* 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>
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.
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
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>
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>
* 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 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.
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.
- 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>
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
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
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
Update registerSharedTools to use new WebSearchToolOptions API and
add hardware tools (I2C, SPI) from upstream. Accept upstream's
new web tools config test.
* add I2C and SPI tools for hardware interaction
- Implemented I2CTool for I2C bus interaction, including device scanning, reading, and writing.
- Implemented SPITool for SPI bus communication, supporting device listing, data transfer, and reading.
- Added platform-specific implementations for Linux and stubs for non-Linux platforms.
- Updated agent loop to register new I2C and SPI tools.
- Created documentation for hardware skills, including usage examples and pinmux setup instructions.
* Remove build constraints for Linux from I2C and SPI tool files.
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.
Merge upstream/main into bugfix/fix-duplicate-telegram-messages.
Conflict resolutions:
- pkg/agent/loop.go: Adopt upstream's processSystemMessage which removes
runAgentLoop call entirely (subagents now communicate via message tool
directly). Keep PR's HasSentInRound() check in Run() for normal
message processing path.
- pkg/tools/message.go: Merge both changes - keep sentInRound tracking
from PR and adopt upstream's *ToolResult return type with Silent: true.
- Add constants package with IsInternalChannel helper to centralize internal channel checks across agent, channels, and heartbeat services
- Add ToProviderDefs method to ToolRegistry to consolidate tool definition conversion logic used in agent loop and tool loop
- Refactor SubagentTool.Execute to use RunToolLoop for consistent tool execution with iteration tracking
- Remove duplicate inline map definitions and type assertion code throughout codebase
Two issues caused duplicate messages to be sent to users:
1. System messages (from subagent): processSystemMessage set SendResponse:true,
causing runAgentLoop to publish outbound. Then Run() also published outbound
using the returned response string, resulting in two identical messages.
Fix: processSystemMessage now returns empty string since runAgentLoop already
handles the send.
2. Message tool double-send: When LLM called the "message" tool during
processing, it published outbound immediately. Then Run() published the
final response again. Fix: Track whether MessageTool sent a message in the
current round (sentInRound flag, reset on each SetContext call). Run()
checks HasSentInRound() before publishing to avoid duplicates.
Extract core LLM tool loop logic into shared RunToolLoop function that can be
used by both main agent and subagents. Subagents now run their own tool loop
with dedicated tool registry, enabling full independence.
Key changes:
- New pkg/tools/toolloop.go with reusable tool execution logic
- Subagents use message tool to communicate directly with users
- Heartbeat processing is now stateless via ProcessHeartbeat
- Simplified system message routing without result forwarding
- Shared tool registry creation for consistency between agents
This architecture follows openclaw's design where async tools notify via
bus and subagents handle their own user communication.
feat(config): add heartbeat interval configuration with default 30 minutes
feat(state): migrate state file from workspace root to state directory
feat(channels): skip internal channels in outbound dispatcher
feat(agent): record last active channel for heartbeat context
refactor(subagent): use configurable default model instead of provider default
Resolved conflicts:
- pkg/heartbeat/service.go: merged both 'started' field and 'onHeartbeatWithTools'
- pkg/tools/edit.go: use validatePath() with ToolResult return
- pkg/tools/filesystem.go: fixed return values to use ToolResult
- cmd/picoclaw/main.go: kept active setupCronTool, fixed toolsPkg import
- pkg/tools/cron.go: fixed Execute return value handling
Fixed tests for new function signatures (NewEditFileTool, NewAppendFileTool, NewExecTool)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove .ralph/ directory files from git tracking.
These are no longer needed as the tool-result-refactor is complete.
Also removes root-level prd.json and progress.txt.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Created new SubagentTool for synchronous subagent execution:
- Implements Tool interface with Name(), Description(), Parameters(), SetContext(), Execute()
- Returns ToolResult with ForUser (summary), ForLLM (full details), Silent=false, Async=false
- Registered in AgentLoop with context support
- Comprehensive test file subagent_tool_test.go with 9 passing tests
Acceptance criteria met:
- ForUser contains subagent output summary (truncated to 500 chars)
- ForLLM contains full execution details with label and result
- Typecheck passes (go build ./... succeeds)
- go test ./pkg/tools -run TestSubagentTool passes (all 9 tests pass)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Vinh Tran