mirror of
https://github.com/tiennm99/goclaw.git
synced 2026-10-15 10:14:51 +00:00
dev
41
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 thotam
|
3f90057c24 |
fix(pipeline): stop aborting runs on heuristic context budget estimates (#1587)
Runs on models without a registered tokenizer (e.g. 9router brand models)
ended with the generic "Agent couldn't generate a response" fallback even
though the real request used about 55% of the context window.
PruneStage counted history with TokenCounter, which falls back to a
chars/2 heuristic for unregistered models and overcounted about 1.8x.
Once over budget it ran memory flush (~35s, invisible in traces), then
mid-loop compaction, which cannot summarize a history made only of tool
call/result pairs. The callback reported the untouched history as
compacted, PruneStage still saw it over budget and returned AbortRun
before any LLM call, and FinalizeStage replaced the empty reply with the
fallback.
- PruneStage and ContextStage overhead count with the request guard's
BudgetCounter. PruneStage no longer controls loop flow; the final
request guard in ThinkStage decides.
- CompactMessages returns ErrNotCompacted when history is unchanged.
Callers stop counting it as a compaction and do not retry it in the
same run, while post-run summarization still sees the pressure.
- When the guard exhausts every reduction step, ThinkStage stops the run
with a localized chat.context_budget_exceeded notice instead of an
error, so the run's tool results are still persisted. The stop reason
marks the trace and agent span as error; team tasks, cron and
heartbeat treat it as a failure via RunOutcome.Failure().
- Memory flush and mid-loop compaction emit event spans.
- Web and desktop UIs treat an unset context_pruning as enabled (the
backend default since
|
||
|
Duc Nguyenandntduc
|
bb7712a9ff |
fix(collaboration): harden delegated task isolation (#1486)
* feat(collaboration): isolate delegated artifacts and child runs Isolate delegated inputs and outputs behind secure artifact exchange lifecycles. Scope Agent Link tasks by tenant and root agent, and enforce delegation spawn-tree boundaries. Add process-wide child-run admission and preserve logical media paths across native, MCP, and sandbox execution. * fix(collaboration): harden delegated task isolation Enforce tenant and root-agent task scope across migrations and stores. Add exactly-once async completion delivery, delegated sandbox boundaries, and confined artifact and media recovery across runtime surfaces. * fix(collaboration): recover interrupted async tasks * fix(collaboration): normalize persisted child-run status --------- Co-authored-by: ntduc <ntduc@cpp.ai.vn> |
||
|
Clark Cant
|
5ca433b8ac |
fix: persist mid-loop compaction to stop re-compaction loop and revive episodic
The v3 pipeline compacts session history mid-loop (prune_stage + final-request guard) but only mutates the run's message buffer, never the session store. Each turn reloads full history and re-compacts from scratch: message_tokens climb 129k->156k across turns while every turn compacts back down to ~60k. The lossy compaction differs per run, degrading the agent. The same missing persistence stalls episodic memory: the cumulative compaction count never advances, so the episodic worker's idempotency key (sessionKey:count) is pinned and every cycle after the first is skipped. Observed on live traffic: 8 run.completed since deploy, 0 new episodic. Fixes, all reusing existing machinery (no new store methods, no migrations): - Bug A: emitSessionCompleted reads cumulative GetCompactionCount (matching the legacy v2 path) instead of the per-run counter that resets to 0. - Bug B/anti-loop: finalize passes state.Prune.MidLoopCompacted into maybeSummarize; under pressure it lowers the trigger to a unit-aligned threshold (compactionInputCap - overhead, same MaxRequestShare the guard uses) so the compaction is PERSISTED via the existing TruncateHistory + IncrementCompaction path. Defensive floor prevents over-compaction on pathological config; tool-result-only bloat still skips (history-only). - Bug C: SourceID embeds the count (sessionKey:count) so the eventbus dedup key advances per compaction cycle instead of swallowing rapid same-session turns within the 5m TTL. Tests: episodic compaction, maybe_summarize pressure, request budget. go build (PG + sqliteonly), go vet, go test -race all green. |
||
|
|
61993b4387 |
feat(i18n): add Russian (ru) language — full parity across backend, web & desktop (#1391)
* docs(i18n): design spec for Russian (ru) language support Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(i18n): register ru locale constant and IsSupported * feat(i18n): scaffold ru catalog (en placeholders) * feat(i18n): translate ru backend catalog to Russian * fix(i18n): polish ru catalog grammar per review * feat(i18n): wire ru into system messages, config enum, parity test Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(i18n): add ru to web language constants and system-message locales * feat(i18n): scaffold ru web locale dir (en placeholders) * feat(i18n): wire ru resources into web i18next config * feat(i18n): translate ru web locale to Russian (41 namespaces) * fix(i18n): normalize ru web terminology (арендатор, привязка) * fix(i18n): restore dropped 'named' in ru setup OAuth hint * feat(i18n): wire ru into desktop i18next and language pickers Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(i18n): add ru desktop locale (Russian, 16 namespaces) * test(i18n): extend traces/hooks locale guards to cover ru * chore(deploy): add repeatable fork-dev local build+deploy tooling Adds a one-command, idempotent way to run goclaw from a locally built image that merges fresh upstream dev with un-merged fork features (Telegram trigger-words PR #1383 + Russian locale), independent of the published :latest image. - scripts/deploy-forkdev.sh: fetch origin/dev -> merge feature branches into local/fork-dev worktree -> push fork/dev -> build -> up -d. - docker-compose.forkdev.yml: overlay pinning image to goclaw:forkdev with pull_policy:never so :latest never silently replaces the build. - .gitignore: track the deploy helper (past deploy-*.sh), ignore the ../.goclaw-forkdev integration worktree. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(telegram): agent-callable message reaction (message action=react) Adds a "react" action to the message tool so an agent can set an emoji reaction on an existing message (e.g. mark its own status post 👍 once fully paid). Mirrors the ChannelEditor wiring: ReactionSetter capability -> Manager.ReactToMessage -> telegram Channel.ReactToMessage (validates against Telegram's supported reaction set; ✅/❌ are rejected). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(config): remove ignored session scoping controls (#1405) Co-authored-by: Collective Developer <man@collective.dev> * feat(telegram): agent-callable message reaction (message action=react) (#1407) Adds a "react" action to the message tool so an agent can set an emoji reaction on an existing message (e.g. mark its own status post 👍 once fully paid). Mirrors the ChannelEditor wiring: ReactionSetter capability -> Manager.ReactToMessage -> telegram Channel.ReactToMessage (validates against Telegram's supported reaction set; ✅/❌ are rejected). Co-authored-by: skensel <skensel@MacBook-Pro-skensel.local> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * ci: build & publish fork image to GHCR (temporary, pre-upstream) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(memory): use 'russian' FTS config for memory_chunks recall Memory keyword search (memory_search.go FTS + the generated tsv column) used the 'simple' text-search config, which does no stemming. Russian grammatical cases therefore never matched: a genitive query token ("Дианы") could not hit the stored nominative token ("Диана"), so memory_search returned nothing for natural queries even though the fact was saved. This is the sole recall path on deployments without an embedding provider (ChatGPT-OAuth/codex cannot embed), so recall was effectively dead there. Switch both sides to the Snowball 'russian' config so index and query lexemes stem to the same root ("диан"), restoring case-insensitive recall. Migration 000094 recreates the generated tsv column (a GENERATED expression cannot be ALTERed in place; ADD COLUMN backfills all rows). Surface parity: desktop/SQLite N/A — SQLite memory search uses LIKE, a separate mechanism unaffected by the PG regconfig. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: skensel <skensel@MacBook-Pro-skensel.local> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Co-authored-by: ナム <namnhfreelancer@gmail.com> Co-authored-by: Collective Developer <man@collective.dev> |
||
|
|
b459d40531 |
feat(sandbox): expose Workdir field in SandboxConfig (#853)
The internal sandbox.Config already supports a custom container Workdir that doubles as the workspace mount target, but config.SandboxConfig (the JSONB-backed per-agent config) did not expose it. Without this, agents must use the hardcoded /workspace mount point even when their scripts expect a different in-container path. Adds an optional "workdir" JSON field that maps through to sandbox.Config.Workdir. Backward compatible — existing agents without workdir set fall back to the /workspace default. Co-authored-by: tuannt23065 <tuannt23065@users.noreply.github.com> Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
nguyenha935andnguyenha935
|
086532484d |
feat: add configurable appearance settings (#1384)
Co-authored-by: nguyenha935 <208228297+nguyenha935@users.noreply.github.com> |
||
|
nguyenha935andGoClaw Operator
|
e1fcccea4f |
feat: add configurable system messages (#1343)
Co-authored-by: GoClaw Operator <operator@goclaw> |
||
|
Zezae OhandClaude Opus 4.8
|
4a79c8a208 |
feat(cron): deterministic command payloads (run a shell command, no LLM) (#1279)
