- Add maxConcurrentSubTurns constant (5) and concurrencySem channel to turnState
- Acquire/release semaphore in spawnSubTurn to limit concurrent child turns per parent
- Add activeTurnStates sync.Map to AgentLoop for tracking root turn states by session
- Implement HardAbort(sessionKey) method to trigger cascading cancellation via turnState.Finish()
- Register/unregister root turnState in runAgentLoop for hard abort lookup
- Add TestSubTurnConcurrencySemaphore to verify semaphore capacity enforcement
- Add TestHardAbortCascading to verify context cancellation propagates to child turns
- Add subTurnResults sync.Map to AgentLoop for per-session channel tracking
- Add register/unregister/dequeue methods in steering.go
- Poll SubTurn results in runLLMIteration at loop start and after each tool,
injecting results as [SubTurn Result] messages into parent conversation
- Initialize root turnState in runAgentLoop, propagate via context
(withTurnState/turnStateFromContext), call rootTS.Finish() on completion
- Wire Spawn Tool to spawnSubTurn via SetSpawner in registerSharedTools,
recovering parentTS from context for proper turn hierarchy
- Refactor subagent.go to use SetSpawner pattern
- Add TestSubTurnResultChannelRegistration and TestDequeuePendingSubTurnResults
Introduce parseTurnBoundaries() which identifies each Turn start index
in the session history. A Turn is a complete "user input → LLM iterations
→ final response" cycle (as defined in the agent refactor design #1316).
findSafeBoundary now uses Turn boundaries instead of raw role-scanning,
making the intent explicit: "find the nearest Turn boundary."
forceCompression drops the oldest half of Turns (not arbitrary messages),
which is simpler and more intuitive. The Turn-based approach naturally
prevents splitting tool-call sequences since each Turn is atomic.
Session history (GetHistory) contains only user/assistant/tool messages.
The system prompt is built dynamically by BuildMessages and is never
stored in session. The previous code incorrectly treated history[0] as
a system prompt, skipping the first user message and appending a
compression note to it.
Fix: operate on the full history slice, and record the compression
note in the session summary (which BuildMessages already injects into
the system prompt) rather than modifying any history message.
Separate context_window from max_tokens — they serve different purposes
(input capacity vs output generation limit). The previous conflation caused
premature summarization or missed compression triggers.
Changes:
- Add context_window field to AgentDefaults config (default: 4x max_tokens)
- Extract boundary-safe truncation helpers (isSafeBoundary, findSafeBoundary)
into context_budget.go — pure functions with no AgentLoop dependency
- forceCompression: align split to safe boundary so tool-call sequences
(assistant+ToolCalls → tool results) are never torn apart
- summarizeSession: use findSafeBoundary instead of hardcoded keep-last-4
- estimateTokens: count ToolCalls arguments and ToolCallID metadata,
not just Content — fixes systematic undercounting in tool-heavy sessions
- Add proactive context budget check before LLM call in runAgentLoop,
preventing 400 context-length errors instead of reacting to them
- Add estimateToolDefsTokens for tool definition token cost
Closes#556, closes#665
Ref #1439
* make gateway aware of config.json change
* fix according to code review
* fix lint
* fix review comment
* fix for review
* refactor to fix review
* fix for review
* fix for review
* feat(web_search): add load balance and failover for api keys
* feat(web_search): add load balance and failover for api keys
* lint
* new iter to get api key
* deleted conflicts
* feat(session): add SessionStore interface and JSONL backend adapter
Extract a SessionStore interface from the methods the agent loop uses
(AddMessage, GetHistory, SetSummary, TruncateHistory, Save, etc.).
Both SessionManager and the new JSONLBackend satisfy this interface,
allowing the persistence layer to be swapped transparently.
JSONLBackend wraps memory.Store and maps its error-returning API to
the fire-and-forget contract that the agent loop expects — write
errors are logged, reads return empty defaults on failure. Save()
triggers compaction to reclaim space after logical truncation.
Part of #1169
* test(session): add JSONLBackend integration tests
8 tests covering the full SessionStore contract through the JSONL
backend: message roundtrip, tool calls, summary, truncation with
compaction, history replacement, empty sessions, session isolation,
and the complete summarization flow (SetSummary → TruncateHistory →
Save).
Includes compile-time interface satisfaction checks for both
SessionManager and JSONLBackend.
Part of #1169
* feat(agent): wire JSONL session store into agent loop
Replace the concrete *SessionManager field with the SessionStore
interface and initialize the JSONL backend by default. Legacy .json
session files are auto-migrated on first startup. Falls back to
SessionManager if the JSONL store cannot be initialized.
The agent loop code (loop.go) requires zero changes — all method
calls work identically through the interface.
Closes#1169
* fix(session): propagate compact error from Save
Save() was swallowing the error returned by Compact and always
returning nil. Callers checking Save's return value would never
see a compaction failure. Return the error directly so the agent
loop can log or handle it as needed.
* feat(session): add Close to SessionStore interface
Add Close() error to SessionStore so callers can release resources
through the interface. JSONLBackend already had Close; this adds
a no-op implementation to SessionManager for compatibility.
* fix(session): close session stores on shutdown and harden migration
- Add Close() to AgentInstance, AgentRegistry, and AgentLoop so JSONL
file handles are released during gateway shutdown and CLI exit.
- Fall back to SessionManager when migration fails, preventing a split
state where some sessions live in JSONL and others remain in JSON.
- Add defer agentLoop.Close() in the CLI agent command path.
- Document SessionStore interface methods (fire-and-forget contract).
* 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>
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.
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).
* 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>
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>
* 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>
- 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>
- 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>
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.
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.
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>
* 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.
- 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
- 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.
* 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.
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).
- 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
- 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
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
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
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
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)
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
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.
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.
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.
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.
- 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
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.
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
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>
- Add state *state.Manager field to AgentLoop struct
- Initialize stateManager in NewAgentLoop using state.NewManager
- Implement RecordLastChannel method that calls state.SetLastChannel
- Implement RecordLastChatID method for chat ID tracking
- Add comprehensive tests for state persistence
- Verify state survives across AgentLoop instances
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Update ToolRegistry.ExecuteWithContext to accept asyncCallback parameter
- Check if tool implements AsyncTool and set callback if provided
- Define asyncCallback in AgentLoop.runLLMIteration
- Callback uses bus.PublishOutbound to send async results to user
- Update Execute method to pass nil for backward compatibility
- Add debug logging for async callback injection
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Modify runLLMIteration to return lastToolResult for later decisions
- Send tool.ForUser content to user immediately when Silent=false
- Use tool.ForLLM for LLM context
- Implement Silent flag check to suppress user messages
- Add lastToolResult tracking for async callback support (US-008)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Update all Tool implementations to return *ToolResult instead of (string, error)
- ShellTool: returns UserResult for command output, ErrorResult for failures
- SpawnTool: returns NewToolResult on success, ErrorResult on failure
- WebTool: returns ToolResult with ForUser=content, ForLLM=summary
- EditTool: returns SilentResult for silent edits, ErrorResult on failure
- FilesystemTool: returns SilentResult/NewToolResult for operations, ErrorResult on failure
- Temporarily disable cronTool in main.go (will be re-enabled in US-016)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
