the agent can send
images and files to users via the MediaStore pipeline.
Feishu channel:
- SendMedia dispatches media parts as image or file uploads
- sendImage uploads via Image.Create then sends image message
- sendFile uploads via File.Create then sends file message
- feishuFileType maps extensions to Feishu file_type values
send_file tool:
- New tool lets the LLM send a local file to the current chat
- Validates path, registers file in MediaStore, returns media ref
- Agent loop wires tool registration, MediaStore propagation, and
context updates
Tested on Radxa Cubie A7A (arm64) with Feishu websocket channel.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(agent): publish outbound media regardless of SendResponse flag
The SendResponse flag controls whether the agent loop publishes the
final text response (callers that publish it themselves set this to
false). However, the media publish path was also gated behind this
flag, which meant tool-produced media was silently dropped for normal
channel messages.
Media should be published immediately when a tool returns media refs,
independent of how the text response is delivered.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(tools): use magic-bytes MIME detection and add file size limit to send_file
- Replace hardcoded extension-to-MIME map with h2non/filetype (magic
bytes) + mime.TypeByExtension fallback, consistent with the vision
pipeline in resolveMediaRefs
- Add configurable max file size check (defaults to config.DefaultMaxMediaSize,
20 MB) to prevent oversized uploads
- Add tests for magic-bytes detection, extension fallback, size limit,
and default max size
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor(agent): add ForEachTool to AgentRegistry for cross-agent tool lookup
Extract the pattern of iterating agents to find a named tool into
AgentRegistry.ForEachTool, simplifying SetMediaStore propagation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(agent,tools): adapt send_file to ctx-based channel injection after upstream refactor
Replace ContextualTool interface (removed upstream) with direct ctx
reading in SendFileTool.Execute, using ToolChannel/ToolChatID helpers.
Remove updateToolContexts which is no longer needed since ExecuteWithContext
already injects channel/chatID into ctx for all tools.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(tools): support toggling send_file tool via config
Add SendFileConfig with Enabled field to ToolsConfig, defaulting to
true. Wrap send_file tool registration in loop.go with the config
check, consistent with the pattern used by other tools.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat(commands): Session management [Phase 1/2] command centralization and registration
* docs: add design for command registry post-review fixes
Documents the architecture decisions for fixing 5 Important issues
from code review: SubCommand pattern, Deps struct, command-group files,
Executor caching, and Telegram registration dedup.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(commands): add SubCommand type and EffectiveUsage method
Introduce SubCommand struct for declaring sub-commands structurally
within a parent command Definition. The EffectiveUsage() method
auto-generates usage strings from sub-command names and args,
preventing drift between help text and actual handler behavior.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(commands): add Deps struct and secondToken helper, remove dead contains()
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(commands): add sub-command routing to Executor
Uses Registry.Lookup for O(1) command dispatch instead of iterating
all definitions. Definitions with SubCommands are routed to matching
sub-command handlers. Missing or unknown sub-commands reply with
auto-generated usage.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor(commands): split into command-group files with Deps injection
Extract show/list/start/help into individual cmd_*.go files.
Replace config.Config parameter with Deps struct for runtime data.
Restore /show agents and /list agents sub-commands.
Use EffectiveUsage for auto-generated help text.
Bridge external callers (agent/loop.go, telegram.go) with Deps wrapper
until Task 5 fully wires the Deps fields.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* perf(commands): cache Executor in AgentLoop, wire Deps with runtime callbacks
Create Executor once in NewAgentLoop instead of per-message. Deps
closures capture AgentLoop pointer for late-bound access to
channelManager and runtime agent model.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(telegram): remove duplicate initBotCommands, keep async startCommandRegistration only
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* chore(commands): restore Outcome comments and annotate Deps.Config
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor(commands): consolidate /switch into commands package, fix ! prefix
Move /switch model and /switch channel handling from inline loop.go
logic into cmd_switch.go using the SubCommand + Deps pattern. This
removes the OutcomePassthrough branch in handleCommand entirely.
Also replace the hardcoded "/" prefix check with commands.HasCommandPrefix
so that "!" prefixed commands are correctly routed to the Executor.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* chore: add docs/plans to .gitignore and untrack existing files
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor(commands): address code review findings
- Remove dead ExecuteResult.Reply field and unused branch in loop.go
- Extract shared agentsHandler for /show agents and /list agents
- Remove redundant firstToken/secondToken (use nthToken instead)
- Simplify Telegram startup: pass BuiltinDefinitions directly
- Centralize req.Reply nil guard in executeDefinition
- Extract unavailableMsg constant (was duplicated 5 times)
- Remove unused MessageID from Request
- Remove stale "reserved for Phase 2" comment on Deps.Config
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor(commands): replace Deps with per-request Runtime
Separate stateless Registry (cached on AgentLoop) from per-request
Runtime (passed to handlers at execution time). This enables future
session management features to inject per-request context without
modifying the command registry.
- Rename Deps → Runtime, move to runtime.go
- Change Handler signature: func(ctx, req) error → func(ctx, req, rt *Runtime) error
- NewExecutor now takes (registry, runtime) — executor is created per-request
- BuiltinDefinitions() no longer takes parameters (stateless)
- AgentLoop caches cmdRegistry, builds Runtime via buildRuntime()
- Update all cmd_*.go handlers and tests
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* style: fix gci import grouping and godoc formatting
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(onboard): skip legacy AGENT.md when copying embedded workspace templates
The workspace/ directory contains both AGENT.md (legacy) and AGENTS.md
(current). copyEmbeddedToTarget was copying both, causing the test
TestCopyEmbeddedToTargetUsesAgentsMarkdown to fail. Skip AGENT.md
during the walk to match the expected behavior.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor(agent): address self-review comments on loop.go
- Move cmdRegistry init into struct literal (review comment #11)
- Rename buildRuntime → buildCommandsRuntime for clarity (review comment #12)
- Add comment to default switch case explaining passthrough (review comment #13)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor(commands): address code review findings on naming and correctness
- Rename dispatcher.go → request.go (no Dispatcher type remains)
- Rename cmd_agents.go → handler_agents.go (shared handler, not a top-level command)
- Add modelMu to protect AgentInstance.Model writes in SwitchModel
- Add ListDefinitions to Runtime so /help uses registry instead of BuiltinDefinitions()
- Fix SwitchChannel message: validation-only callback should not say "Switched"
- Propagate Reply errors in executor instead of discarding with _ =
- Add HasCommandPrefix unit test
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor(onboard): extract legacy filename to constant
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(agent): handle commands before route error check
Move handleCommand() before the routeErr gate so global commands
(/help, /show, /switch) remain available even when routing fails.
Context-dependent commands that need a routed agent will report
"unavailable" through their nil-Runtime guards.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* revert: remove unnecessary AGENT.md skip in onboard
Reverts 02d0c04 and 74deae1. The test failure was caused by a local
leftover workspace/AGENT.md file (gitignored but embedded by go:embed).
Deleting the local file fixes the root cause; the code-level skip was
never needed.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: executeDefinition Unknown option
* fix(agent): use routed agent for model commands, restore Telegram command diff
- Remove modelMu: message processing is serial, no concurrent writes
- Pass routed agent to handleCommand/buildCommandsRuntime instead of
always using default agent
- GetModelInfo/SwitchModel are nil when agent is nil (route failed),
handlers reply "unavailable"
- Restore GetMyCommands + slices.Equal check before SetMyCommands to
avoid unnecessary Telegram API calls on restart
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(commands): remove unintended config mutation in SwitchModel
SwitchModel should only update the routed agent's runtime Model field.
Writing to cfg.Agents.Defaults.ModelName was a behavioral change that
corrupts the default agent config when switching a non-default agent.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor(commands): move /switch channel to /check channel
/switch channel only validates availability, not actually switching.
Rename to /check channel to match actual behavior. /switch channel
now shows a redirect message pointing users to the new command.
Addresses review feedback from yinwm on PR #959.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Add a boolean input (default: true) to control whether release artifacts
are uploaded to Volcengine TOS.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
1. CJK token estimation: replace flat rune_count/3 with script-aware
counting — CJK runes (U+2E80–U+9FFF, U+F900–U+FAFF, U+AC00–U+D7AF)
count as 1 token each, non-CJK runes at /4. This fixes a 3x
underestimate for Chinese/Japanese/Korean text that could incorrectly
route complex CJK messages to the light model.
2. Routing observability: SelectModel now returns the computed score as
a third value. selectCandidates logs the score on both paths — Info
level for light model selection, Debug level for primary model
selection.
3. Added tests: TestExtractFeatures_TokenEstimate_Mixed (CJK+ASCII mix),
TestRouter_SelectModel_ReturnsScore.
Addresses review feedback from @mingmxren.
Add reusable workflow (upload-tos.yml) to upload release archives to
Volcengine TOS bucket. Supports both workflow_call from release pipeline
and manual workflow_dispatch trigger. Uploads to versioned ({tag}/) and
latest/ directories.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Upstream added ThinkingLevel, SummarizeMessageThreshold,
SummarizeTokenPercent, MaxMediaSize, and maybeSummarize.
Our branch added Router, LightCandidates, and selectCandidates.
Both sets of changes are kept. Dead updateToolContexts removed
(upstream deleted it; no callers exist).
Add TimeoutSeconds field to ExecConfig so the shell command execution
timeout can be configured instead of being hardcoded to 60s.
- Add TimeoutSeconds int field to ExecConfig in pkg/config/config.go
with json/env tags (PICOCLAW_TOOLS_EXEC_TIMEOUT_SECONDS)
- Set default value of 60s in DefaultConfig() in pkg/config/defaults.go
- Read TimeoutSeconds from config in NewExecToolWithConfig() in
pkg/tools/shell.go; falls back to 60s when value is 0 or unset
Sort irc import alphabetically in helpers.go and fix struct field
alignment in irc.go to satisfy golangci-lint gci formatter.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
io.ReadAll errors were silently discarded with `body, _ := io.ReadAll(...)`,
which could cause empty or partial data to be used for JSON unmarshaling
or error messages. This adds proper error checks for all instances.
Add IRC as a new channel for picoclaw, supporting server connections,
channel joins, DMs, mention-based group triggers, and IRCv3 typing
indicators. Uses ergochat/irc-go for connection management with SASL,
NickServ, and automatic reconnection support.
Closes#1137
The --registry flag value was previously ignored and only used as a
switch. Now the flag value is properly used as the registry name.
Fixes#1104
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
* fix: eliminate data races on shared tool instances
Signed-off-by: Boris Bliznioukov <blib@mail.com>
* fix: remove unused indirect dependency on github.com/gdamore/tcell/v2
Signed-off-by: Boris Bliznioukov <blib@mail.com>
* fix: reviewer comments improve context handling for tool execution and ensure defaults for non-conversation callers
Signed-off-by: Boris Bliznioukov <blib@mail.com>
---------
Signed-off-by: Boris Bliznioukov <blib@mail.com>
* feat: add extended thinking support for Anthropic models
Support configurable thinking levels (off/low/medium/high/xhigh/adaptive)
via `agents.defaults.thinking_level` config field.
- "adaptive": uses Anthropic's adaptive thinking API (Claude 4.6+)
- "low/medium/high/xhigh": uses budget_tokens (all thinking-capable models)
- "off": disables thinking (default)
API constraints handled:
- Temperature cleared when thinking is enabled
- budget_tokens clamped to max_tokens-1
- Thinking response blocks parsed into Reasoning field
Relates to #645, #966
* fix: address PR review feedback for thinking support
- Add ThinkingCapable interface for provider capability detection
- Warn when thinking_level is set but provider doesn't support it
- Warn when temperature is cleared due to thinking enabled
- Adjust budget values per Anthropic best practices (medium=16K, xhigh=64K)
- Add budget clamp warning and 80% threshold warning
- Add parseResponse thinking block tests
- Add thinking_level field to config.example.json
* refactor: move ThinkingLevel from AgentDefaults to ModelConfig
Thinking is a model-level capability, not a global agent property.
Per-model config avoids silent ignoring on non-Anthropic providers
and eliminates spurious warning logs in multi-provider setups.
Addresses PR #1076 review feedback from @yinwm.