* feat(cron): deterministic command payloads (run a shell command, no LLM) Cron jobs always run an agent turn today, so deterministic work (health probes, backups, syncs) pays model tokens on every fire. This adds a "command" payload kind that runs a shell command directly in the gateway process with zero model tokens, mirroring openclaw's command cron. - store: CronPayload.Command (*CronCommandSpec — argv/cwd/env/input/ timeouts/output cap). Persists in the existing payload JSON blob, so there is NO migration and no schema version bump. - internal/cronexec: in-process runner with wall-clock + no-output timeouts, per-stream output capping, and process-group termination so a timed-out command's forked children are also killed. - gateway_cron handler: command jobs run in-process and deliver stdout on success (honoring the NO_REPLY sentinel). A non-zero exit / timeout returns an error so the run is recorded as error and retried per cron.max_retries; failures are NOT delivered, mirroring the agent path (only successful output is announced — no channel spam). - surfaces: cron.create RPC, the agent `cron` tool, and a new `goclaw cron create` CLI all accept command payloads. - security: gated by cron.command_enabled (default false). Commands run with the gateway process's privileges, so the feature is opt-in per gateway; when disabled the RPC and tool reject command payloads and the handler refuses to run them. - i18n (en/vi/zh), docs (08-scheduling-cron.md), and tests for the runner and the handler command path. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(cron): gate command payloads on the update surfaces too handleUpdate (RPC + agent tool) passed CronJobPatch.Command straight to UpdateJob, which switches the payload to command kind for any non-nil Command — without the command_enabled gate or ValidateCronCommandSpec that create enforces. A normal job could therefore be mutated into a command job (or persisted with an invalid spec, e.g. empty argv) on a gateway where command cron is disabled, breaking the disabled-gateway contract. Both update surfaces now require cron.command_enabled and validate the spec before UpdateJob, matching create. The agent tool parses the command via the same path as add and drops the raw keys so a shell-string command can't break the generic patch unmarshal. Regression tests added for RPC and tool update (command disabled + invalid argv), plus a positive enabled-valid case. Addresses review feedback from @mrgoonie on #1279. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
nguyenha935andnguyenha935
|
9ec542251d |
fix(agent): configure and instrument compaction timeout (#1259)
Co-authored-by: nguyenha935 <208228297+nguyenha935@users.noreply.github.com> |
||
|
Duy /zuey/
|
990fabf94b |
fix(config): persist shell deny group disables
Squash merge PR #112 after resolving the project changelog conflict with current dev. Local checks passed: config gateway tests, provider/http/tools deny-pattern tests, go build ./..., and go build -tags sqliteonly ./.... PR CI run 26704832350 passed release-versioning, go, and web. |
||
|
Duy /zuey/
|
361f2abbf5 |
fix(packages): use writable scratch dir for github updates
Squash merge PR #97 after resolving changelog conflict with current dev. PR CI run 26703171763 passed release-versioning, go, and web. |
||
|
Goon
|
c99f7e1fa4 | feat(skills): add slash command activation | ||
|
Goon
|
1296031d5a | feat(skills): configure upload size limits | ||
|
Duy /zuey/
|
4472c607b8 |
feat(workstation): Remote Workstation Runtime — SSH exec + security + audit (#4)
* feat(packages): add update flow for GitHub binaries (#900) Closes #900. Proactive update-check + atomic swap for GitHub-installed binaries on the Runtime & Packages page. Interfaces prepared for pip/npm/apk extension in Phase 2. - UpdateCache + UpdateRegistry + PackageLocker (ctx-aware keyed mutex) - GitHubUpdateChecker: ETag-aware, distinct /latest vs /list ETag keys, semver-correct ordering via golang.org/x/mod/semver, non-semver fallback that refuses to downgrade, pre-release + stable candidate fusion for the v1.0.0-rc.1 -> v1.0.0 transition - GitHubUpdateExecutor: two-phase .bak swap with hadBackup-aware rollback, manifest save retry (3x, 100ms/500ms/1s backoff), nil-safe meta access, explicit ScratchDir, 0755 set pre-rename - HTTP: GET /v1/packages/updates (SWR), POST /v1/packages/updates/refresh, POST /v1/packages/update, POST /v1/packages/updates/apply-all (always 200, failed[] is error source). Master-scope gated. - WS events package.update.{checked,started,succeeded,failed} forwarded to owner clients via event_filter.go - Frontend: useUpdates hook + 3 components (summary bar, update-all modal, row button), master-scope-gated disabled state - i18n: 8 backend keys + 17 frontend keys x en/vi/zh - Config: packages.github_token (reserved), updates_check_ttl, scratch_dir - 45+ new tests, race-clean, BenchmarkCheckAll10Packages ~1.1ms/op warm * docs(packages): document update flow + Phase 1 completion - packages-github.md: "Updating Installed Packages" section with UI + API contract, troubleshooting runbook (corrupt cache, rate-limit, scratch dir, mid-swap recovery) - 17-changelog.md + CHANGELOG.md: Phase 1 entry - 14-skills-runtime.md: cross-ref to update flow - journal entry capturing CRIT fixes (double-write, lock-key mismatch, rollback false-alarm) + design wins (keyed locks, red-team pre-flight) * feat(workstation): remote workstation runtime — SSH exec + security + audit Adds generic Remote Workstation Runtime enabling agents to execute commands on user-owned SSH workstations. Includes registry (DB + API + UI), SSH backend with connection pool and circuit breaker, workstation.exec + claude_remote tools, NFKC + binary-name allowlist security, and audit logging. Standard edition only. Closes #941. * fix(workstation): address 3 critical + 5 important code review findings - C1: Add json:"-" to Metadata/DefaultEnv fields; use SanitizedView() in all API responses to prevent SSH private key leakage - C2: Wire CheckEnv into PermCheckFn; LD_PRELOAD/PATH injection now blocked - C3: SSH Setenv fallback — prepend `export K=V;` when server rejects Setenv - I1: BackendCache sync.RWMutex → sync.Mutex (fix data race on lastUsed) - I2: Validate metadata shape in handleUpdate before store write - I3: Include command in exec-done event; activity sink uses actual cmd hash - I4: Wrap pool release in sync.Once (idempotent double-call safety) - I5: Verify workstation tenant ownership before adding permissions * fix(packages): bypass HTTPS+IP validation in update executor tests Test httptest servers bind to http://127.0.0.1 which fails both the HTTPS scheme check and literal-IP SSRF guard. Add testSkipDownloadValidation flag (same pattern as existing withTestDownloadHosts) to skip full URL validation in test context. * fix(workstation): address Claude review findings — tenant isolation + pool leak + dead code - Activity list: add workstation ownership check before listing (prevents cross-tenant activity enumeration via known UUID) - SSH pool: clean up p.sem + p.circuits maps in CloseWorkstation, prune, and Close to prevent unbounded map growth - RPC handlers: return ErrInvalidRequest on JSON unmarshal failure instead of silently using zero-value params - Remove unused containsControlChars function in normalize.go - HTTP tests: add 10s context timeout to prevent CI package timeout * fix(workstation): DefaultEnv JSON parse, backend cache leak, perm ownership check - DefaultEnv: replace KEY=VALUE text parse with json.Unmarshal (stored as JSON by HTTP handler, was silently ignored) - BackendCache: close losing backend on concurrent cache miss to prevent pruneLoop goroutine leak - Backend interface: add Close() error method; SSHBackend delegates to pool.Close() - handlePermList: add wsStore.GetByID ownership check (prevents cross-tenant UUID enumeration returning empty array vs 404) - scanRows: log scan errors instead of silently skipping * fix(workstation): wire activity sink shutdown + remove misleading comment - WireActivitySink: capture cleanup func, register in gateway shutdown (was discarded → retention goroutine leaked + buffered rows lost) - Add Stop() to WorkstationActivityStore interface (PG+SQLite already had it) - wireWorkstationTools returns cleanup func; gateway.go defers it - Remove misleading "re-validate env" comment in allowlist.go Check() * ci: bump unit test timeout from 90s to 120s hooks/handlers package (goja script tests) consumes ~85s on cold CI runners, leaving insufficient headroom for HTTP retry tests with 1s backoff. 120s provides adequate breathing room without masking real deadlocks. * fix: compile errors in integration tests + allowlist docstring - packages_update_test: add missing lockKey arg to registry.Apply - mcp_grant_revoke_test: remove unused fakeMCPClient struct - allowlist.go: fix Check() docstring to match actual 3-step pipeline * fix(test): relax mcp grant revoke assertion for pre-Phase02 state Execute-time grant checking not yet wired — test correctly gets an error but the message is "no active client" (nil clientPtr) rather than "grant revoked". Accept any error as valid regression guard. * chore: trigger CI on digitopvn/goclaw fork * ci: retrigger workflows * fix(permissions): classify workstation methods in RBAC policy |
||
|
viettranx
|
860bfff38f |
chore: minor formatting and cleanup across config, audio, cache, http, and provider modules
- config: align struct tag formatting in TelemetryConfig for readability - audio tests: modernize test patterns - cache, http, hooks, providers: small style and cleanup passes - No functional changes |
||
|
viettranx
|
b7592bcacf |
feat(hooks/script): integrate script handler — FireResult + source-tier gate + migration
Wave 1 Phase 03. Wires the Phase 02 Goja handler into the dispatcher, widens
the DB schema for script + builtin sources, and refactors Dispatcher.Fire to
return a FireResult so builtin-source hooks can mutate event input.
