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.
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
- write config and cron store with 0600 instead of 0644
- check allow list in Slack slash commands and app mentions
- pass workspace restrict flag to cron exec tool
Closes#179
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'
This platform has a growing desktop and embedded user base, and is fully
supported by Go. The only necessary change is the mapping between
`uname -m` output and GOARCH.
Due to non-technical reasons [1], there is currently no Docker official
image that provides linux/loong64 support, so Docker-based builds are
not included in this commit for now.
[1]: https://github.com/docker-library/official-images/issues/16404
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.
* feat: add Codex CLI provider for OpenAI subprocess integration
Add CodexCliProvider that wraps `codex exec --json` as a subprocess,
analogous to the existing ClaudeCliProvider pattern. This enables using
OpenAI's Codex CLI tool as a local LLM backend.
- CodexCliProvider: subprocess wrapper parsing JSONL event stream
- Credential reader for ~/.codex/auth.json with token expiry detection
- Factory integration: provider "codex-cli" and auth_method "codex-cli"
- Fix tilde expansion in workspace path for CLI providers
- 37 unit tests covering parsing, prompt building, credentials, and mocks
* fix: add tool call extraction to Codex CLI provider
- Extract shared tool call parsing into tool_call_extract.go
(extractToolCallsFromText, stripToolCallsFromText, findMatchingBrace)
- Both ClaudeCliProvider and CodexCliProvider now share the same
tool call extraction logic for PicoClaw-specific tools
- Fix cache token accounting: include cached_input_tokens in total
- Add 2 new tests for tool call extraction from JSONL events
- Update existing tests for corrected token calculations
* fix(docker): update Go version to match go.mod requirement
Dockerfile used golang:1.24-alpine but go.mod requires go >= 1.25.7.
This caused Docker builds to fail on all branches with:
"go: go.mod requires go >= 1.25.7 (running go 1.24.13)"
Update to golang:1.25-alpine to match the project requirement.
* fix: handle codex CLI stderr noise without losing valid stdout
Codex writes diagnostic messages to stderr (e.g. rollout errors) which
cause non-zero exit codes even when valid JSONL output exists on stdout.
Parse stdout first before checking exit code to avoid false errors.
* style: fix gofmt formatting and update web search API in tests
- Remove trailing whitespace in web.go and base_test.go
- Update config_test.go and web_test.go for WebSearchToolOptions API
Add validation logic for SkillInfo to ensure name and description meet requirements
Include test cases covering various validation scenarios
Add testify dependency for testing assertions
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
Fixes four issues identified in the community code review:
- Session persistence broken on Windows: session keys like
"telegram:123456" contain ':', which is illegal in Windows
filenames. filepath.Base() strips drive-letter prefixes on Windows,
causing Save() to silently fail. Added sanitizeFilename() to
replace invalid chars in the filename while keeping the original
key in the JSON payload.
- HTTP client with no timeout: HTTPProvider used Timeout: 0 (infinite
wait), which can hang the entire agent if an API endpoint becomes
unresponsive. Set a 120s safety timeout.
- Slack AllowFrom type mismatch: SlackConfig used plain []string
while every other channel uses FlexibleStringSlice, so numeric
user IDs in Slack config would fail to parse.
- Token estimation wrong for CJK: estimateTokens() divided byte
length by 4, but CJK characters are 3 bytes each, causing ~3x
overestimation and premature summarization. Switched to
utf8.RuneCountInString() / 3 for better cross-language accuracy.
Also added unit tests for the session filename sanitization.
Ref #116
yuchou87