Resolve merge conflicts to keep both SearXNG and GLM Search
providers. Updated search priority order to:
Perplexity > Brave > SearXNG > Tavily > DuckDuckGo > GLM Search
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The TestConvertProvidersToModelList_AllProviders test expected 19
providers but adding Avian brings the total to 20.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Accept upstream versions for all non-Telegram files to keep PR
scope focused on Telegram message chunking only.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
After re-splitting an oversized chunk, sub-chunks were sent without
verifying their HTML also fits under 4096 chars. Non-uniform HTML
expansion (e.g. a sub-chunk dense with bold/links) could still exceed
the limit. Use a queue that pushes sub-chunks back for re-validation
instead of sending them blindly.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When HTML parsing fails, the fallback was re-sending the same HTML
string with ParseMode cleared, showing raw HTML tags to users.
Now pass the original markdown chunk so the fallback displays
readable plain text instead.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The Manager splits at MaxMessageLength before calling Send(), and
Telegram's Send() was re-splitting at 4000 internally. Aligning the
channel-level limit to 4000 avoids that redundant second split while
preserving the safety margin for markdown-to-HTML expansion.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
addMsg now calls f.Sync() before f.Close(), matching the durability
guarantee of writeMeta and rewriteJSONL (both use WriteFileAtomic
with fsync). Without this, a power loss could leave the appended
line in the kernel page cache only — lost on reboot.
When the LLM returns multiple tool calls, they are now executed
concurrently using goroutines + sync.WaitGroup instead of sequentially.
Results are collected in an indexed slice and processed in original order
to preserve message ordering. MessageTool.sentInRound is changed to
atomic.Bool for thread safety.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Address Copilot review feedback:
- Move resolveDiscordRefs(content) before the referenced message
concatenation to prevent message links in quoted replies from being
expanded twice.
- Add unit tests for channelRefRe and msgLinkRe regex patterns,
covering valid/invalid inputs and the 3-link cap.
* feat(config): add GLMSearchConfig for GLM Search provider
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* test(tools): add failing tests for GLM Search provider
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(tools): add GLMSearchProvider for web search
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(agent): wire GLM Search config into web search tool registration
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Security fix: resolveDiscordRefs now takes a guildID parameter and
skips message links pointing to a different guild, preventing the bot
from leaking content across guilds.
Also uses s.State.Channel() cache before falling back to API calls
to reduce Discord API usage and rate limit risk.
- Guard against nil ReferencedMessage.Author to prevent panic
- Hoist regexp.MustCompile to package-level vars to avoid
re-compilation on every handleMessage call
- Both are defensive programming improvements
Add resolveDiscordRefs method that:
1. Resolves <#id> channel mentions to #channel-name by calling
the Discord API to fetch channel info
2. Expands Discord message links (up to 3) by fetching the linked
message content and appending it as '[linked message from User]: content'
Applied to both quoted/referenced messages and the main message
content for full context resolution.
When a user replies to a message in Discord, the bot now reads
m.ReferencedMessage and prepends its content to the incoming
message as '[quoted message from Username]: content'.
This gives the LLM full context of what message the user is
replying to, enabling meaningful follow-up conversations.
Add Avian (https://avian.io) as an OpenAI-compatible provider with
API base https://api.avian.io/v1 and AVIAN_API_KEY env var support.
Models: deepseek/deepseek-v3.2, moonshotai/kimi-k2.5, z-ai/glm-5,
minimax/minimax-m2.5. Supports chat completions, streaming, and
function calling.
Changes:
- Add Avian to ProvidersConfig struct, IsEmpty(), HasProvidersConfig()
- Add avian protocol to factory provider and default API base
- Add avian case to legacy provider selection (factory.go)
- Add avian migration rule for old config format
- Add default model entries to ModelList (deepseek-v3.2, kimi-k2.5)
- Add avian to example config
- Update AllProviders test count from 18 to 19
Keep both KimiCodeUserAgent test (from this branch) and
serializeMessages tests (from upstream) — no overlap.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- 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>
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>
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>
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>
* 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>
- 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>
- 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)
- 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>
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>
- 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>
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>
- 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
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).
- 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>
- 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>
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.
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.
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.
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.
When markdownToTelegramHTML expands a chunk beyond 4096 chars (e.g.
**a** → <b>a</b>), re-split the markdown with a proportionally smaller
maxLen so each resulting HTML chunk fits within Telegram's limit.
Extract sendHTMLChunk helper to avoid duplicating the HTML-send +
plain-text-fallback logic.
Add test case for markdown-short-but-HTML-long scenario to verify
the re-splitting behavior.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add Exa (https://exa.ai) as a new web search provider option, slotting
into the priority chain between Perplexity and Brave. Configurable via
config.json or PICOCLAW_TOOLS_WEB_EXA_* environment variables.
Results are capped to the requested count for consistency with other
search providers.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Load .env files from the config directory before reading config.json,
enabling secrets and API keys to be stored outside version control.
Supports fresh installs (no config.json) by applying env vars and
provider overrides to the default config.
Adds loadProviderEnvOverrides() for PICOCLAW_PROVIDERS_<NAME>_API_KEY
and _API_BASE environment variables across all standard providers.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- classifier.go: s/honour/honor/ (American English per misspell)
- router.go: break SelectModel signature across lines (golines)
- router_test.go: break long Message literal (golines)
- router_test.go: replace CJK string literal with rune slice so
gosmopolitan does not flag the source file; behaviour is identical
Cover empty content early return, single-message send,
multi-chunk splitting for long messages, HTML-to-plain-text
fallback per chunk, and error propagation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
instance.go:
- Add Router *routing.Router and LightCandidates []FallbackCandidate
to AgentInstance.
- At agent creation, when routing.enabled and light_model resolves
successfully in model_list, pre-build the Router and resolve the
light model candidates once. If the light model isn't in model_list,
log a warning and disable routing for that agent gracefully.
loop.go:
- Add selectCandidates(agent, userMsg, history) helper.
It calls Router.SelectModel and returns either agent.Candidates /
agent.Model (primary tier) or agent.LightCandidates / light_model
(light tier). Returns primary unchanged when routing is disabled.
- In runLLMIteration, resolve (activeCandidates, activeModel) once
before entering the tool-iteration loop. The model tier is sticky
for the entire turn so a multi-step tool chain doesn't switch
models mid-way.
- Replace hard-coded agent.Candidates / agent.Model references in
callLLM and the debug log with the resolved active values.
The fallback chain and retry logic are untouched. When light_model
returns an error the fallback chain handles escalation normally.
Add three new files to pkg/routing/:
features.go — ExtractFeatures(msg, history) → Features
Computes five structural dimensions with zero keyword matching:
- TokenEstimate: rune_count/3 (CJK-safe token proxy)
- CodeBlockCount: ``` pairs in the message
- RecentToolCalls: tool call count in the last 6 history entries
- ConversationDepth: total messages in session
- HasAttachments: data URIs or media file extensions
classifier.go — Classifier interface + RuleClassifier
RuleClassifier uses a weighted sum that is capped at 1.0:
code block → +0.40 (triggers heavy model alone at 0.35 threshold)
token > 200 → +0.35 (triggers heavy model alone)
tool calls > 3 → +0.25
token 50-200 → +0.15
conversation depth > 10 → +0.10
attachment → 1.00 (hard gate, always heavy)
router.go — Router wraps config + Classifier
Router.SelectModel(msg, history, primaryModel) returns either the
configured light_model or the primary model depending on whether
the complexity score clears the threshold. Threshold defaults to
0.35 when zero/negative to prevent misconfiguration.
router_test.go — 34 tests covering all branches and edge cases
Introduce RoutingConfig with three fields:
- enabled: activates per-turn model routing
- light_model: references a model_name in model_list
- threshold: complexity score cutoff in [0,1]
When routing.enabled is true and the incoming message scores below
threshold, the agent switches to light_model for that turn. Absent or
disabled config leaves existing behaviour completely unchanged.
Example:
"agents": {
"defaults": {
"model": "claude-sonnet-4-6",
"routing": {
"enabled": true,
"light_model": "gemini-flash",
"threshold": 0.35
}
}
}
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.
- Introduced WeCom AIBot channel configuration in config.go with relevant fields.
- Implemented WeCom AIBot channel factory registration in init.go.
- Created unit tests for WeCom AIBot channel functionalities including initialization, start/stop behavior, webhook path handling, message encryption/decryption, and signature generation.
- Set default values for WeCom AIBot configuration in defaults.go.
The serializeMessages() function was not preserving the reasoning_content
field when serializing messages for vision API calls. This caused the
TestProviderChat_PreservesReasoningContentInHistory test to fail.
This fix ensures reasoning_content is included in both text-only messages
and vision messages with media attachments.
Co-authored-by: Zachary Guerrero <zack.grrr@gmail.com>
Add Media field to processOptions, pass msg.Media from inbound
messages through to BuildMessages and serializeMessages so
vision-capable LLMs receive image_url content parts.
Based on work by @as3k in sipeed/picoclaw#555.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add Media []string field to Message struct for image/media URLs
- Implement serializeMessages() to format messages with image_url content parts
- Enables OpenAI-compatible vision APIs to receive image attachments
* fix(tools): allow /dev/null redirection and add read/write sandbox split
- Remove deny pattern that incorrectly blocked redirects to /dev/null
- Expand block device write pattern to cover nvme, mmcblk, vd, xvd,
hd, loop, dm-, md, sr and nbd in addition to sd
- Add safe path whitelist for kernel pseudo-devices so workspace path
check does not reject /dev/null, /dev/zero, /dev/random, /dev/urandom,
/dev/stdin, /dev/stdout and /dev/stderr
- Add allow_read_outside_workspace config option (default true) so file
read and list tools are unrestricted while write tools stay sandboxed
Closes https://github.com/sipeed/picoclaw/issues/964
Closes https://github.com/sipeed/picoclaw/issues/965
Signed-off-by: Huang Rui <vowstar@gmail.com>
* feat(tools): add configurable allow patterns and path whitelists
- Add custom_allow_patterns to exec config so users can exempt specific
commands from deny pattern checks
- Add allow_read_paths and allow_write_paths regex lists to tools config
for whitelisting specific paths outside the workspace
- Introduce whitelistFs that wraps sandboxFs and falls through to hostFs
for paths matching whitelist patterns
- Use variadic constructor signatures to keep backward compatibility
Suggested-by: lxowalle
Signed-off-by: Huang Rui <vowstar@gmail.com>
---------
Signed-off-by: Huang Rui <vowstar@gmail.com>
* fix: return fetched content to LLM in web_fetch tool
WebFetchTool.Execute was setting ForLLM to a summary string
("Fetched N bytes from URL ...") instead of the actual extracted
text. This meant the LLM never saw the page content and could not
answer questions based on fetched web pages.
Return the extracted text in ForLLM so the model can use it.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: put full JSON result in ForLLM, summary in ForUser
Accept suggestion from afjcjsbx: the LLM should receive the full JSON
result (including extracted text) while the user sees a short summary.
Update tests to match the new field assignment.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat(config): Add support for env var configuration
This commit introduces support for two environment variables,
allowing users to override the default paths for picoclaw's home
directory and configuration file.
- `PICOCLAW_CONFIG`: Directly specifies the path to the `config.json` file.
This is initialised first, takes precedence over the hardcoded path, and is ideal
for containerized deployments or custom config management.
- `PICOCLAW_HOME`: Overrides the root directory for all picoclaw data, (except the config)
(e.g., `~/.picoclaw`). This is useful for portable installations or placing
data in non-standard locations.
This change provides greater flexibility for running picoclaw in various environments without
being tied to the default home directory structure.