Dispatcher:
- FireResult{Decision, UpdatedToolInput, UpdatedRawInput} replaces the plain
Decision return. stdDispatcher.runSync keeps a local evMut copy so a
builtin-source hook's updatedInput flows to downstream hooks in the chain
and to the caller; non-builtin (source=ui) script mutations are dropped +
WARN-logged (defense-in-depth; source tier enforced at the dispatcher, not
only at the handler).
- applyBuiltinMutation + placeholder builtinAllowlistFor (rawInput, toolInput)
— Phase 04 overrides the allowlist from builtins.yaml.
- noopDispatcher returns FireResult{DecisionAllow}.
- Script mutation tests: TestDispatcher_ScriptMutation_BuiltinSourceApplies,
TestDispatcher_ScriptMutation_UISourceDenied.
Pipeline + callers (14 Fire sites refactored):
- FireHook wrapper returns FireResult; context_stage.go:52 applies
UpdatedRawInput → state.Input.Message; tool_stage.go:52 applies
UpdatedToolInput → tc.Arguments before ExecuteToolCall.
- delegate_bridge + delegate_tool keep the Decision branch; Updated* ignored.
- dispatcher_test / delegate_bridge_test / delegate_tool_hooks_test /
integration test helpers updated for the new shape.
Validation:
- edition_gate allows HandlerScript on every edition (sandboxed, no shell
escape surface).
- config.validateHandler rejects empty source, source > 32 KiB, goja compile
error; validateTimeout rejects on_timeout=ask|defer (reserved).
- Six new config tests cover the script path.
Migrations:
- PG migration 000053 relaxes handler_type + source CHECKs and drops
uq_hooks_{global,tenant,agent} — scripts routinely want many small hooks
per event. RequiredSchemaVersion → 53.
- SQLite SchemaVersion → 21; patch 20 is a SELECT 1 placeholder because
SQLite can't ALTER a CHECK — rebuildAgentHooksV21 runs outside the
migration tx (parallel to backfillV16) to rename/recreate the table with
widened CHECKs. schema.sql fresh-DB path matches.
- H9 fix: PGHookStore.Create + SqliteHookStore.Create honor caller-provided
cfg.ID (uuid.Nil falls back to UUIDv7), unblocking Phase 04 idempotent
UUIDv5 seed. TestCreateHonorsFixedID on both stores.
Config:
- config.HooksConfig{ScriptConcurrency, ScriptPerTenantConcurrency,
ScriptCacheSize, BuiltinDisable}; buildHookHandlers wires the script
handler with the caps from appCfg.Hooks.
Gates green: go build ./... + sqliteonly, go test -race -count=1 across
hooks/pipeline/sqlitestore.
|
||
|
viettranx
|
48335d7797 |
feat(pruning)!: faithful port of TS context pruning + backfill migration
Port goclaw context pruning to match upstream TS design in
openclaw/src/agents/pi-hooks/context-pruning/:
- Opt-in default: prune only when mode="cache-ttl" (was opt-out)
- Remove Pass 0 per-result 30% guard (duplicated Pass 1 with different
suffix, caused wobble)
- Dedupe double prune call per iteration: PruneStage owns the single
entry point; loop_history only runs limitHistoryTurns + sanitizeHistory
- Add cache-TTL gate for Anthropic prompt cache: skip prune while cache
is live, scoped per-session via sync.Map
- Add context.pruned event emission for observability
- Configurable TTL as Go duration string ("5m", "30s")
BREAKING CHANGE: context pruning now opt-in. Add
contextPruning.mode: "cache-ttl" to config.agents.defaults to restore.
Migration 51 / SQLite v19 backfills mode="cache-ttl" for agents with
existing custom context_pruning config missing the mode field, so
previously-configured agents keep pruning after the opt-in flip.
NULL configs stay NULL (new opt-in default applies).
Web UI adds Cache TTL input + toggle wiring mode to cache-ttl/off.
|
||
|
viettranx
|
b0b87da7cd |
feat(config): add optional Audio config for STT/Music
Add optional Audio *AudioConfig pointer field on Config with STT and Music sub-structs. Nil-safe — absent in JSON5 decodes as nil, no breaking change. cfg.Tts retained unchanged for backward compat. setupAudioExtras stub wired for Phase 3/4 STT/Music provider registration. |
||
|
viettranx
|
e715e43a0b |
fix(tools): Windows multi-drive workspace isolation (#836)
- Add case-insensitive path comparison on Windows in isPathInside() - Add allowed_paths config for cross-drive access on Windows - Wire allowed_paths to read/write/edit/list file tools - Add POST /v1/agents/sync-workspace endpoint to propagate workspace changes - Add comprehensive tests for cross-drive, tenant isolation, symlink escape |
||
|
viettranx
|
e839f42412 |
fix(cron): improve panic recovery and config validation
- Use safego.Recover for per-job panic recovery in PG and SQLite cron schedulers (captures stack traces vs inline fmt.Sprint) - Log warning when cron job_timeout config value is invalid instead of silently falling back to default |
||
|
Luan VuandLuvu182
|
50871eaaae |
fix(cron): prevent scheduler loop from blocking when a job hangs (#820)
* fix(cron): prevent scheduler loop from blocking when a job hangs The cron scheduler's runLoop calls checkAndRunDueJobs() every second, which previously used wg.Wait() to block until ALL claimed jobs complete. If any single job hung (LLM provider timeout, agent loop stuck, network issue), wg.Wait() would block indefinitely, preventing the scheduler from ever checking for new due jobs — effectively killing all cron scheduling until a container restart. Changes: - Remove wg.Wait() from both PG and SQLite cron schedulers — jobs now run as independent goroutines that don't block the check loop - Add panic recovery to PG runLoop (safeCheckAndRunDueJobs wrapper) and per-job goroutines, matching the existing safego.Recover pattern in the SQLite scheduler - Add 10-minute context timeout to the cron job handler so a hung agent run is cancelled instead of blocking forever - Use select with context.Done() in the handler to respect the timeout when waiting for the scheduler outcome - Invalidate PG job cache per-job on completion instead of after the (now-removed) batch wait The SQLite scheduler already had safego.Recover on job goroutines but still used wg.Wait() — this commit removes that blocking wait as well. * fix(cron): make job timeout configurable + add SQLite runLoop panic recovery - Add `cron.job_timeout` config field (Go duration string, default "10m") so operators can tune the per-job timeout for complex agent workloads without code changes - Add `safeCheckJobs` panic recovery wrapper to SQLite cron runLoop, matching the PG scheduler's `safeCheckAndRunDueJobs` for consistency - Use dynamic timeout string in error message for better diagnostics * fix: remove unused "time" import from gateway_cron.go * fix(cron): apply same fixes to SQLite DB scheduler (sqlitestore) The SQLite DB-backed scheduler (used by desktop edition with SQLite backend) had the exact same wg.Wait() blocking issue and missing panic recovery as the PG scheduler. Apply identical fixes: - Remove wg.Wait() — jobs run as independent goroutines - Add safeCheckAndRunDueJobs panic recovery wrapper for runLoop - Add per-job panic recovery and cache invalidation --------- Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com> |
||
|
viettranx
|
4cf66eb379 |
feat(ts-port): reasoning strip, dreaming config + weighted scoring