* `README.md` updated explain PICOCLAW_CONFIG and PICOCLAW_HOME
* docs: translate environment variables section to multiple languages
---------
Co-authored-by: picoclaw <picoclaw@sipeed.com>
- Remove Feishu from webhook channel list in README.md and README.zh.md;
add clarifying note that Feishu uses WebSocket/SDK mode instead
- Replace Chinese text in README.vi.md header with Vietnamese equivalent
- Translate mixed-language WeCom note in README.vi.md to full Vietnamese
- Mark webhook_path as optional (否) in docs/channels/line/README.zh.md
- Remove incorrect yaml struct tags from new-channel example in
pkg/channels/README.md and README.zh.md (config uses json tags only)
- Fix multi-mode initChannel example to use whatsapp/whatsapp_native
(matching the "WhatsApp Bridge vs Native" comment) instead of matrix
- Correct ReasoningChannelID description: list the 12 channels that
have the field and note that PicoConfig does not expose it
* fix(pkg/providers):do regex precompile insteadd on the fly
* fix(providers): replace HTTP-specific regex with standalone status code matcher
The precompiled HTTP regex used uppercase "HTTP" which never matched
because ClassifyError lowercases the input. Replace it with a
case-insensitive word-boundary pattern that matches any standalone
3-digit status code (300-599), which also subsumes the HTTP/x.x case.
Add test case for standalone status code extraction.
* fix(providers): restore http regex and add standalone status code matcher
Restore the http-prefixed regex (without unnecessary (?i) flag since
input is already lowercased by ClassifyError) as a mid-priority pattern
to reduce false positives. Add a standalone word-boundary matcher as a
fallback for bare status codes like "429". Fix test to use lowercased
input matching the actual calling convention.
* perf(tools): move path regex compilation from per-call to package init
The path regex in guardCommand was compiled on every call. Hoist it
to a package-level var (absolutePathPattern) alongside defaultDenyPatterns
in a single var block, so it is compiled once at init time.
* style(tools): move inline comment to fix golines formatting error
- Fix ignored error from SendAndWait call
- Improve error message for unimplemented stdio mode with helpful guidance
- Add TODO comment with reference link for future stdio implementation
The openaiMessage struct and stripSystemParts() were not carrying over
the ReasoningContent field when serializing conversation history for
API requests. This caused thinking models (e.g. kimi-k2.5) to receive
incomplete assistant messages on subsequent turns, resulting in 400
errors from the Moonshot API.
Add the ReasoningContent field to openaiMessage and copy it in
stripSystemParts(). Also add a test to verify reasoning_content is
preserved when sending conversation history.
Fixes#588
Related: #876
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Replace manual temp+rename in writeMeta and rewriteJSONL with the
project's standard fileutil.WriteFileAtomic. This adds fsync before
rename, which is important for flash storage on embedded devices
where power loss can leave zero-length files after an unsynced rename.
- Log a warning when readMessages skips a corrupt line, so operators
can see that data was lost after a crash instead of silently dropping it.
- Document the lossy sanitizeKey mapping (telegram:123 → telegram_123)
as an intentional tradeoff.
* fix(tools): close resp.Body on retry cancel and cache http.Client instances
Fix resp.Body leak in DoRequestWithRetry where req.Body (request) was
incorrectly closed instead of resp.Body (response) on context cancel.
Cache http.Client on web search/fetch provider structs and channel
adapters (WeCom, LINE) to avoid per-call allocation overhead.
* fix(channels): preserve original http client timeouts for LINE and WeCom
Split LINE single 60s client into infoClient (10s) for bot info lookups
and apiClient (30s) for messaging API calls. Lower WeCom cached client
base timeout from 60s to 30s (matching uploadMedia), and ensure it is
always >= the configured ReplyTimeout so the per-request context
deadline remains the effective limit.
* refactor(tools): extract timeout consts and deduplicate WebFetchTool constructors
Address PR review feedback from xiaket:
- Define searchTimeout, perplexityTimeout, fetchTimeout, defaultMaxChars,
and maxRedirects as package-level consts instead of magic numbers.
- Remove misleading "No proxy" comment in NewWebFetchTool.
- Deduplicate NewWebFetchTool by delegating to NewWebFetchToolWithProxy.
* test(utils): add context cancellation test for DoRequestWithRetry
Verify that resp.Body is properly closed when the context is canceled
during retry sleep, covering the C8 resp.Body leak fix.
* fix(utils): close resp in test to satisfy bodyclose linter
* fix(utils): eliminate flakiness in context cancellation retry test
Synchronize cancellation using an onRoundTrip callback from the
transport wrapper instead of a timing-based context timeout. This
ensures the first client.Do completes before cancel fires, so
cancellation always hits during sleepWithCtx.
- MCPTool.Name(): append FNV-32a hash of original (unsanitized) server+tool
names whenever sanitization is lossy or total length exceeds 64 chars,
ensuring names that differ only in disallowed characters remain distinct
- ToolRegistry.Register(): emit warn log when a tool registration overwrites
an existing tool with the same name, making collisions observable
- scripts/test-docker-mcp.sh: switch shebang from #/bin/bash /Users/yuchou/Work/klook-calendar/klook-google-cal-sync/src/googlecalconversrv/bin/start.sh to # for portability on minimal distros and Nix environments
- Avoid logging sensitive cfg.Args in ConnectServer; log args_count instead
- Sanitize server/tool name components in MCPTool.Name() to ensure valid
identifiers for downstream providers (lowercase, [a-z0-9_-] only)
- Add slack as 5th MCP server example in config.example.json
- Move Dockerfile.full and docker-compose.full.yml into docker/ directory
for consistency with existing docker/Dockerfile and docker/docker-compose.yml
- Fix all Makefile docker-* targets to reference correct compose file paths
- Fix docker/docker-compose.full.yml build context (.. ) and volume paths
- Fix scripts/test-docker-mcp.sh compose file path and replace cowsay test
with actual @modelcontextprotocol/server-filesystem MCP server test
- Add early return for empty content to avoid silent no-op
- Split raw markdown before HTML conversion so SplitMessage's
code-fence-aware logic works correctly and HTML tags/entities
are never broken by mid-tag splitting
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Allow APIBase-only config for opencode provider selection (like VLLM)
- Keep moonshot provider on moonshot.cn/v1 default, only use kimi.com/coding/v1 for kimi/kimi-code
- Use url.Parse hostname match for Kimi User-Agent check instead of strings.Contains
- Add opencode to DefaultAPIBase test cases in factory_provider_test.go
- Add opencode migration tests (full config + APIBase-only) in migration_test.go
- Update AllProviders test count to include opencode (18 -> 19)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Deny regex: expand left boundary to match shell separators (;, &&, ||)
to prevent bypass via chained commands like ";format c:"
- Path regex: add "." to initial char class to catch hidden dirs (/.ssh),
add "=" to left boundary to catch flag-attached paths (--file=/etc/passwd)
- Add test: ModelName must match user model for GetModelConfig lookup
- Add test: stripSystemParts preserves reasoning_content in wire format
- Add test: forceCompression avoids orphaning tool result messages
- Add test: deny pattern blocks disk-wiping commands with shell separators
while allowing legitimate --format flags
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Split HTML content into 4000-char chunks before sending to handle cases
where markdown-to-HTML conversion causes messages to exceed Telegram's
4096-character limit. Uses the existing SplitMessage utility which
preserves code block integrity across chunk boundaries.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add "kimi", "kimi-code", "moonshot" provider cases in factory.go
with default API base https://api.kimi.com/coding/v1
- Add Kimi Code API User-Agent header (KimiCLI/0.77) for api.kimi.com
- Add "opencode" provider with default API base https://opencode.ai/zen/v1
- Add "opencode" to recognized HTTP-compatible protocols in factory_provider
- Add Opencode field to ProvidersConfig, IsEmpty, HasProvidersConfig
- Add opencode migration entry in ConvertProvidersToModelList
- Update moonshot fallback API base from api.moonshot.cn to api.kimi.com
1. migration.go: Set ModelName to userModel when provider matches so
GetModelConfig(userModel) can find the entry. Previously the migration
created entries with the provider name as ModelName (e.g. "moonshot")
but lookup used the model name (e.g. "k2p5"), causing "model not found".
2. openai_compat/provider.go: Preserve reasoning_content in conversation
history. Thinking models (e.g. Kimi K2, DeepSeek-R1) return
reasoning_content which must be echoed back. Without it, APIs return
400: "thinking is enabled but reasoning_content is missing".
3. shell.go: Fix deny pattern regex for format/mkfs/diskpart to use
(?:^|\s) instead of \b to avoid matching --format flags.
Fix path extraction regex to use submatch to avoid matching flags
like -rf as paths.
4. loop.go: Adjust forceCompression mid-point to avoid splitting
tool-call/result message pairs, which causes API errors.
Cancel the constructor-created context before overwriting in Start()
to prevent the original cancel function from becoming unreachable.
Move len(processedMsgs) check inside the write lock to eliminate a
data race, and re-insert the current msgID after map reset to prevent
duplicate processing of the in-flight message.
Applies to both WeComBotChannel and WeComAppChannel.
The ctx field was only set in Start(), so tests calling handleMessageCallback
without Start() caused a nil pointer dereference in MessageBus.PublishInbound.
The HTTP request context is canceled as soon as the handler returns the
response, causing PublishInbound to fail with "context canceled" when
processMessage runs asynchronously in a goroutine. Use the channel's
long-lived context (c.ctx) instead.
- Implement POSIX-specific gateway process management in gateway_posix.go
- Implement Windows-specific gateway process management in gateway_windows.go
- Create a menu system in menu.go for user interaction
- Develop model management functionality in model.go, including adding, deleting, and testing models
- Introduce a style configuration in style.go for consistent UI appearance
- Set up the main application entry point in main.go
- Update go.mod and go.sum to include necessary dependencies for tcell and tview
Add GOARM=6 targets for both picoclaw and picoclaw-launcher builds
to support older ARM devices like Raspberry Pi Zero/1.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
A standalone web-based tool for managing picoclaw configuration, OAuth
authentication providers, and gateway process lifecycle. Features include
a sidebar layout with i18n (en/zh) and theme support, real-time gateway
log streaming, startup prerequisites checks, and Windows icon embedding.
Co-authored-by: wj-xiao <meetwenjie@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
- WhatsApp Start(): use deferred cleanup to nil out c.client/c.container
and disconnect/close resources on any error after struct fields are
assigned, preventing stale references and double-close in Stop()
- handleReasoning: treat bus.ErrBusClosed as an expected condition
(DEBUG level) alongside context timeout/cancel, avoiding WARN noise
during normal shutdown
- WhatsApp Send(): detect unpaired state (Store.ID == nil) and return
ErrTemporary instead of attempting to send while QR login is pending
- handleReasoning: check the returned error type (DeadlineExceeded /
Canceled) instead of ctx.Err() to decide log level, so pubCtx
timeouts on a full bus are correctly classified as expected
- Test: fill bus with a short-timeout loop instead of hardcoding the
buffer size (64), making the test resilient to buffer size changes
Move the stopping check and wg.Add(1) inside reconnectMu in
eventHandler, and set the stopping flag under the same lock in Stop().
This makes the two operations atomic with respect to each other,
preventing the race where:
1. eventHandler checks stopping (false)
2. Stop() sets stopping=true and enters wg.Wait() (wg is 0)
3. eventHandler calls wg.Add(1) → panic or goroutine leak
- Use c.runCtx for GetQRChannel so the QR producer is canceled on Stop()
- Add atomic stopping guard to prevent wg.Add/wg.Wait race in eventHandler
- Make Stop() context-aware: disconnect client before waiting, respect ctx deadline
- Reduce reasoning publish log noise: use debug level for expected ctx errors
- Add test for handleReasoning when outbound bus is full (timeout path)
Add a 5-second timeout to handleReasoning's PublishOutbound call so
fire-and-forget goroutines do not block indefinitely when the outbound
bus channel is full. Reasoning output is best-effort; on timeout the
publish is abandoned with a warning log instead of holding the
goroutine alive.
Fixes goroutine leak introduced in #802.
- Move runCtx/runCancel creation before event handler registration and
QR loop so Stop() can cancel at any point during startup
- Replace blocking QR event loop in Start() with a background goroutine
that selects on runCtx.Done(), preventing Start() from hanging
indefinitely when waiting for QR scan
- Track all background goroutines (QR handler, reconnect) with
sync.WaitGroup; Stop() waits for them to finish before releasing
client/container resources
- Cancel runCtx on error paths in Start() to avoid leaked contexts
Fixes resource leak introduced in #655.
* chore(docker): move Dockerfile into docker/ directory
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(docker): add entrypoint script to goreleaser Dockerfile
- entrypoint.sh: on first run (config and workspace both absent) runs
picoclaw onboard then exits for the user to configure; subsequent
starts exec picoclaw gateway directly
- Dockerfile.goreleaser: copy and use entrypoint.sh, run as root
- .goreleaser.yaml: update dockerfile path, add entrypoint.sh to
extra_files so it is included in the docker build context
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore(docker): update docker-compose to use pre-built image and bind mount
- Use docker.io/sipeed/picoclaw:latest instead of building locally
- Replace named volume with bind mount ./data:/root/.picoclaw
- Move docker-compose.yml into docker/ directory
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* docs: update Docker Compose section to reflect new docker/ layout
- Use docker compose -f docker/docker-compose.yml for all commands
- Update setup flow: first run generates docker/data/config.json,
container exits, user edits config, then restarts
- Replace "Rebuild" section with "Update" (docker pull) since the
compose file now uses the pre-built sipeed/picoclaw image
- Apply same changes to README.zh.md
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(docker): use restart: on-failure to prevent restart after first-run setup
unless-stopped restarts the container regardless of exit code, causing
an infinite loop when entrypoint exits 0 after the initial onboard.
on-failure only restarts on non-zero exit (i.e. crashes), so the
container stays stopped after setup until the user restarts it manually.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* docs: sync Docker Compose section across all language READMEs
Apply the same updates as the English/Chinese READMEs:
- Use docker compose -f docker/docker-compose.yml for all commands
- Update setup flow to first-run auto-config pattern
- Replace build/rebuild section with update via docker pull
- Affected: README.fr.md, README.ja.md, README.pt-br.md, README.vi.md
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Define PlaceholderCapable, TypingCapable, and ReactionCapable interfaces
and have BaseChannel.HandleMessage auto-detect and trigger all three as
independent pipelines on inbound messages. This replaces the scattered
manual orchestration code in each channel's handleMessage with a single
unified dispatch in the framework layer.
Changes:
- Add PlaceholderCapable interface to interfaces.go
- Add ReactionCapable + RecordReactionUndo to interfaces.go
- BaseChannel.HandleMessage auto-triggers Typing → Reaction → Placeholder
- Manager gains reactionUndos sync.Map with TTL janitor cleanup
- Telegram: extract SendPlaceholder from manual code, add StartTyping
- Discord: add SendPlaceholder + StartTyping
- Pico: add SendPlaceholder (uses Pico Protocol message.create)
- Slack: extract ReactToMessage from manual code
- OneBot: extract ReactToMessage, remove leaked pendingEmojiMsg sync.Map
- LINE: move group-chat guard into StartTyping, remove manual orchestration
- Config: add Placeholder to PicoConfig; remove from Slack/LINE/OneBot
(no MessageEditor, so placeholder config was dead code)
Port changes that were applied to the old pkg/channels/*.go files on main
to their new locations in channel subpackages:
- telegram: precompile regex, var transcribedText, GetModelName()
- discord: var transcribedText declaration
- onebot: resp.Body.Close(), "canceled" spelling, remove empty line
- slack: named return values in parseSlackChatID
- wecom: remove sendMarkdownMessage dead code
- whatsapp: resp.Body.Close() after Dial
- gateway/helpers: remove unused errors import
Prevents potential backpressure under load when multiple channels
publish concurrently in gateway mode, where SDK callbacks blocking
on a full buffer can cause message loss or timeouts.
- Replace stdlib log.Printf with logger.InfoCF/WarnCF for consistency
with the rest of the codebase (addresses @nikolasdehor review point #3)
- ReleaseAll: clean refToScope/refs mappings even if refs entry is missing
- CleanExpired: guard refToScope lookup before scope cleanup
- Add TestReleaseAllCleansMappingsIfRefsMissing for robustness
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Address review feedback from @alexhoshina and Codex:
- Log sendLoading errors in ticker goroutine instead of discarding
- Only start typing indicator when PlaceholderRecorder is available
to avoid wasted API calls and unnecessary goroutine creation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(skills): add retry mechanism for HTTP requests
Implement a retry mechanism with exponential backoff for HTTP requests in the skill installer. This improves reliability when fetching skills from GitHub by automatically retrying failed requests up to 3 times.
Add comprehensive tests to verify retry behavior under different scenarios including success on different attempts and proper delay between retries.
* fix: improve http request retry logic with status code checks
Add shouldRetry helper function to determine retryable status codes.
Close response body between retry attempts and break early for non-retryable status codes.
* refactor: remove unused BuiltinSkill struct
The struct was not being used anywhere in the codebase, so it's safe to remove it to reduce clutter and improve maintainability.
* refactor(http): move retry logic to utils package
Extract HTTP retry functionality from skills package to utils for better reusability
Add context-aware sleep function and comprehensive tests
* refactor(http): extract retry delay unit to variable
Extract hardcoded retry delay unit to a variable for better testability and flexibility. Update tests to use milliseconds for faster execution while maintaining the same behavior.
* test(http_retry): remove t.Parallel from test cases
* test(http_retry): remove redundant test cases for retry success
The removed test cases for success on second and third attempts were redundant since the retry logic is already covered by other tests. This simplifies the test suite while maintaining coverage.
Change the default value of session.dm_scope from "main" to
"per-channel-peer" to provide better conversation isolation by
default. This prevents context leakage between different users
and channels.
MigrateFromJSON previously called AddFullMessage in a loop, then
renamed the .json file to .json.migrated. If the process crashed
after appending some messages but before the rename, a retry would
re-read the same .json and append all messages again — duplicating
whatever was written before the crash.
Switch to SetHistory which atomically replaces the session contents.
A retry after crash overwrites the partial data instead of appending.
In SetHistory and Compact, the JSONL file was rewritten before updating
the meta file. If the process crashed between the two writes, the meta
still had a large Skip value pointing past the now-shorter JSONL file,
causing GetHistory to return empty — effectively data loss.
Reverse the order: write meta (with Skip=0) first, then rewrite JSONL.
On crash between the two writes, the old uncompacted file is still
intact and GetHistory reads from line 1, returning stale-but-complete
data. The next operation self-corrects.
A crash between the JSONL append and the meta update in addMsg can
leave meta.Count stale (e.g. file has 101 lines but meta says 100).
The previous code only reconciled when Count==0, so a nonzero stale
count was silently trusted, causing keepLast/skip to be calculated
against the wrong total.
Now TruncateHistory always counts the actual lines on disk. This is
cheap (scan without unmarshal) and TruncateHistory is not a hot path.
Changed `go generate ./cmd/picoclaw` to `go generate ./cmd/picoclaw/...`
so that the workspace embed in cmd/picoclaw/internal/onboard is correctly
generated before building.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Implement TypingCapable interface for LINE channel using the
loading animation API (1:1 chats only, no group support).
- Add StartTyping() with 50s periodic refresh and context-based stop
- Integrate PlaceholderRecorder.RecordTypingStop in processEvent
- Skip RecordPlaceholder (LINE has no message edit API)
- Change sendLoading to accept context and return error
- Relax callAPI status check from 200 to 2xx range
Design consulted with Codex (GPT-5.2).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Address feedback from @yinwm for long-running daemon use:
- Replace sync.Map with a fixed-size sharded lock array (64 mutexes).
Keys are mapped via FNV hash, so memory is O(1) regardless of how
many sessions are created over the process lifetime.
- Increase scanner buffer cap from 1 MB to 10 MB. Tool results
(read_file on large files, web search responses) can easily exceed
1 MB. The scanner still starts at 64 KB and only grows as needed.
Address Codex (GPT-5.2) review feedback:
- Start: guard against Interval<=0 or MaxAge<=0 to prevent
time.NewTicker panic on misconfiguration
- ReleaseAll: split into two phases (collect under lock, delete
after unlock) matching CleanExpired pattern
- ReleaseAll: log file removal errors
- Add TestStartZeroIntervalNoPanic and TestStartZeroMaxAgeNoPanic
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- CleanExpired: split into two phases — collect expired entries under
lock, then delete files after releasing the lock to minimize contention
- CleanExpired: guard against zero MaxAge (no-op if unconfigured)
- CleanExpired: log file removal errors instead of silently ignoring
- Start: protect with startOnce to prevent multiple goroutines
- Stop: rename once -> stopOnce for clarity
- cmd_gateway: call mediaStore.Stop() on error path after Start()
- Add TestCleanExpiredZeroMaxAge and double-Start test
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Address review feedback from @Zhaoyikaiii:
- Replace map[string]*sync.Mutex + separate mu with sync.Map.LoadOrStore
for simpler, lock-free session lock management.
- Add skip parameter to readMessages so callers (GetHistory, Compact)
can skip truncated lines without paying the json.Unmarshal cost.
- Add countLines helper for TruncateHistory's count reconciliation,
avoiding full deserialization when only the line count is needed.
Address file growth concern from #711 review: logical truncation via
skip offset is fast but leaves dead lines on disk indefinitely.
Compact() rewrites the JSONL file keeping only active messages, using
the same temp+rename pattern for crash safety. No-op when skip == 0.
The caller (lifecycle manager or agent loop) decides when to trigger
compaction — e.g. when skipped lines exceed active lines.
Read existing sessions/*.json files, convert to JSONL format, and
rename originals to .json.migrated as backup. The migration is
idempotent — second runs skip already-migrated files.
Session keys are read from JSON content (not filenames) so that
sanitized names like telegram_123 correctly map back to telegram:123.
Cover all Store interface methods plus edge cases:
- Basic roundtrip, ordering, empty session, tool calls
- Logical truncation (keep last N, keep zero, keep more than exist)
- SetHistory replacing all + resetting skip offset
- Crash recovery with partial JSON lines
- Persistence across store instances
- Concurrent add+read (10 goroutines x 20 msgs)
- Simulated #704 race (summarizer vs main loop)
- Benchmarks for AddMessage and GetHistory (100/1000 msgs)
Add JSONLStore that persists sessions as .jsonl files (one message per
line) plus .meta.json for summary and truncation offset.
Key design decisions:
- Append-only writes — no full-file rewrites on AddMessage
- Logical truncation via skip offset instead of physical deletion
- Per-session mutex for safe concurrent access
- Crash recovery: malformed trailing lines are silently skipped
- Atomic metadata writes using temp+rename
Zero new dependencies — pure stdlib.
Refs #711
Introduce a backend-agnostic Store interface in pkg/memory/ that maps
one-to-one with the current SessionManager API. Each method is atomic
— no separate Save() call needed.
Refs #711
* fix: remove redundant tools definitions from system prompt
Tools are already provided to the LLM via JSON schema through
ToProviderDefs(), so the text-based tools section in the system
prompt is redundant.
This removes the buildToolsSection() logic and the tools field
from ContextBuilder, reducing system prompt length while maintaining
the "ALWAYS use tools" rule reminder.
Fixes#731
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: correct spelling 'initialized' (was 'initialised')
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Whitespace is a linter that checks for unnecessary newlines at the start and end of functions, if, for, etc.
Signed-off-by: Kai Xia <kaix+github@fastmail.com>
* refactor(cli): migrate to Cobra-based command structure
Refactor CLI to use Cobra instead of manual os.Args parsing.
- Introduce root command and structured subcommands under cmd/picoclaw/internal
- Convert agent, auth, cron, gateway, migrate, onboard, skills, status and version to Cobra commands
- Replace manual flag parsing with Cobra flags
- Remove direct os.Args usage from command handlers
- Keep existing command behavior and output semantics
This change focuses on CLI structure and maintainability.
No business logic changes intended.
* chore(cli): remove version2 alias and make cobra a direct dependency
* test(cli): add basic command tests
- Add tests for CLI command tree and flag parsing
- Align LDFLAGS injection path for version info
- Remove unused manual help function
* test: migrate command tests to testify assertions
Replace standard library testing error checks (t.Error*, t.Fatalf)
with assert/require from stretchr/testify across all cobra command tests
for improved readability and consistency.