Phase 6 — Reasoning token stripping: - ReasoningDecision.StripThinking auto-flags Kimi + DeepSeek-Reasoner - Guard clauses in Anthropic/OpenAI/Codex stream handlers - Usage.ThinkingTokens + RawAssistantContent preserved (billing + tool passback safe) Phase 8 — Per-agent dreaming config: - MemoryConfig.Dreaming JSONB (no migration), resolver callback pattern - Enabled/DebounceMs/Threshold/VerboseLog fields with partial-override merge - ConsolidationDeps gains optional AgentStore Phase 10 — Dreaming weighted scoring: - Migration 000045 adds recall_count/recall_score/last_recalled_at on episodic_summaries - ComputeRecallScore 4-component formula (freq/rel/recency/freshness, 14d half-life) - memory_search fire-and-forget RecordRecall; ListUnpromotedScored in DreamingWorker - Bootstrap-friendly filter: unrecalled entries bypass thresholds - Debounce stamped on filter-empty skip to prevent starvation loop Phase 5 follow-up — last_compaction_at in sessions.metadata JSONB: - v3 PruneStage.CompactMessages and v2 maybeSummarize both stamp timestamp - Zero migration; exported const SessionMetaKeyLastCompactionAt RequiredSchemaVersion: 44 → 45 (PG), SchemaVersion: 12 → 13 (SQLite). 27 new tests; builds pass under PG and sqliteonly tags. |
||
|
viettranx
|
77a80680ff |
fix(tracing): include thinking tokens in cost calculation
CalculateCost previously ignored usage.ThinkingTokens entirely, causing cost underestimation for every reasoning-capable model (OpenAI o3/o4-mini, Codex/GPT-5, Anthropic extended thinking). Thinking tokens are reported by providers as a sub-count of completion tokens — OpenAI completion_tokens already includes reasoning_tokens, Codex output_tokens likewise, and Anthropic output_tokens counts thinking at the output rate. Default behaviour (ReasoningPerMillion=0) now matches provider billing semantics: full CompletionTokens priced at OutputPerMillion, no double-counting. When ReasoningPerMillion is explicitly configured, the completion bucket is split into visible output + thinking and each priced independently. Defensive clamp to zero when Anthropic's thinkingChars/4 estimate exceeds reported OutputTokens. Adds ReasoningPerMillion field to ModelPricing and 7 regression tests covering the double-count gate, distinct-rate split, Anthropic estimate overrun, and backward compatibility for non-reasoning models. |
||
|
viettranx
|
2c1ef25392 |
feat(subagent): token tracking, edition limits, waitAll, auto-retry, producer-consumer announce (#600)
- Token cost tracking: accumulate input/output tokens per subagent, include in announce messages and persist to DB - Per-edition rate limits: MaxSubagentConcurrent/Depth on Edition struct, tenant-scoped concurrency enforcement in Spawn/RunSync - WaitAll action: spawn(action=wait, timeout=N) blocks until all children complete, returns merged summary - Auto-retry: configurable MaxRetries (default 2) with linear backoff for transient LLM failures - Producer-consumer announce queue: merges staggered subagent results into single LLM run (same pattern as team task announces) - Raw metadata in bus messages to prevent double-formatting - Fire-and-forget DB persistence with detached context + tenant scope - Split oversized files for <200 line compliance |
||
|
viettranx
|
0c6cd02285 |
refactor(compaction): remove minMessages guard, use token-only threshold
Message count-based compaction trigger (default 200) was a legacy safety net from when token estimation was unreliable. With calibrated overhead estimation using actual LLM PromptTokens, the token threshold alone is sufficient — matching industry standard (Claude Code, Anthropic API, LangChain all use token-only). Also fixes EstimateTokens vs EstimateHistoryTokens inconsistency in end-of-run overhead calculation (loop_history.go), and updates stale CLAUDE.md docs from 75% to 85%. |
||
|
Viet Tran
|
e183b459c9 |
feat: SQLite desktop edition — full desktop app with team tasks (#505)
* feat(store): add SQLite backend foundation with build-tag injection
Add sqlitestore package (//go:build sqlite) as alternative to PostgreSQL:
- pool.go: WAL mode, busy_timeout, 4 concurrent read connections
- helpers.go: ? param helpers, JSON array storage, nullable/update utils
- scope.go: tenant scope with ? placeholders (vs PG's $N)
- schema.sql: 1296-line flattened DDL from 29 PG migrations (51 tables)
- schema.go: embedded schema with transactional apply + version tracking
- factory.go: NewSQLiteStores() stub (stores wired in Phase 2)
Build-tag split for store initialization:
- cmd/gateway_stores_pg.go (//go:build !sqlite) — default PG-only
- cmd/gateway_stores_sqlite.go (//go:build sqlite) — runtime PG/SQLite switch
- cmd/gateway_setup.go: extracted wireTracingAndCron() shared helper
Config: GOCLAW_STORAGE_BACKEND + GOCLAW_SQLITE_PATH env vars.
Security: goclaw.db added to DenyPaths (exec, read_file, filesystem tools).
* feat(edition): add centralized edition package for feature tier limits
New internal/edition/ package — single source of truth for all edition limits:
- Edition struct with MaxAgents, MaxTeams, MaxChannels, KGEnabled, TeamFullMode, etc.
- Standard (default, all features) and Lite (desktop, 5 agents, 1 team) presets
- atomic.Pointer for thread-safe Current()/SetCurrent()
Wiring:
- cmd/gateway.go: GOCLAW_EDITION env override (lite/standard) at startup
- cmd/gateway_stores_sqlite.go: auto-set Lite when backend=sqlite
- /v1/edition HTTP endpoint for UI comparison modal (public, no auth)
* feat(sqlitestore): implement Phase 2A core stores + sqliteonly build tag
Implement 12 SQLite store backends (4200+ LOC) mirroring existing PG stores:
- SessionStore, AgentStore, ProviderStore, TracingStore, SnapshotStore
- ConfigSecretsStore, SystemConfigStore, TenantStore, HeartbeatStore
- BuiltinToolStore, BuiltinToolTenantConfigStore, SkillTenantConfigStore
All stores wired in factory.go. Remaining stores (Memory, Cron, Skills,
Teams, etc.) left nil — gateway handles gracefully.
Add sqliteonly build tag for PG-free desktop builds:
- go build . → PG only
- go build -tags sqlite . → PG + SQLite (runtime switch)
- go build -tags sqliteonly . → SQLite only (no pgx dependency)
Key SQLite adaptations:
- ? placeholders (not $N), json_extract/json_each/json_array_length
- DISTINCT ON → GROUP BY + Go dedup, ANY($1) → IN (?,?...)
- rows.Err() checks on all scan loops, execMapUpdateWhereTenant in helpers
- GetOrCreateUserProfile uses RowsAffected() instead of PG's xmax trick
* feat(sqlitestore): implement Phase 2B feature stores
Port 8 additional store backends to SQLite (19 new files, ~6000 LOC):
Cron: cron.go, cron_crud.go, cron_exec.go, cron_scheduler.go
- Job scheduling with cache, ListDue, MarkRunning, MarkComplete
Skills: skills.go, skills_crud.go, skills_content.go, skills_grants.go
- CRUD, grants, content management. LIKE search (no FTS/vector in Lite)
MCP: mcp_servers.go, mcp_servers_access.go, mcp_user_credentials.go
- Server CRUD, agent/user grants, encrypted credentials
Channels: channel_instances.go, pairing.go, pending_messages.go, contacts.go
- Channel management, device pairing, message queue, contact store
Teams: teams.go, teams_tasks.go, teams_tasks_lifecycle.go, teams_tasks_activity.go
- Team/task CRUD, lifecycle transitions, activity log, progress tracking
- JSON array for members/blocked_by (replaces PG text[])
Remaining nil stores: Memory, AgentLinks, KnowledgeGraph, Activity,
SecureCLI, APIKeys, ConfigPermissions — gateway handles gracefully.
* fix(sqlitestore): fix critical arg ordering + data races in Phase 2B stores
C1: ListTasks arg mismatch — limit+1 in userID slot, wrong results
C2: SearchTasks missing duplicate userID arg for (? = '' OR t.user_id = ?)
H3: cron_crud.go cacheLoaded written without mutex → use InvalidateCache()
H4: cron_exec.go discarded ExecContext error → log warning
H1: Add rows.Err() checks in cron_crud, cron_scheduler, cron_exec, pairing
* feat(sqlitestore): implement Phase 2C — Memory, Activity, APIKeys, ConfigPermissions
Complete remaining essential stores (6 new files, ~900 LOC):
Memory: memory.go, memory_docs.go, memory_search.go
- Document/chunk CRUD, LIKE-based search (no vector in Lite edition)
- Embedding methods return empty results gracefully
Activity: activity.go — simple activity logging
APIKeys: api_keys.go — API key CRUD with SHA-256 hash lookup
ConfigPermissions: config_permissions.go — permission rules with TTL cache
24/27 stores now wired. Only AgentLinks, KnowledgeGraph, SecureCLI
remain nil (disabled in Lite edition by design).
Total: 49 files, 11,435 LOC in internal/store/sqlitestore/
* fix(sqlitestore): fix variable shadow in GetDocument + handle chunk delete error
C1: GetDocument scopeClause used := inside if/else blocks, shadowing
outer err variable — query errors silently swallowed. Fixed by renaming
to tcErr matching PG pattern.
H1: IndexDocument chunk deletion ExecContext error was discarded, could
cause duplicate chunks. Now returns error on failure.
* feat(desktop): Phase 3 — Wails v2 desktop app shell with chat UI
Desktop app (ui/desktop/) using Wails v2 + React 19 + Tailwind CSS 4:
Go backend:
- main.go: Wails entry point with embedded frontend assets
- app.go: gateway embedding via goroutine, health check, Wails bindings
- keyring.go: OS keyring secrets with file fallback
- cmd/gateway_export.go: exports RunGateway() for desktop embedding
React frontend:
- WS v3 client: protocol handshake, exponential backoff, call queue
- Chat system: Zustand stores, RAF-batched streaming, 10 event handlers
- Components: MessageBubble, MarkdownRenderer (rehype-sanitize),
CodeBlock, ToolCallBlock, ThinkingBlock, ActivityIndicator, InputBar
- Layout: AppShell (2-column), Sidebar with agent/session list, TopBar
- Onboarding wizard (5 steps): welcome, gateway, provider, agent, ready
- Magic Blue theme (dark/light), Inter + JetBrains Mono typography
Build: all 3 variants pass (PG, sqlite, sqliteonly)
* chore: ignore Wails build artifacts (wailsjs, build, package.json.md5)
* fix(desktop): correct onboarding provider list and agent creation API contract
- ProviderStep: expand from 3 to 16 providers in 4 groups (Popular, Cloud, Local, Regional)
with correct provider_type values and api_base defaults
- AgentStep: fix API payload — use agent_key (slug), provider (name string),
agent_type=predefined with description in other_config
- use-agents: fix field mapping — agent_key, display_name from backend response
- Clean up failed provider on verify error
* fix(desktop): add missing providers — Bailian Coding, Z.ai Coding, Ollama Cloud
* fix(desktop): match web dashboard brand colors + persist onboarding in store
- Replace Magic Blue theme with web dashboard's warm blue OKLCH palette
- Move onboarding state from localStorage to Zustand persist store
- Add "Run Setup Wizard" option in TopBar settings menu to re-trigger onboarding
- Fix light mode theme activation (explicit :root:not(.dark) overrides)
* fix(desktop): apply dark theme before first paint + better error messages
- Add class="dark" default on <html> + inline script to read persisted theme
before React hydrate (prevents light flash on dark mode)
- Improve provider test error message for network failures
* feat(desktop): add GoClaw logo from web UI to onboarding + topbar
* fix(desktop): add Vite proxy for dev mode to avoid CORS gateway errors
- Proxy /v1, /ws, /health to localhost:18790 in Vite dev server
- Use relative URLs in dev mode (import.meta.env.DEV) so proxy handles CORS
- Production build uses direct gateway URL from Wails binding
* fix(desktop): GoClaw dock icon + fix duplicate provider slug on re-test
- Convert goclaw-icon.svg to 1024x1024 PNG for macOS dock icon
- Fix provider creation: handle existing slug by finding and updating
- Track build/appicon.png in git (exclude only build/bin/)
* fix(sqlitestore): UUID text/blob mismatch in scopeClause breaks all queries
scopeClause passed uuid.UUID (16-byte array) to SQLite ? placeholder,
but tenant_id column stores TEXT strings. SQLite compared BLOB vs TEXT
→ no match → all scoped queries returned empty results.
Fix: pass scope.TenantID.String() to ensure TEXT comparison.
Also includes:
- macOS dock icon (.icns from GoClaw logo)
- Onboarding auto-detect existing providers/agents
- Debug logging for token + API URL
* fix(desktop): CORS for dev mode + direct gateway URL
- Wails dev server (port 34115) doesn't proxy API calls, causing 405
- Frontend now connects directly to gateway URL from Wails binding
- Added GOCLAW_DESKTOP=1 env → enables CORS middleware on gateway
- desktopCORS wraps mux with Access-Control-Allow-* headers + OPTIONS
- Simplified provider test flow: list-then-create/update
* fix(desktop): split onboarding into 6 steps matching web UI flow
Web UI flow: create provider → select model + verify → create agent.
Desktop was incorrectly trying to verify before creating provider.
Changes:
- ProviderStep: now only creates/saves provider (no verify)
- NEW ModelVerifyStep: loads models from provider, test connection
- AgentStep: receives pre-selected model, shows read-only model field
- OnboardingWizard: 6 steps with auto-detect skip logic
- Auto-detect: has agents→Ready, has providers→ModelVerify, nothing→Provider
* feat(desktop): add Combobox component, use searchable model selector
- New Combobox: searchable dropdown with custom value support
- ModelVerifyStep: replace plain input/select with Combobox
- Models loaded from GET /v1/providers/{id}/models API
- Allows typing custom model name if API returns empty list
* fix(desktop): rename icon to iconfile.icns matching Wails convention
* refactor(desktop): overhaul UI/UX, fix onboarding, fix event handling
Desktop app major refactor:
UI/UX:
- Chat-focused layout with floating panels on dotted canvas
- Sidebar: agent list + sessions grouped by date (no resource counts)
- Modern input bar: rounded pill with attach/send buttons
- User bubble: card style matching web UI (not solid color)
- Thinking block: collapsible, max-height, proper label
- ErrorBoundary wrapping app
- Dock icon: regenerated with transparent bg + dark rounded frame
Onboarding:
- 3-step flow matching web UI (Provider → Model → Agent)
- Proper create vs update (check DB before POST)
- SetupStepper with step circles + connectors
- Agent presets from web UI (Fox Spirit, Artisan, Astrologer)
- Auto-detect existing setup via use-bootstrap-status hook
Event handling (verified from Go source):
- chunk: payload.content (not payload.chunk)
- thinking: payload.content (not payload.thinking)
- tool.call: payload.id/name (not toolId/toolName)
- tool.result: payload.is_error/content (not error field)
- run.completed: usage.prompt_tokens/completion_tokens
- New: block.reply, run.retrying handlers
Backend fixes:
- SQLite scanTime helper for modernc.org/sqlite text timestamps
- X-GoClaw-User-Id header in desktop API client (not X-User-ID)
- user_id: system (owner role in desktop single-user mode)
- CORS: allow X-GoClaw-User-Id header
- SQLite busy timeout: 5s → 10s
- Snapshot SQL: cross-DB compatible (FILTER→CASE, ::BIGINT→CAST)
- Promise.allSettled for bootstrap status (one fail doesn't block other)
* feat(desktop): chat polish, SQLite fixes, summoning modal, bootstrap guard
Chat Polish (Phase 1):
- ToolCallBlock: Wrench/Zap icons, phase badges, arg summary, grouped rendering
- ThinkingBlock: auto-expand on stream, Brain icon, cursor pulse
- MessageBubble: isStreaming prop, streaming cursor, grouped tool calls
- ImageLightbox: fullscreen overlay, gallery nav, keyboard shortcuts, download
- MediaBlock: grid layout, click-to-open lightbox, hover overlay
- ActivityIndicator: phase-specific icons (Brain/Wrench/RefreshCw)
- ChatCanvas: track lastAssistantId for streaming, EmptyState with prompts
- Filter [System] nudge messages and tool-role messages from chat history
SQLite Fixes:
- sessions_list: fix time.Time scan failure (3 sites) using sqliteTime scanner
- snapshots: fix ON CONFLICT expression mismatch with unique index
- snapshots: fix GetLatestBucket using nullSqliteTime
- pool: explicit PRAGMAs (busy_timeout=15s, WAL, synchronous=NORMAL)
- schema: seed master tenant (was missing, causing FK violations)
- schema: incremental migration framework (version-gated patches)
Onboarding:
- SummoningModal: port from web UI with framer-motion animations
- AgentStep: show summoning modal after create, continue button