* fix(cli): make linter happy
* test: avoid duplication in windows config path test
* test: simplify allowed command checks using slices.Contains
* fix(skills): register subcommands during command construction
- Move subcommand registration out of PersistentPreRunE
- Ensure `picoclaw skills <subcommand>` resolves correctly
- Minor install command and test cleanups
* refactor(cli): address review feedback and improve command clarity
* fix(authLogoutCmd): rm os.Exit
Avoid rebuilding the entire system prompt on every BuildMessages() call
by caching the static portion (identity, bootstrap, skills summary,
memory) and only recomputing it when workspace source files change.
Key changes:
- ContextBuilder caches the static prompt behind an RWMutex with
double-checked locking. Source file changes are detected via cheap
os.Stat mtime checks so no explicit invalidation is needed.
- Track file existence at cache time (existedAtCache map) so that
newly created or deleted bootstrap/memory files also trigger a
rebuild — the old modifiedSince() silently returned false on
os.IsNotExist.
- Walk the skills directory recursively with filepath.WalkDir to
catch content-only edits at any nesting depth; directory mtime
alone misses in-place file modifications on most filesystems.
- ToolRegistry.sortedToolNames() sorts tool names before iteration,
ensuring deterministic tool definition order across calls — a
prerequisite for LLM-side prefix/KV cache reuse.
- Merge all context (static + dynamic + summary) into a single
system message for provider compatibility: the Anthropic adapter
extracts messages[0] as the top-level system parameter, and Codex
reads only the first system message as instructions.
- Fix a data race in BuildMessages() where cachedSystemPrompt was
read without holding the lock in a debug log statement.
- Add tests: single system message invariant, mtime auto-invalidation,
new-file creation detection, skill file content change, explicit
InvalidateCache, cache stability, concurrent access (20 goroutines
x 50 iterations, passes go test -race), and a benchmark.
Rename fastID() to uniqueID() with a security caveat comment clarifying
the ID is not cryptographically secure, and add unit tests for the
refactored index-based split helper functions.
The spawn tool accepts empty strings as valid task arguments, which
causes a subagent to run with no meaningful work. The subagent's
completion message is then routed back to the originating channel
(e.g. Signal, Discord), where the main agent processes it and may
hallucinate an unrelated response that gets sent to users.
Validate that the task parameter is non-empty after trimming whitespace.
Related: #545
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
HTTP timeouts (context deadline exceeded, Client.Timeout) were
incorrectly classified as context window errors, triggering useless
history compression. Replace broad substring checks ("context",
"token", "length") with specific patterns for real context limit
errors and explicitly exclude timeout errors from that path.
Additionally, timeout errors were not retried at all — the retry
loop only handled context window errors. Now timeouts are retried
up to 2 times with exponential backoff (5s, 10s).
Walk backwards over preceding tool messages to find the nearest assistant
with ToolCalls, instead of only checking the immediate predecessor. Add
unit tests for sanitizeHistoryForProvider covering key edge cases.
Add background TTL-based cleanup (L2 safety net) directly into
FileMediaStore so file deletion and in-memory ref removal happen
atomically under the same mutex, preventing dangling references.
- Add storedAt timestamp and refToScope reverse map to mediaEntry
- Add CleanExpired() for atomic TTL-based expiration
- Add Start()/Stop() for background goroutine lifecycle
- Add MediaCleanupConfig (enabled, max_age, interval) to config
- Wire up in cmd_gateway.go with config-driven defaults
- Add 8 new tests including concurrent cleanup safety
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
make test and make vet fail on a fresh clone because the go:embed
workspace directory does not exist until go generate runs. The build
target already depends on generate, but test and vet did not.
Also fixes the test target comment which incorrectly read '## fmt: Format Go code'.
Translate Chinese comments to English in qq, slack, and telegram channel
implementations, following the translation work done in PR #697. The
original PR modified the old parent package files, but these have been
moved to subpackages during the refactor, so translations are applied
to the new locations.
* chore: Update default host bindings from 0.0.0.0 to 127.0.0.1 for various services and examples.
* config: Update default host bindings to 0.0.0.0 for improved Docker accessibility and add related documentation.
* chore: resolve conflict
* chore: remove link
* docs: Add a tip for Docker users regarding gateway host configuration to the French and Vietnamese READMEs.
* fix: typo issue
* docs: Update Chinese README.zh.md.
- Update Dockerfile to use golang:1.25-alpine to match go.mod (go 1.25.7)
- Optimize logger by avoiding string concatenation in file writes
- Add explicit empty string assignment for fieldStr when no fields
These changes improve build consistency and reduce memory allocations
in the hot logging path, which is important for the project's goal
of running on resource-constrained devices (<10MB RAM).
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
- Drain buffered messages in MessageBus.Close() so they aren't silently lost
- Replace all context.TODO() with context.WithTimeout(5s) across 7 call sites
- Fix OneBot pending channel leak: send nil sentinel in Stop() and handle
nil response in sendAPIRequest() to unblock waiting goroutines
* chore: Update default host bindings from 0.0.0.0 to 127.0.0.1 for various services and examples.
* config: Update default host bindings to 0.0.0.0 for improved Docker accessibility and add related documentation.
* refactor: reimplement filesystem tools with `os.OpenRoot` for enhanced security and simplified path validation.
* chore: revert other PR content from this branch
* docs: Update Chinese README.
* docs: Update Chinese README.
* docs: Update Chinese README.
* refactor: Reorder filesystem helper functions, extract directory entry formatting logic, and enhance `WriteFileTool`'s result message.
* feat: Enhance `mkdirAllInRoot` to prevent creating directories over existing files and add tests for directory creation functionality.
* Refactor filesystem tools to use a `fileReadWriter` interface for both host and sandboxed I/O, improving atomic writes and error handling.
* refactor: unify filesystem read/write operations with atomic write guarantees and clearer naming.
* refactor: rename `appendFileWithRW` function to `appendFile`
* refactor: unify filesystem access by introducing a `fileSystem` interface and updating tools to use it directly, removing `os.Root` dependency from `sandboxFs`.
* chore: run make fmt
* fix: `validatePath` now returns an error when the workspace is empty.
The configuration field for specifying the model has been renamed from
"model" to "model_name" for better clarity and consistency with the
model_list configuration.
A GetModelName() accessor method has been added to maintain backward
compatibility. Existing configurations using the old "model" field will
continue to work correctly.
This change affects:
- Configuration structure (AgentDefaults struct)
- All references across the codebase
- Documentation in all language variants
- Example configuration files
Introduce SenderInfo struct and pkg/identity package to standardize user
identification across all channels. Each channel now constructs structured
sender info (platform, platformID, canonicalID, username, displayName)
instead of ad-hoc string IDs. Allow-list matching supports all legacy
formats (numeric ID, @username, id|username) plus the new canonical
"platform:id" format. Session key resolution also handles canonical
peerIDs for backward-compatible identity link matching.
- MediaStore: use full UUID to prevent ref collisions, preserve and
expose metadata via ResolveWithMeta, include underlying OS errors
- Agent loop: populate MediaPart Type/Filename/ContentType from
MediaStore metadata so channels can dispatch media correctly
- SplitMessage: fix byte-vs-rune index mixup in code block header
parsing, remove dead candidateStr variable
- Pico auth: restrict query-param token behind AllowTokenQuery config
flag (default false) to prevent token leakage via logs/referer
- HandleMessage: replace context.TODO with caller-propagated ctx,
log PublishInbound failures instead of silently discarding
- Gateway shutdown: use fresh 15s timeout context for StopAll so
graceful shutdown is not short-circuited by the cancelled parent ctx
Message splitting is exclusively a Manager responsibility. Moving it
into the channels package eliminates the cross-package dependency and
aligns with the refactoring plan.
Phase 10: Define TypingCapable, MessageEditor, PlaceholderRecorder interfaces.
Manager orchestrates outbound typing stop and placeholder editing via preSend.
Migrate Telegram, Discord, Slack, OneBot to register state with Manager instead
of handling locally in Send. Phase 7: Add native WebSocket Pico Protocol channel
as reference implementation of all optional capability interfaces.
Add unified ShouldRespondInGroup to BaseChannel, replacing scattered
per-channel group filtering logic. Introduce GroupTriggerConfig (with
mention_only + prefixes), TypingConfig, and PlaceholderConfig types.
Migrate Discord MentionOnly, OneBot checkGroupTrigger, and LINE
hardcoded mention-only to the shared mechanism. Add group trigger
entry points for Slack, Telegram, QQ, Feishu, DingTalk, and WeCom.
Legacy config fields are preserved with automatic migration.
Remove SetTranscriber and inline transcription logic from 4 channels
(Telegram, Discord, Slack, OneBot) and the gateway wiring. Voice/audio
files are still downloaded and stored in MediaStore with simple text
annotations ([voice], [audio: filename], [file: name]). The pkg/voice
package is preserved for future Agent-level transcription middleware.
Add outbound media sending capability so the agent can publish media
attachments (images, files, audio, video) through channels via the bus.
- Add MediaPart and OutboundMediaMessage types to bus
- Add PublishOutboundMedia/SubscribeOutboundMedia bus methods
- Add MediaSender interface discovered via type assertion by Manager
- Add media dispatch/worker in Manager with shared retry logic
- Extend ToolResult with Media field and MediaResult constructor
- Publish outbound media from agent loop on tool results
- Implement SendMedia for Telegram, Discord, Slack, LINE, OneBot, WeCom
Merge 3 independent channel HTTP servers (LINE :18791, WeCom Bot :18793,
WeCom App :18792) and the health server (:18790) into a single shared
HTTP server on the Gateway address. Channels implement WebhookHandler
and/or HealthChecker interfaces to register their handlers on the shared
mux. Also change Gateway default host from 0.0.0.0 to 127.0.0.1 for
security.
PublishInbound/PublishOutbound held RLock during blocking channel sends,
deadlocking against Close() which needs a write lock when the buffer is
full. ConsumeInbound/SubscribeOutbound used bare receives instead of
comma-ok, causing zero-value processing or busy loops after close.
Replace sync.RWMutex+bool with atomic.Bool+done channel so Publish
methods use a lock-free 3-way select (send / done / ctx.Done). Add
context.Context parameter to both Publish methods so callers can cancel
or timeout blocked sends. Close() now only sets the atomic flag and
closes the done channel—never closes the data channels—eliminating
send-on-closed-channel panics.
- Remove dead code: RegisterHandler, GetHandler, handlers map,
MessageHandler type (zero callers across the whole repo)
- Add ErrBusClosed sentinel error
- Update all 10 caller sites to pass context
- Add msgBus.Close() to gateway and agent shutdown flows
- Add pkg/bus/bus_test.go with 11 test cases covering basic round-trip,
context cancellation, closed-bus behavior, concurrent publish+close,
full-buffer timeout, and idempotent Close
* feat: integrate Tavily search
* fix: set include_raw_content to false in Tavily search as wealready get relevant data inside content
* refactor: update Go type declarations to `any`, apply formatting fixes.
Define sentinel error types (ErrNotRunning, ErrRateLimit, ErrTemporary,
ErrSendFailed) so the Manager can classify Send failures and choose the
right retry strategy: permanent errors bail immediately, rate-limit
errors use a fixed 1s delay, and temporary/unknown errors use exponential
backoff (500ms→1s→2s, capped at 8s, up to 3 retries). A per-channel
token-bucket rate limiter (golang.org/x/time/rate) throttles outbound
sends before they hit the platform API.
Channels previously deleted downloaded media files via defer os.Remove,
racing with the async Agent consumer. Introduce MediaStore to decouple
file ownership: channels register files on download, Agent releases them
after processing via ReleaseAll(scope).
- New pkg/media with MediaStore interface + FileMediaStore implementation
- InboundMessage gains MediaScope field for lifecycle tracking
- BaseChannel gains SetMediaStore/GetMediaStore + BuildMediaScope helper
- Manager injects MediaStore into channels; AgentLoop releases on completion
- Telegram, Discord, Slack, OneBot, LINE channels migrated from defer
os.Remove to store.Store() with media:// refs
Move message splitting from individual channels (Discord) to the Manager
layer via per-channel worker goroutines. Each channel now declares its
max message length through BaseChannelOption/MessageLengthProvider, and
the Manager automatically splits oversized outbound messages before
dispatch. This prevents one slow channel from blocking all others.
- Add WithMaxMessageLength option and MessageLengthProvider interface
- Set platform-specific limits (Discord 2000, Telegram 4096, Slack 40000, etc.)