- App: auto-detect empty DB and reset onboarded flag
- ChatCanvas: loading spinner while agent loads after onboarding
Bootstrap Guard:
- After auto-cleanup of BOOTSTRAP.md, check if USER.md is still empty
- Inject reminder if agent cleared BOOTSTRAP but didn't fill USER.md
Session Management:
- Load chat history on session click (was missing useEffect)
- Fix race condition: don't clear messages on session switch (atomic replace)
- SidebarFooter: center New Chat button text
* fix(desktop): session management, delete confirm, event listener race fix
- New Chat: only clears state, no empty session creation (sendMessage auto-creates)
- Delete session: hover X button with ConfirmDialog confirmation
- Event listener: use sessionKeyRef instead of closure to prevent stale events
- Remove "skip to dashboard" link from onboarding
- Add reusable ConfirmDialog + ConfirmDeleteDialog common components
* feat(desktop): settings view with tabbed layout (Phase 4)
- SettingsView: tab container with header, close button, canvas-dots bg
- SettingsTabBar: 9 tabs (Appearance, Providers, Agents, MCP, Skills, Tools, Cron, Traces, About)
- AppearanceTab: dark/light theme toggle, language + timezone placeholders
- AboutTab: version, edition limits, runtime info
- ui-store: activeView, settingsTab, openSettings(), closeSettings()
- AppShell: switch between chat and settings views
- SidebarFooter: gear icon opens settings (was "Run Setup Wizard")
- Keyboard: Cmd+, opens settings, Escape closes
- Branding: "GoClaw Lite" in sidebar header
- Agent status: online (green) instead of idle for desktop
- Tab content wrapped in solid bg card with border
* feat(desktop): provider management CRUD in settings (Phase 5)
- use-providers hook: list, create, update, delete, verify via HTTP API
- ProviderList: list view with Add button, empty state
- ProviderRow: status dot, type badge, edit/delete actions
- ProviderFormDialog: create/edit with type selector, masked API key, test connection
- Wire ProviderList into Settings Providers tab
* fix(desktop): remove Test Connection from provider form (requires model + provider ID)
* feat(desktop): agent management CRUD in settings (Phase 6)
- AgentData/AgentInput types matching web UI contracts
- use-agent-crud hook: list, create, update, delete, resummon (5 agent limit)
- AgentCard: emoji, status dot, provider/model/type badges, edit/delete/resummon
- AgentFormDialog: provider Combobox + model Combobox (from /v1/providers/{id}/models)
- Create: agent_type selector, "Check & Create" verifies model before create
- Edit: no type change, no re-verify needed
- Personality textarea for predefined agents
- AgentList: grid, edition limit warning, create triggers SummoningModal
- Delete uses ConfirmDeleteDialog (type name to confirm)
- Sidebar agent list refreshes after CRUD
* feat(desktop): agent detail panel with full config (Phase 6 polish)
Agent detail panel (fullscreen overlay covering sidebar):
- PersonalitySection: emoji editor, display name, description, status select, default toggle, agent key display
- ModelBudgetSection: provider/model Combobox with verify-before-save, context window, max tool iterations
- EvolutionSection: self_evolve toggle with info callout (predefined agents only)
- Sticky save bar: backdrop blur, cancel/save buttons, spinner on save
- Save blocked if provider/model changed but not verified
AgentList: card click opens detail panel, create dialog separate
AgentFormDialog: create-only, Check & Create with verify
* fix(desktop): resummon confirm, summoning z-index, save bar UX
- Resummon requires confirm dialog before triggering
- SummoningModal z-index z-50 → z-[70] (above detail panel z-[60])
- Save bar: show error inline, "Verify model first" when blocked
* feat(desktop): agent detail quality polish — files tab, memory config, rich cards
Types (synced with web UI):
- AgentData: added owner_id, workspace, restrict_to_workspace, frontmatter, context_window, max_tool_iterations as required fields
- MemoryConfig, CompactionConfig interfaces
- BootstrapFile type for WS file operations
AgentCard (matching web UI agent-card.tsx):
- Star icon for default agent
- Animated pulse badge for summoning status
- Self-evolve sparkle indicator (orange when active)
- Frontmatter/expertise with line-clamp-3
- Context window display (e.g. "200K ctx")
- Safe emoji extraction, UUID name detection
AgentDetailPanel:
- Tab navigation: Overview + Files tabs
- Overview: Personality + ModelBudget + Memory + Evolution sections
- Files tab: WS-based file editor (agents.files.list/get/set)
- File sidebar with selection
- Textarea editor with dirty tracking
- Save button with spinner
- Sticky save bar with backdrop blur (overview only)
- Resummon with confirm dialog
MemorySection (matching web UI memory-section.tsx):
- Enable/disable toggle
- 6 config fields: max_results, min_score, max_chunk_len, chunk_overlap, vector_weight, text_weight
- "Using global defaults" when disabled
* feat(desktop): agent files — hide USER/HEARTBEAT, add Edit with AI
- Hide USER.md, USER_PREDEFINED.md, HEARTBEAT.md from files tab (managed by bootstrap/cron)
- Add "Edit with AI" button → RegenerateDialog → POST /v1/agents/{id}/regenerate
- Auto-select first file on load
- Show file size in sidebar
- Pass agentId to files tab for regenerate API call
* fix(desktop): remove memory config section (no embedding in SQLite)
* fix(desktop): remove misleading bytes display from file sidebar
* fix(desktop): replace native checkboxes/selects with custom Switch + Combobox
- New Switch component matching Radix UI toggle style
- Replace all native <input type="checkbox"> with Switch in agent/provider forms
- Replace native <select> for status with Combobox
- All interactive elements have cursor-pointer
* fix(desktop): evolution callout colors — use opacity-based for both themes
* fix(desktop): global cursor-pointer for all interactive elements
* fix(desktop): improve dark mode contrast for text and status colors
- text-secondary: 0.62 → 0.68 lightness (better readability on dark bg)
- text-muted: 0.52 → 0.58 lightness (was below WCAG AA 4.5:1 minimum)
- success: 0.45 → 0.55 (green was too dim on dark bg)
- warning: 0.65 → 0.70 (slightly brighter)
- idle: 0.52 → 0.58 (match text-muted)
* fix(desktop): revert color values to exact web UI match (0.62/0.52/0.45)
* fix(desktop): agent card badge colors — match web UI badge variants exactly
* feat(desktop): add MCP servers + Builtin Tools settings tabs
Phase 7 implementation:
MCP Tab:
- Full CRUD with 5-server edition limit
- Form dialog with transport-conditional fields (stdio/SSE/streamable-http)
- Test Connection with inline success/error feedback
- Agent grants dialog (grant/revoke per agent)
- Tools discovery dialog (view server tools)
- KeyValueEditor with sensitive field masking (auth/token/secret)
Tools Tab:
- Category-grouped list of 41 seeded builtin tools
- Toggle enable/disable with optimistic update
- Specialized settings forms: web_fetch extractor chain, media provider chain
- Generic JSON editor fallback for other tools
- Provider/model Combobox selection for media tools
Common:
- RefreshButton component with 500ms min spin animation
- KeyValueEditor with password masking for sensitive keys
Fixes:
- SQLite builtin_tools scan: use scanTimePair() for timestamps
- Session click while in settings: now closes settings view
- Dark mode text contrast: bumped text-secondary/text-muted lightness
- Light mode text contrast: darkened text-secondary/text-muted
- Focus ring thickness: ring-2 → ring-1 globally
- Misleading "memory layering (Postgres)" log label
* feat(desktop): add Skills tab, agent skill grants, emoji avatar, agent form redesign
Skills:
- Skills settings tab with upload ZIP, toggle, delete, runtime check
- Agent skill grants section in agent detail panel (toggle per agent)
- SQLite SkillManageStore interface compliance fixes
Agent form:
- 2-column layout, wider modal (max-w-3xl)
- 6 personality presets (Fox Spirit, Artisan, Astrologer, Researcher, Writer, Coder)
- Separate Verify Model + Summon buttons
- Always predefined type (removed open option)
Fixes:
- SQLite time.Time scan: mcp_servers, mcp_grants, activity_logs
- Combobox portal with scroll/resize tracking
- AgentAvatar shows emoji from other_config
- uploadFile sends X-GoClaw-User-Id header + generic type
- isApiClientReady guard prevents ErrorBoundary crash
- Verify model field: valid (not success)
* fix(sqlitestore): comprehensive timestamp scan sweep + UI fixes
SQLite timestamp sweep (13 files, 25+ sites):
All time.Time direct scans replaced with sqliteTime/scanTimePair/nullSqliteTime.