- Convert SplitMessage to rune-aware counting for correct Unicode handling
- Replace single dispatcher goroutine with per-channel buffered worker queues
- Remove Discord's internal SplitMessage call (now handled centrally)
Add bus.Peer struct and explicit Peer/MessageID fields to InboundMessage,
replacing the implicit peer_kind/peer_id/message_id metadata convention.
- Add Peer{Kind, ID} type to pkg/bus/types.go
- Extend InboundMessage with Peer and MessageID fields
- Change BaseChannel.HandleMessage signature to accept peer and messageID
- Adapt all 12 channel implementations to pass structured peer/messageID
- Simplify agent extractPeer() to read msg.Peer directly
- extractParentPeer unchanged (parent_peer still via metadata)
Add comprehensive unit tests for the ToolRegistry covering registration,
lookup, execution, context injection, async callbacks, schema generation,
provider definition conversion, and concurrent access.
Fix a defensive edge case in Truncate where a negative maxLen would cause
a slice bounds panic, and add table-driven tests covering boundary
conditions, zero/negative lengths, and Unicode handling.
Co-authored-by: Cursor <cursoragent@cursor.com>
Mistral's API strictly validates tool_calls in assistant messages and
rejects non-standard fields. The ToolCall struct had Name and Arguments
as top-level JSON fields, duplicating data already in Function.Name
and Function.Arguments. OpenAI silently ignored these extras but
Mistral returns 422.
Change json tags to "-" so these internal fields are no longer
serialized to API payloads while remaining available in Go code.
Add Mistral as a first-class provider alongside the 17 existing ones.
Mistral uses the OpenAI-compatible API at https://api.mistral.ai/v1
with provider-specific model prefix stripping (mistral/model → model).
Changes:
- Add Mistral to ProvidersConfig, IsEmpty(), HasProvidersConfig()
- Add mistral entry in default model_list (defaults.go)
- Add mistral protocol in factory_provider.go and getDefaultAPIBase()
- Add mistral prefix stripping in openai_compat normalizeModel()
- Add mistral case in legacy factory.go resolveProviderSelection()
- Add mistral migration entry in ConvertProvidersToModelList()
- Add mistral to supported providers in migrate/config.go
- Add mistral section in config.example.json
- Update AllProviders test (17 → 18 providers)
Tested end-to-end with mistral-small-latest model.
When users migrate from the legacy `providers` config to the new
`model_list` format, voice transcription silently breaks on Telegram,
Discord and Slack channels.
The gateway was reading the Groq API key exclusively from
`cfg.Providers.Groq.APIKey`, which is empty once the key is defined
only inside a `model_list` entry. The transcriber was never initialized,
so voice messages fell back to a plain `[voice]` placeholder.
This fix also scans `model_list` for any entry whose `model` field
starts with `groq/` and uses its `api_key` as a fallback, preserving
full backward compatibility with the legacy `providers.groq` field.
Models like Moonshot kimi-k2.5 and DeepSeek-R1 return a
reasoning_content field in assistant messages. When thinking is enabled,
the API requires this field to be echoed back in subsequent requests.
PicoClaw was silently dropping it, causing 400 errors on tool-call
round-trips.
- Add ReasoningContent to Message and LLMResponse types
- Parse reasoning_content in openai_compat parseResponse()
- Carry reasoning_content through assistant tool-call messages
- Add unit test for reasoning_content parsing
Fixes#588
A race could occur when Close() called conn.Session.Close() concurrently
with an in-flight conn.Session.CallTool(), leading to undefined behavior.
Fix by adding a sync.WaitGroup to Manager:
- CallTool increments the WaitGroup while holding the read lock (after
checking m.closed), ensuring no new calls are counted after Close sets
the flag
- Close sets m.closed=true, releases the write lock, then waits for all
in-flight calls to finish via wg.Wait() before closing sessions
ListAgentIDs() was called on every iteration of the inner tool loop,
causing repeated allocations. Capture the slice once and reuse it for
both agentCount and the registration loop.
Previously Close() discarded all underlying errors and returned only
'failed to close N server(s)', making debugging impossible.
Now each error wraps the server name and original cause, and all errors
are joined so callers can inspect the full failure list.
A line like '=value' would result in envVars[""] = "value", producing
an invalid environment entry for the child process. Return an error
instead when the key is empty.
Add back filesystem, github, brave-search, and postgres as example MCP
server configurations. These were removed from DefaultConfig() to reduce
memory footprint, but should remain in the example config as documentation
for users setting up MCP servers.
CallTool can return (nil, nil) if the underlying MCP library misbehaves.
Without a nil check, result.IsError would panic. Return an explicit error
ToolResult instead.
Avoid building zero services when all services are gated behind profiles.
Without an explicit service target, 'docker compose build' silently skips
all profile-gated services, causing subsequent 'docker compose run' to
use stale or missing images.
- Fix DingTalk section referencing "QQ numbers" instead of DingTalk user IDs
- Fix Anthropic example showing OAuth when code uses paste-token auth
- Replace OpenClaw references in ANTIGRAVITY_AUTH.md with actual PicoClaw paths and Go patterns
- Fix auth file path from auth-profiles.json to auth.json in ANTIGRAVITY_USAGE.md
- Remove non-existent approval tool from tools_configuration.md, add skills tool docs
- Update Quick Start configs in fr/pt-br/vi/ja translations to use model_list format
- Fix allowFrom camelCase to allow_from in fr/pt-br translations
- Fix camelCase config keys in ja translation
- Update zh/ja web search config from old flat format to brave/duckduckgo
- Fix broken ClawdChat link and trailing commas in zh translation
- Add missing qwen/cerebras providers to fr/pt-br/vi translation tables
- Add missing protocol prefixes to migration guide
- Fix typos in community roadmap
Brave Search discontinued free tier on Feb 12, 2026.
Updated all README references to reflect paid pricing.
Emphasized SearXNG as free alternative.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Update config.example.json to include SearXNG web search provider
configuration alongside existing Brave, DuckDuckGo, and Perplexity options.
This ensures users have a complete reference for all available search
providers when setting up their PicoClaw instance.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Update README to document the new SearXNG search provider option alongside
existing Brave, DuckDuckGo, and Perplexity providers.
Changes:
- Document provider priority order: Perplexity > Brave > SearXNG > DuckDuckGo
- Add SearXNG configuration examples in Quick Start and Full Config sections
- Expand "Get API Keys" section with all 4 search provider options
- Enhance troubleshooting section with detailed setup instructions for each provider
- Add SearXNG to API Key Comparison table (unlimited/self-hosted)
SearXNG benefits documented:
- Zero cost with no API fees or rate limits
- Privacy-focused self-hosted solution
- Aggregates 70+ search engines for comprehensive results
- Solves datacenter IP blocking issues on Oracle Cloud, GCP, AWS, Azure
- No API key required, just deploy and configure base URL
This documentation complements the code implementation in commit e7d8975.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* feat(discord): add mention_only option for @-mention responses
Add MentionOnly config option to Discord channel. When enabled, the bot
only responds when explicitly @-mentioned, useful for shared servers.
- Add MentionOnly bool field to DiscordConfig
- Store botUserID on startup for mention checking
- Check m.Mentions before processing messages when MentionOnly is true
- Update config example and README documentation
* fix(discord): resolve race condition and strip mention from content
- Get botUserID before opening session to avoid race condition
- Add stripBotMention to remove @mention from message content
- Handles both <@USER_ID> and <@!USER_ID> mention formats
* fix(discord): skip mention_only check for DMs
DMs should always be responded to regardless of mention_only setting.
Added check to skip the mention_only logic when GuildID is empty.
* Update README.md
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---------
Co-authored-by: Hua Audio <161028864+Huaaudio@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Implements SearXNG as a third web search provider to address Oracle Cloud
datacenter IP blocking issues and provide a cost-free, self-hosted alternative
to commercial search APIs.
Changes:
- Add SearXNGConfig struct with Enabled, BaseURL, and MaxResults fields
- Implement SearXNGSearchProvider with JSON API integration
- Update provider priority: Perplexity > Brave > SearXNG > DuckDuckGo
- Wire SearXNG configuration through agent tool registration
- Add default config values (disabled by default, empty BaseURL)
Benefits:
- Solves DuckDuckGo datacenter IP blocking (138 bytes redirect responses)
- Zero-cost alternative to Brave Search API ($5/1000 queries)
- Self-hosted solution with 70+ aggregated search engines
- Privacy-focused with no rate limits or API keys required
- Ideal for Oracle Cloud, GCP, AWS, and Azure VM deployments
The implementation follows the existing provider interface pattern and
maintains backward compatibility with all existing search providers.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
config.example.json was missing three sections that exist in the Go
config structs and defaults:
- tools.web.duckduckgo: DuckDuckGo is enabled by default in
defaults.go and requires no API key (free search provider), but
users who copy the example config silently lose it since the
section was omitted.
- tools.exec: The ExecConfig struct supports enable_deny_patterns
and custom_deny_patterns for security hardening, but users had
no way to discover these options from the example.
- channels.qq: The QQ channel was the only channel in ChannelsConfig
missing from the example while all others were present.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(onebot): add metadata for direct and group message handling
* fix(qq): add metadata for direct and group message handling
* fix(dingtalk): add metadata for direct and group message handling
* fix(feishu): add metadata for direct and group message handling
* fix(whatsapp): add metadata for direct and group message handlinga
* fix(line): add metadata for direct and group message handling
* fix(maixcam): add metadata for person detection handling
* fix(config): add default session configuration with DMScope
Resolved conflicts:
- pkg/config/config.go: Removed duplicate DefaultConfig() (already in defaults.go)
- pkg/config/defaults.go: Updated Temperature to *float64 (nil default)
Upstream changes included:
- Temperature changed from float64 to *float64 (nil means use provider default)
- New HeartbeatConfig and DevicesConfig
- Various agent and tool improvements
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Address review comment from @xiaket - the "Supported providers" message
was printed in multiple places. Now extracted as a constant.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace all claude-sonnet-4 references with claude-sonnet-4.6 across
codebase including documentation, tests, and configuration examples.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove duplicate model_name check in ValidateModelList to support
load balancing feature where multiple configs can share the same
model_name for round-robin selection.
Update tests to reflect the new behavior.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add github_copilot to the supportedProviders map to match
the providers handled in MergeConfig.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Remove sync.RWMutex and rrCounters from Config struct
- Simplify GetModelConfig to use global atomic counter for load balancing
- Remove unnecessary locks from HasProvidersConfig, SaveConfig, etc.
- Add buildModelWithProtocol helper to handle models with existing prefix
- Fix TestCreateProviderReturnsHTTPProviderForOpenRouter to use model_list
- Upgrade all Claude 3 references to Claude 4 across documentation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Change "removed in v2.0" to "removed in a future version"
for the deprecated providers section.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Auth fixes:
- Fix OpenAI/Anthropic OAuth and token login to update ModelList
- Fix logout to clear AuthMethod in ModelList
- Add helper functions: isOpenAIModel, isAnthropicModel, isAntigravityModel
- Fix slice bounds panic in isAntigravityModel using strings.HasPrefix
- All auth operations now preserve existing model_list configuration
Factory provider fixes:
- Add OAuth support for openai protocol in CreateProviderFromConfig
- CodexAuthProvider is now used when auth_method is oauth/token
Default model updates:
- OpenAI login: set default model to gpt-5.2
- Anthropic login: set default model to claude-sonnet-4
- Antigravity login: set default model to gemini-flash (remove provider field)
Model changes:
- Change default OpenAI model from gpt-4o to gpt-5.2
- gpt-5.2 is compatible with Codex API (chatgpt.com backend)
- Update all README files, config examples, and migration code
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Include all 17 supported providers in default config as templates
- Each entry has model_name, model, api_base, and empty api_key
- Add comments with API key links for each provider
- Keep onboard message simple (only OpenRouter and Ollama)
- Fix duplicate model_name (cerebras-llama-3.3-70b)
Providers included:
Zhipu, OpenAI, Anthropic, DeepSeek, Gemini, Qwen, Moonshot,
Groq, OpenRouter, NVIDIA, Cerebras, Volcengine, ShengsuanYun,
Antigravity, GitHub Copilot, Ollama, VLLM
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: add MaxTokens and Temperature fields to AgentInstance and update related logic
* feat: add MaxTokens and Temperature options to SubagentManager and update tool loop logic
* feat: add default temperature handling and update related tests
* feat: allow temperature 0 and distinguish unset
* fix: format MockLLMProvider struct in subagent_tool_test.go
Add comprehensive Model Configuration (model_list) section to all 6 language versions:
- English, Chinese (zh), French (fr), Japanese (ja), Portuguese (pt-br), Vietnamese (vi)
Key additions:
- Complete vendor list (17 providers) with protocol prefixes and API base URLs
- Basic and vendor-specific configuration examples
- Load balancing documentation
- Migration guide from legacy providers config
- Multi-agent support design rationale
Replace Chinese vendor names with English/Pinyin in non-Chinese versions for better readability.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Update model configurations to use provider-specific protocols (zhipu, vllm,
gemini, shengsuanyun, deepseek, volcengine) instead of using the generic
"openai" protocol for all providers. This change ensures each provider
uses its correct protocol identifier and model naming convention.