Files: activity, teams, teams_tasks, teams_tasks_activity, config_permissions,
agents_access, tracing_spans, tracing_scan, channel_instances, tenants,
pending_messages, api_keys, heartbeat.
UI fixes:
- Agent switching: clear active session + chat when agent changes
- MCP table: vertical align middle on row cells
* fix(sqlitestore): fix json.RawMessage scan + sqliteVal for dynamic updates
- mcp_servers_access: scan json columns via string intermediates (SQLite
TEXT → json.RawMessage incompatible, use string then convert)
- helpers: add sqliteVal() to auto-marshal map/slice/struct to JSON
string in execMapUpdate/execMapUpdateWhereTenant — fixes agent save
500 error when updating other_config, tools_config, etc.
- Add AgentMcpSection: toggle MCP server grants per agent in detail panel
- Clean up debug logging from McpGrantsDialog
* feat(desktop): add i18n (react-i18next) + toast system + language/timezone pickers
i18n:
- Install react-i18next + i18next
- Copy 12 web locale namespaces (en/vi/zh) + desktop.json namespace
- Create i18n/index.ts with browser language detection + localStorage persist
- Replace ~300 hardcoded strings across 40+ components with t() calls
- Language picker in ChatTopBar (top-right) + Settings > Appearance
- Timezone picker in ChatTopBar with search + Intl.supportedValuesOf fallback
- All 6 agent presets fully translated (vi/zh) with prompts from locale files
- Agent Key never translated (uses stable English slugs)
Toast:
- Zustand toast store (success/error/warning/default, 4s auto-dismiss)
- Toaster component (bottom-right, z-100, slide-in animation)
- Toast calls in all CRUD hooks (agents, providers, MCP, skills, tools)
* feat(desktop): add Cron Jobs + Traces settings tabs with syntax highlighting
Cron Jobs (Phase 8):
- WS RPC hook (cron.list/create/delete/toggle/run/runs)
- CronList table with schedule formatting, status badges, run/toggle/delete
- CronFormDialog with slug name, agent selector, 3-way schedule (every/cron/once)
- CronRunsDialog for execution history
Traces (Phase 9):
- HTTP REST hook (GET /v1/traces with pagination + agent filter)
- TraceList table with duration, tokens, spans, relative time
- TraceDetailDialog with metadata, collapsible input/output, flat span list
- Syntax-highlighted JSON/code previews via react-syntax-highlighter
* fix(sqlitestore): fix tracing scan — endTime *time.Time → nullSqliteTime
Both trace and span scan functions used *time.Time for nullable end_time
column, which fails on SQLite TEXT timestamps. Changed to nullSqliteTime
with Valid check before assigning pointer.
* fix(desktop): fix cron schedule type label — map 'at' kind to 'once' i18n key
* fix(desktop): prevent flash on cron/traces refresh — keep data while refetching
* feat(desktop): add file attachment rendering — FileButton + FilePreviewDialog
- FileButton: compact attachment button with emoji icon, filename, size, download
- FilePreviewDialog: modal with type-detected preview (image/video/audio/markdown/code/text)
- MarkdownRenderer: override a/img for /v1/files/ links → FileButton + resolved URLs
- MediaBlock: non-image files render as FileButton instead of plain links
- api.ts: add getBaseUrl() for file URL resolution
* fix(desktop): resolve file URLs in chat — toFileUrl for media_refs + relative paths
- use-chat: add toFileUrl() to convert raw paths to /v1/files/{basename} URLs
for both run.completed media and history media_refs
- MarkdownRenderer: detect relative file paths (./path/file.ext) via isFileLink
in addition to /v1/files/ links, resolve all to gateway URL
* fix(desktop): authenticated file serving — media cache + blob URLs
Security fix: all /v1/files/ requests now use Bearer auth via fetchFile().
No more raw <a href> or <img src> with unauthenticated file URLs.
- Add media-cache.ts (blob cache with 5-min TTL, dedup inflight fetches)
- Add use-media-url.ts hook (returns cached blob URL for authenticated media)
- Add AuthImage component (loads images via auth blob) + downloadFile helper
- Update MarkdownRenderer: file images use AuthImage, downloads use downloadFile
- Update FileButton: authenticated download via blob
- Update FilePreviewDialog: authenticated fetch for text/preview content
- Clean filename display (strip timestamps + query params)
* fix(desktop): fix file attachments — use media_refs.id for URL, auth all media
Root cause: media_refs from backend has {id, mime_type, kind} but no path/url.
The id IS the filename basename. Fixed toFileUrl to use ref.id as fallback.
Also: AuthImage for lightbox, authenticated audio/video in MediaBlock,
clean filename display (strip timestamps).
* fix(desktop): file serving, traces, and media rendering improvements
Backend:
- Store MediaRef.Path in loop_finalize for direct file serving
- Use full path (not basename) in gateway_managed event signing
- Add fuzzyMatchInDir for LLM-hallucinated filenames
- Add findInWorkspace support for agent dirs and ws/ directory
- Add POST /v1/files/sign endpoint for client-side URL signing
- Always save LLM span input_preview (not just verbose mode)
- Truncate previews from tail (keep recent context), limit 2000 chars
- Add exact filename hint to create_image/video/audio tool results
Desktop frontend:
- File attachments: FileButton, FilePreviewDialog, AuthImage with blob cache
- Media cache: sign URLs via API for non-ft URLs, Bearer auth fallback
- Download via Wails SaveFile binding (native Save As dialog)
- OpenFile + DownloadURL Wails Go bindings
- Traces: rewrite with span tree hierarchy, formatTokens (90.8K),
formatDuration with start/end fallback, expandable spans
- Traces: export via DownloadURL, copy with checkmark state
- Code preview: JSON = oneDark syntax highlight, text = light pre block
- MarkdownRenderer: baseUrl prop for relative image resolution
- ImageLightbox: preventDefault on keyboard nav (no macOS beep)
- ErrorBoundary: reload instead of re-render on retry
- Combobox: compact sizing (py-1.5, text-sm)
- FileButton: fix nested button HTML violation
* feat(desktop): team tasks kanban board + edition policy + file preview fixes
Phase 11 implementation:
Backend:
- TeamActionPolicy interface — lite/full edition gating for team_tasks tool
- Filter blocked actions from schema enum + early guard in Execute()
- System prompt: edition-specific team member guidance
- Skip skill_manage/publish_skill registration + seeding in lite
- teams.create: require at least 1 member
- files.go: 2-layer path isolation (workspace boundary + tenant scope)
Desktop UI:
- Kanban board with 6 status columns + framer-motion layout animation
- Task detail modal with collapsible description/result sections
- Team create dialog with styled member checkboxes
- Sidebar: teams section with create button + Lite edition badge
- Chat TaskPanel: compact active tasks with real-time WS updates
- Real-time: debounced get-light fetch (300ms) + progress patch (1s)
- Edition comparison modal (Lite vs Standard feature table)
- Custom dropdown filter replacing native select
- i18n: teams namespace (en/vi/zh)
Fixes:
- WS params: camelCase (teamId, taskId, sessionKey) matching backend
- FileButton: span wrapper (HTML nesting) + createPortal for dialog
- FilePreviewDialog: defensive filename normalization for extension check
- use-chat: prevSessionRef init null — fix blank chat on view switch
- Scrollbar: 3px auto-hide
- Agent click in sidebar returns to chat view
* feat: Update frontend build assets, change the default agent thinking level to 'low', and update Go module dependencies.