Add support for persisting thought_signature metadata from Google/Gemini 3
models. This introduces ExtraContent and GoogleExtra types to handle
provider-specific metadata, and ensures thought signatures are properly
preserved through the tool call lifecycle.
- Move provider creation logic to factory_provider.go with protocol-based approach
- Add OpenAIProviderConfig with WebSearch support and embedded ProviderConfig
- Add maxTokensField to OpenAI-compatible provider for configurable token field
- Introduce new providers: Ollama, DeepSeek, GitHubCopilot, Antigravity, Qwen
- Remove redundant CreateProvider function from factory.go
- Add ThoughtSignature field to FunctionCall for tool response handling
- Remove duplicate Name field assignment in tool loop
- Update tests to reflect new provider configuration structure
Append emergency compression note to the original system prompt
instead of creating a separate system message. Some APIs like
Zhipu reject two consecutive system messages.
* fix: keep Discord typing indicator alive during agent processing
Discord's ChannelTyping() expires after ~10s, but agent processing
(LLM + tool execution) typically takes 30-60s+. Replace single-fire
ChannelTyping() with a self-managed typing loop inside DiscordChannel.
- startTyping(chatID): goroutine refreshes ChannelTyping every 8s
- stopTyping(chatID): called in Send() when response is dispatched
- Stop() cleans up all typing goroutines on shutdown
- startTyping placed after all early returns to prevent goroutine leaks
Typing lifecycle fully contained in channel layer, no interface changes.
Fixes#390
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: add goroutine safety to Discord typing indicator
- Add 5-minute timeout as safety net to prevent indefinite goroutine leaks
when agent produces no outbound message (empty response, panic, etc.)
- Listen on c.ctx.Done() so goroutine exits when channel context is cancelled
- Log ChannelTyping() errors at debug level for diagnostics (rate limits, session closed)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Use cfg.WorkspacePath() as a fallback when defaultAgent is nil or
its Workspace is empty. This ensures MCP servers with relative
envFile paths can always resolve them correctly, even when agents
haven't been fully initialized yet.
Previously, workspacePath would be an empty string in these cases,
causing relative envFile paths to fail to resolve. Now the fallback
guarantees a valid workspace path is always provided to
LoadFromMCPConfig.
Addresses Copilot code review feedback.
Add a closed flag to the Manager struct to prevent CallTool from
accessing server connections after Close has been called. The flag
is checked within the RLock in CallTool to ensure thread-safety.
Previously, CallTool could obtain a server reference using RLock,
then that reference could be closed by Close() running concurrently,
leading to use-after-close errors. Now:
1. CallTool checks the closed flag before accessing servers
2. Close sets the closed flag before closing connections
3. CallTool directly accesses m.servers within the lock instead
of using GetServer() to avoid releasing the lock prematurely
This ensures CallTool will not use a server connection that is
being closed or has been closed.
Addresses Copilot code review feedback.
Use a map to merge environment variables with guaranteed override
behavior. Config variables (cfg.Env) now properly override file
variables (envFile), which in turn override parent process environment.
Previously, simply appending to a slice could result in duplicate
variables, and while most systems use the last occurrence, this
behavior is not guaranteed and could lead to unexpected results.
Addresses Copilot code review feedback.
Change 'envFile' to 'env_file' to maintain consistency with the rest
of the codebase which uses snake_case for JSON field names (e.g.,
'api_key', 'api_base', 'max_results', 'exec_timeout_minutes').
Addresses Copilot code review feedback.
Separate tool counting metrics for better clarity:
- unique_tools: number of distinct MCP tools
- total_registrations: total tool registrations across all agents
- agent_count: number of agents receiving the tools
Previously, tool_count was misleading as it showed total registrations,
making it appear that more unique tools were registered than actually exist.
Addresses Copilot code review feedback.
Move defer cleanup inside else block to only clean up when MCP servers
are successfully initialized. This prevents unnecessary cleanup attempts
when LoadFromMCPConfig fails.
Addresses Copilot code review feedback.
Resolved conflicts in:
- config/config.example.json: Added empty MCP config block
- pkg/config/config.go: Added MCP config structures to new ToolsConfig
- pkg/agent/loop.go: Integrated MCP tools with new AgentRegistry architecture
MCP tools now register to all agents in the registry during startup.
* fix: change BotStatus type to json.RawMessage and add isAPIResponse function
* feat(onebot): add rich media, API callback, keepalive and voice transcription
Comprehensive improvements to the OneBot channel for better NapCatQQ
compatibility:
- Add echo-based API callback mechanism (sendAPIRequest) for
request/response correlation via pending map
- Add WebSocket ping/pong keepalive (30s ping, 60s read deadline)
- Fetch bot self ID via get_login_info on connect/reconnect
- Refactor parseMessageContentEx into parseMessageSegments supporting
image, record, video, file, reply, face, forward segments
- Add voice transcription via Groq transcriber (SetTranscriber)
- Switch to message segment array format for sending with auto reply
quote via lastMessageID tracking
- Add message_sent event handling and detailed notice event processing
(recall, poke, group increase/decrease, friend add, etc.)
- Use sync/atomic for echoCounter, optimize listen() lock pattern
- Clean up pending callbacks on Stop(), defer temp file cleanup
- Mount Groq transcriber on OneBot channel in main.go gateway
* feat(onebot): add user ID allowlist check for incoming messages
- Currently, the agent does not respond to messages sent by users outside the allowlist.
* refactor(onebot): simplify channel implementation and add emoji reaction
- onebot.go from 1179 to 980 lines (~17%)
When no provider field is set but model is specified, use the user's model
as ModelName for the first provider. This maintains backward compatibility
with old configs that relied on implicit provider selection and ensures
GetModelConfig(model) can find the model by its configured name.
Add validation to ensure model_name is unique across all entries in
model_list. This prevents potential conflicts when multiple model
configs share the same model_name identifier.
- Preserve user's configured model during config migration (issue #5)
- Simplify ExtractProtocol using strings.Cut
- Extract NormalizeToolCall to shared utility, removing ~70 lines of duplicate code
- Clean up unused fields in providerMigrationConfig struct
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Accept hard upper limit (maxLen) instead of pre-subtracted value
- Caller now passes actual platform limit (e.g., 2000 for Discord)
- Internal buffer of 500 chars is handled within message.go
- Preferred split at maxLen - 500, may extend to maxLen for code blocks
- Never exceeds maxLen, no more mental math for callers
- Move FindLast, findLast, and SplitMessage from discord.go to pkg/utils/message.go
- Update discord.go to use utils.SplitMessage()
- Makes splitting logic reusable across other channels
1. Add VLLM default API base (http://localhost:8000/v1)
- Previously returned empty string, causing provider creation to fail
2. Implement MaxTokensField configuration
- Add maxTokensField field to HTTPProvider
- Add NewHTTPProviderWithMaxTokensField constructor
- Use configured field name for max_tokens parameter
- Fallback to model-based detection for backward compatibility
3. Add tests for VLLM, deepseek, ollama default API bases
Example config usage:
{
"model_name": "glm-4",
"model": "openai/glm-4",
"max_tokens_field": "max_completion_tokens"
}
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Move OAuth helper functions to factory_provider.go
- Add auto-migration in LoadConfig: old providers -> model_list
- Add Workspace field to ModelConfig for CLI-based providers
- Fix OAuth handling to use auth store instead of raw APIKey
- Update tests to use new model_list configuration format
This eliminates the giant switch-case in legacy_provider.go,
achieving the goal of "zero-code provider addition" from the
design document (issue #283).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Refactor command handlers into separate files to improve code organization
and maintainability. Each command (agent, auth, cron, gateway, migrate,
onboard, skills, status) now has its own dedicated file.
Restructure provider creation to support new model_list configuration
system that enables zero-code addition of OpenAI-compatible providers.
Move legacy provider logic to separate file for backward compatibility.
Move configuration functions from config.go to separate files
(defaults.go, migration.go) for better organization.
Resolve conflicts in pkg/providers/types.go and pkg/agent/loop.go:
- types.go: use protocoltypes aliases from PR #213, keep fallback types
- loop.go: drop old single-agent createToolRegistry (replaced by multi-agent pattern)
Refactor to align with PR #213 patterns:
- instance.go: use NewExecToolWithConfig (accept full config for deny patterns)
- registry.go: pass full config to NewAgentInstance
- loop.go: add Perplexity web search options to registerSharedTools
Merge upstream/main into refactor/provider-protocol-122.
Resolve http_provider.go conflict (keep thin delegate).
Wire OpenAIProviderConfig.WebSearch through providerSelection
and into CodexProvider for codex-auth and codex-cli-token paths.
Add complete pt-BR translation of the README and update language
navigation links across all existing READMEs (English, Chinese,
Japanese) to include the Portuguese option.
Phase 1: centralize protocol message/tool/response types in protocoltypes and keep compatibility aliases in providers and protocol packages.
Phase 1: preserve HTTPProvider constructor compatibility and route Anthropic api_base through factory auth/provider constructors with base URL normalization.
Phase 2: expand provider routing/auth tests (deepseek/nvidia/shengsuanyun, codex/claude oauth/codex-cli) and add openai_compat + anthropic coverage for proxy transport, model normalization, numeric option coercion, token-source refresh, and base URL behavior.
Phase 3: apply gofmt and validate with Dockerized tests (go test ./pkg/providers/... ./pkg/migrate and go test ./...).
Remove pre-populated example servers (filesystem, github, brave-search,
postgres) from DefaultConfig() to reduce memory footprint per instance.
Changes:
- Set MCP.Servers to empty map instead of 4 example servers
- Reduces default config size by ~500 bytes per instance
- Users should add MCP servers via config.json or documentation
Example configurations are still available in:
- README.md MCP section
- config.example.json
- Official MCP documentation
This optimization benefits deployments with many agent instances.
Replace full *config.Config reference with config.MCPConfig value type
in AgentLoop to allow garbage collection of unused configuration data.
Changes:
- AgentLoop now stores only MCPConfig and workspacePath (minimal deps)
- Add mcp.Manager.LoadFromMCPConfig() for minimal dependency version
- Keep LoadFromConfig() for backward compatibility
- Full Config object can be GC'd after NewAgentLoop() returns
This optimization reduces memory usage by not holding references to
unused channel, provider, gateway, and device configurations.
Resolve conflicts:
- pkg/agent/loop.go: integrate context compression, command handling,
utf8 token estimation, and summarization notification into
multi-agent routing architecture
- pkg/config/config_test.go: merge imports from both branches
- pkg/agent/loop_test.go: update test to use registry-based sessions
Critical bug fix:
- MCP tools were never registered because servers loaded in Run()
but tool registration happened in NewAgentLoop() with empty manager
- Move MCP tool registration from createToolRegistry to Run()
- Register MCP tools for both main agent and subag after successful server loading
- Add subagentManager field to AgentLoop for dynamic registration
- Add tool_count logging for better observability
This ensures MCP tools are properly available to both agent and subagents.
- Add defer in Run() to guarantee MCP connection cleanup
- Handles both normal termination and context cancellation
- Prevents resource leaks when Run() exits via ctx.Done()
- MCP Manager.Close() is idempotent, safe to call from both defer and Stop()
This fixes GitHub Copilot feedback that MCP cleanup only happened in
Stop() but Run() could return on ctx.Done() without cleanup, causing
subprocess/session leaks on normal cancellation shutdown.
- Defer MCP server initialization to Run() using agent's context
- Add mcpConfig and mcpInitOnce fields to AgentLoop
- Use sync.Once to ensure MCP loads exactly once with proper context
- Prevents orphaned subprocesses and resource leaks on cancellation
This fixes GitHub Copilot feedback that MCP connections with
context.Background() won't terminate when the agent stops, causing
potential resource leaks and orphaned stdio/SSE connections.
- Handle json.RawMessage and []byte types by direct unmarshal
- Use JSON marshal/unmarshal for struct types to preserve schema
- Add test case for json.RawMessage schema
- Fixes issue where non-map schemas returned empty object
This fixes GitHub Copilot feedback that Parameters() was dropping
tool schema when InputSchema wasn't already map[string]interface{}
- Change NewMCPTool to accept MCPManager interface instead of concrete *mcp.Manager
- Remove unused mcpPkg import from mcp_tool.go
- Remove newMCPToolForTest helper function as NewMCPTool now accepts interface
- Update all tests to use NewMCPTool directly with MockMCPManager
- Improves testability and follows dependency inversion principle
- Resolve relative envFile paths relative to workspace instead of CWD
- Add filepath import for path operations
- Pass workspace path to goroutines for path resolution
- Improves portability in Docker environments where CWD may vary
- Absolute envFile paths continue to work as before
- Add errors.Join to return aggregated error when all enabled MCP servers fail
- Track enabled server count separately from total configured servers
- Return error only when all servers fail, not for partial failures
- Improve logging with accurate server counts (enabled vs connected)
- Maintains fault tolerance: partial failures don't stop initialization
Replace --profile flags with explicit service names in build commands.
The 'docker compose build' command does not support --profile flag;
profiles are only used for runtime operations like 'up' and 'run'.
Changes:
- docker-build: specify picoclaw-agent picoclaw-gateway
- docker-build-full: specify picoclaw-agent picoclaw-gateway
Fixes: unknown flag: --profile error
Add --profile gateway --profile agent flags to docker build commands
to ensure services are built even when using profiles in compose files.
Without profiles specified, docker compose build skips all services
that have a profile defined, resulting in 'No services to build' warning.
Changes:
- docker-build: add --profile flags
- docker-build-full: add --profile flags
Fixes: WARN[0000] No services to build
Fix uv symlink path from /root/.cargo/bin to /root/.local/bin.
The uv installer puts binaries in ~/.local/bin, not ~/.cargo/bin.
Changes:
- Update uv symlink source: /root/.local/bin/uv
- Add uvx symlink as well (installed alongside uv)
Fixes: /bin/sh: 1: uv: not found error during build
Symlink uv from /root/.cargo/bin to /usr/local/bin to make it
accessible without relying on ENV PATH setting. Add version check
to verify successful installation during build.
Changes:
- Symlink uv to /usr/local/bin/uv
- Add 'uv --version' validation step
- Remove ENV PATH setting (no longer needed)
Fixes: uv: not found error in test script
Replace docker-compose (v1) with docker compose (v2) command syntax
across all files. Docker Compose v2 is now the default in modern
Docker installations and uses 'docker compose' instead of 'docker-compose'.
Changes:
- scripts/test-docker-mcp.sh: update all 8 docker-compose commands
- Makefile: update all 8 docker-compose commands in docker-* targets
- No changes to file names (docker-compose.full.yml remains as-is)
Compatibility: Requires Docker with Compose v2 plugin (Docker Desktop
or docker-compose-plugin package)
Add --entrypoint sh flag to docker-compose run commands in test script
to bypass picoclaw agent's interactive mode. This allows direct command
execution for testing MCP tools.
Changes:
- Add --entrypoint sh to all docker-compose run commands
- Use SERVICE variable for better maintainability
- Simplify command syntax: sh -c 'cmd' → -c 'cmd'
Add Dockerfile.full with Debian-based runtime including git, nodejs, npm, python3, and uv for MCP servers. Add docker-compose.full.yml with npm cache optimization. Add Makefile targets for docker-build-full, docker-run-full, and docker-test. Add test script for MCP tools validation.
Implement comprehensive MCP support with stdio/HTTP/SSE transports, environment variable configuration (env and envFile), custom headers, tool registration, and automatic resource cleanup. Includes full test coverage and VSCode-compatible configuration.
- Added pkg/mcp/manager.go for server lifecycle management
- Added pkg/tools/mcp_tool.go for tool wrapping
- Integrated into agent loop with cleanup
- Support for envFile loading (.env format)
- Headers injection for HTTP/SSE authentication
- Example configs for filesystem, github, brave-search, postgres
Update registerSharedTools to use new WebSearchToolOptions API and
add hardware tools (I2C, SPI) from upstream. Accept upstream's
new web tools config test.
Resolve conflicts in loop.go, config.go, config_test.go,
spawn.go, and subagent.go. Integrate upstream ToolResult/AsyncTool
pattern with multi-agent routing features. Rename mockProvider
to mockRegistryProvider in registry_test.go to avoid redeclaration
with upstream's loop_test.go.
Thank you for your interest in contributing to PicoClaw! This project is a community-driven effort to build the lightweight and versatile personal AI assistant. We welcome contributions of all kinds: bug fixes, features, documentation, translations, and testing.
PicoClaw itself was substantially developed with AI assistance — we embrace this approach and have built our contribution process around it.
We are committed to maintaining a welcoming and respectful community. Be kind, constructive, and assume good faith. Harassment or discrimination of any kind will not be tolerated.
---
## Ways to Contribute
- **Bug reports** — Open an issue using the bug report template.
- **Feature requests** — Open an issue using the feature request template; discuss before implementing.
- **Code** — Fix bugs or implement features. See the workflow below.
- **Documentation** — Improve READMEs, docs, inline comments, or translations.
- **Testing** — Run PicoClaw on new hardware, channels, or LLM providers and report your results.
For substantial new features, please open an issue first to discuss the design before writing code. This prevents wasted effort and ensures alignment with the project's direction.
Rebase your branch onto upstream `main` before opening a PR:
```bash
git fetch upstream
git rebase upstream/main
```
---
## AI-Assisted Contributions
PicoClaw was built with substantial AI assistance, and we fully embrace AI-assisted development. However, contributors must understand their responsibilities when using AI tools.
### Disclosure Is Required
Every PR must disclose AI involvement using the PR template's **🤖 AI Code Generation** section. There are three levels:
| Level | Description |
|---|---|
| 🤖 Fully AI-generated | AI wrote the code; contributor reviewed and validated it |
| 🛠️ Mostly AI-generated | AI produced the draft; contributor made significant modifications |
| 👨💻 Mostly Human-written | Contributor led; AI provided suggestions or none at all |
Honest disclosure is expected. There is no stigma attached to any level — what matters is the quality of the contribution.
### You Are Responsible for What You Submit
Using AI to generate code does not reduce your responsibility as the contributor. Before opening a PR with AI-generated code, you must:
- **Read and understand** every line of the generated code.
- **Test it** in a real environment (see the Test Environment section of the PR template).
- **Check for security issues** — AI models can generate subtly insecure code (e.g., path traversal, injection, credential exposure). Review carefully.
- **Verify correctness** — AI-generated logic can be plausible-sounding but wrong. Validate the behavior, not just the syntax.
PRs where it is clear the contributor has not read or tested the AI-generated code will be closed without review.
### AI-Generated Code Quality Standards
AI-generated contributions are held to the **same quality bar** as human-written code:
- It must pass all CI checks (`make check`).
- It must be idiomatic Go and consistent with the existing codebase style.
- It must not introduce unnecessary abstractions, dead code, or over-engineering.
- It must include or update tests where appropriate.
### Security Review
AI-generated code requires extra security scrutiny. Pay special attention to:
- File path handling and sandbox escapes (see commit `244eb0b` for a real example)
- External input validation in channel handlers and tool implementations
- **Description** — What does this change do and why?
- **Type of Change** — Bug fix, feature, docs, or refactor.
- **AI Code Generation** — Disclosure of AI involvement (required).
- **Related Issue** — Link to the issue this addresses.
- **Technical Context** — Reference URLs and reasoning (skip for pure docs PRs).
- **Test Environment** — Hardware, OS, model/provider, and channels used for testing.
- **Evidence** — Optional logs or screenshots demonstrating the change works.
- **Checklist** — Self-review confirmation.
### PR Size
Prefer small, reviewable PRs. A PR that changes 200 lines across 5 files is much easier to review than one that changes 2000 lines across 30 files. If your feature is large, consider splitting it into a series of smaller, logically complete PRs.
---
## Branch Strategy
### Long-Lived Branches
- **`main`** — the active development branch. All feature PRs target `main`. The branch is protected: direct pushes are not permitted, and at least one maintainer approval is required before merging.
- **`release/x.y`** — stable release branches, cut from `main` when a version is ready to ship. These branches are more strictly protected than `main`.
### Requirements to Merge into `main`
A PR can only be merged when all of the following are satisfied:
1. **CI passes** — All GitHub Actions workflows (lint, test, build) must be green.
2. **Reviewer approval** — At least one maintainer has approved the PR.
3. **No unresolved review comments** — All review threads must be resolved.
4. **PR template is complete** — Including AI disclosure and test environment.
### Who Can Merge
Only maintainers can merge PRs. Contributors cannot merge their own PRs, even if they have write access.
### Merge Strategy
We use **squash merge** for most PRs to keep the `main` history clean and readable. Each merged PR becomes a single commit referencing the PR number, e.g.:
```
feat: Add Ollama provider support (#491)
```
If a PR consists of multiple independent, well-separated commits that tell a clear story, a regular merge may be used at the maintainer's discretion.
### Release Branches
When a version is ready, maintainers cut a `release/x.y` branch from `main`. After that point:
- **New features are not backported.** The release branch receives no new functionality after it is cut.
- **Security fixes and critical bug fixes are cherry-picked.** If a fix in `main` qualifies (security vulnerability, data loss, crash), maintainers will cherry-pick the relevant commit(s) onto the affected `release/x.y` branch and issue a patch release.
If you believe a fix in `main` should be backported to a release branch, note it in the PR description or open a separate issue. The decision rests with the maintainers.
Release branches have stricter protections than `main` and are never directly pushed to under any circumstances.
---
## Code Review
### For Contributors
- Respond to review comments within a reasonable time. If you need more time, say so.
- When you update a PR in response to feedback, briefly note what changed (e.g., "Updated to use `sync.RWMutex` as suggested").
- If you disagree with feedback, engage respectfully. Explain your reasoning; reviewers can be wrong too.
- Do not force-push after a review has started — it makes it harder for reviewers to see what changed. Use additional commits instead; the maintainer will squash on merge.
### For Reviewers
Review for:
1.**Correctness** — Does the code do what it claims? Are there edge cases?
2.**Security** — Especially for AI-generated code, tool implementations, and channel handlers.
3.**Architecture** — Is the approach consistent with the existing design?
4.**Simplicity** — Is there a simpler solution? Does this add unnecessary complexity?
5.**Tests** — Are the changes covered by tests? Are existing tests still meaningful?
Be constructive and specific. "This could have a race condition if two goroutines call this concurrently — consider using a mutex here" is better than "this looks wrong".
### Reviewer List
Once your PR is submitted, you can reach out to the assigned reviewers listed in the following table.
- **Wechat&Discord** — We will invite you when you have at least one merged PR
When in doubt, open an issue before writing code. It costs little and prevents wasted effort.
---
## A Note on the Project's AI-Driven Origin
PicoClaw's architecture was substantially designed and implemented with AI assistance, guided by human oversight. If you find something that looks odd or over-engineered, it may be an artifact of that process — opening an issue to discuss it is always welcome.
We believe AI-assisted development done responsibly produces great results. We also believe humans must remain accountable for what they ship. These two beliefs are not in conflict.
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
wenjie