|
||
|
viettranx
|
258e378593 |
feat(memory): add chunk overlap support and clean up per-agent config
- Add ChunkOverlap to MemoryConfig (default 200) for context continuity at chunk boundaries during semantic search - Implement overlap logic in ChunkText() with safety clamp at maxChunkLen/2 - Wire per-agent chunk_len/chunk_overlap overrides at IndexDocument time via RunContext, falling back to global PGMemoryConfig defaults - Add sync.RWMutex to PGMemoryStore for thread-safe config updates - Persist chunk settings via system_configs (embedding.max_chunk_len, embedding.chunk_overlap) with runtime refresh on config change - Remove dead per-agent embedding_provider/embedding_model fields from agent Memory UI (system uses single global provider) - Show Memory section always-visible in agent config (no toggle needed) - Add chunk_overlap fields to System Settings modal and Config AI Defaults - Update i18n (en/vi/zh) for all new and removed keys |
||
|
viettranx
|
0cffbf5bfa | fix(agent): loop improvements, history compaction, config tweaks | ||
|
viettranx
|
84b1b07634 |
refactor(config): centralize hardcoded ~/.goclaw paths via config resolution
Replace all hardcoded ~/.goclaw path constructions with configurable
sources (cfg.ResolvedDataDir() for service dirs, cfg.Agents.Defaults.Workspace
for agent workspaces). This fixes data persistence issues in Docker
deployments where paths differ from local dev.
- Add DataDir field to Config with ResolvedDataDir() resolver
- Add ResolvedDataDirFromEnv() package-level helper for packages without Config
- Populate StoreConfig.SkillsStorageDir (was never set, caused hardcoded fallback)
- Agent workspaces now use subdirectory format (workspace/{key}) for volume compatibility
- Remove dead GOCLAW_SESSIONS_STORAGE env/config (sessions moved to PostgreSQL)
- Fix deploy-stg.sh trailing space after backslash + remove deprecated GOCLAW_MODE
- Add GOCLAW_SKILLS_DIR override in docker-compose for volume persistence
|
||
|
viettranx
|
4c7db6e09b |
feat(agent): add mid-run message injection for DM and WebSocket
Inject user follow-up messages into the running agent loop at turn boundaries instead of queueing them for a new run. This preserves context so the LLM sees both tool results and user follow-ups together. - Add InjectedMessage type and drainInjectChannel helper - Add InjectCh to ActiveRun with buffered channel (cap=5) - Drain injection channel at two points in agent loop (after tool results and before no-tool-calls exit) - Route steer/new_task intents to InjectMessage with scheduler fallback - WebSocket: inject into running loop when session is busy - Remove IntentClassify config toggle (always on) - Web UI: show send + stop buttons side by side during agent run - i18n: add injection acknowledgment messages (en/vi/zh) |
||
|
Viet Tran
|
0926d053b0 |
feat: add token usage tracking, cost analytics, budget enforcement, wake API, and activity audit trail (#142)
- A1+C2: Include token usage in run.completed event payload for WS clients
- A2: Cost tracking with model pricing config, cost calculation, and cost summary API
- A3: Budget enforcement per agent with monthly budget limits (migration 000015)
- C1: External wake/trigger API (POST /v1/agents/{id}/wake) for orchestrators
- C3: Activity audit trail with structured logging and queryable API
- UI: Activity page, cost stat card on overview, budget section in agent detail
- i18n: Complete en/vi/zh translations for all new features
|
||
|
Luan VuandLuvu182
|
25fd9c9d6d |
feat(cron): configurable default timezone for cron expressions (#117)
* feat(cron): configurable default timezone for cron expressions Cron expressions (e.g. "0 8 * * *") are evaluated relative to a timezone. Without an explicit per-job timezone, they default to the server's system timezone, which may not match the user's local time — especially in Docker containers (default UTC) or multi-region deployments. This adds a `default_timezone` setting to `CronConfig` (IANA format, e.g. "Asia/Ho_Chi_Minh") that is applied as fallback when a cron job has no explicit `schedule.tz`. The setting is configurable via the UI config page (Integrations → Cron Scheduler) and hot-reloads on config changes. Backend: - Add `DefaultTimezone` field to `CronConfig` - Add `SetDefaultTimezone()` to `CronStore` interface + PG implementation - Apply default TZ in `AddJob()` when `schedule.TZ` is empty - Wire at startup + subscribe to config change events for hot reload - Update cron tool description so LLM knows about gateway default Frontend: - Add timezone dropdown (20 common IANA timezones) to Cron config section - Add i18n keys for en, vi, zh * fix(cron): apply default timezone to existing jobs via computeNextRun Pass defaultTZ as fallback to computeNextRun so existing cron jobs (with timezone = NULL in DB) also use the gateway's configured default timezone when computing next_run_at. This ensures old jobs benefit from the timezone setting without needing a DB migration or backfill. --------- Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com> |
||
|
viettranx
|
bdb60de7ae |
chore: upgrade Go 1.25 → 1.26 and apply go fix modernizations
- Update go.mod and Dockerfile to Go 1.26 - Apply `go fix ./...` stdlib modernizations across 170+ files - Add `go fix` to post-implementation checklist in CLAUDE.md - Fix go fix misapplied rewrite in loop_history.go |
||
|
viettranx
|
e593b9cf22 |
feat(channels): real-time agent activity status & intent classification
- Add tool status display on channels during tool execution (streaming preview + reactions) - Emit agent.activity events at phase transitions (thinking, tool_exec, compacting) - Enrich delegation progress with per-member activity and tool info - Add LLM-based intent classifier for DM status queries when agent is busy - Keyword fast-path for cancel/status patterns (no LLM cost) - Falls back to LLM classification with 5s timeout - Supports status_query (immediate reply) and cancel (abort run) intents - Register/unregister runs in makeSchedulerRunFunc for channel inbound tracking - Add sessionRuns secondary index in Router for O(1) IsSessionBusy lookups - Add intent_classify config toggle (global default + per-agent override) - Add tool_status config toggle for channel tool status display - Add i18n keys and translations (en/vi/zh) for status messages - Add web UI config toggles for intent_classify and tool_status |
||
|
viettranx
|
0d3230b2bf |
feat(cache): add build-tag-gated Redis cache backend
Add optional Redis cache support via `go build -tags redis`, following the same paired-stub pattern as OTel and Tailscale. The Cache[V] interface is unchanged; Redis and in-memory implementations are injected at startup without altering usage logic. - Add RedisCache[V] implementation with JSON serialization, fail-open on errors - Add gateway_redis.go / gateway_redis_noop.go paired wiring files - Refactor GroupWriterCache and ContextFileInterceptor to accept injected caches - Add GOCLAW_REDIS_DSN env var, docker-compose.redis.yml overlay - Update Dockerfile and GitHub Actions with ENABLE_REDIS build arg - Add Redis variant to CI matrix (5 variants: latest, otel, tsnet, redis, full) |
||
|
Luan Vu
|
7d744eb4f2 |
refactor(oauth): DB-backed token storage, split codex.go, remove file-based artifacts (#65)
Replace file-based OAuth token storage with DB-backed storage using llm_providers (access token) + config_secrets (refresh token). - Store: Add Settings JSONB field, chatgpt_oauth provider type - OAuth: DBTokenSource backed by provider + secrets stores - HTTP: oauth.go uses DB stores + registers provider in-memory - Providers: chatgpt_oauth support in registerInMemory/registerProvidersFromDB - Config: Remove HasOAuthToken, revert envFallback→envStr - CLI: auth commands call HTTP API on running gateway - Split codex.go (478→189 LOC) into codex.go + codex_build.go + codex_types.go - Frontend: Remove fake OAUTH_PROVIDER_ID, use real DB-backed providers - Tests: Rewrite with mock stores, fix SSE mock servers |
||
|
Viet Tran
|
6895e369f6 |
refactor: remove standalone mode, consolidate to managed-only (PostgreSQL) (#70)
- Remove standalone mode code: file-based stores, standalone gateway, heartbeat service, SQLite memory, standalone docker-compose - Rename docker-compose.managed.yml → docker-compose.postgres.yml - Clean up ~130 Go comments referencing "managed mode" qualifier - Simplify docker-compose.yml env vars (providers/channels via web UI) - Update .env.example to essential vars only (token + encryption key) - Add setup wizard UI (provider → agent → channel bootstrap flow) - Add logs.tail WebSocket handler for live log streaming - Add cursor-pointer to interactive UI components - Clean up config page (remove standalone-only sections) - Update README and docs for managed-only architecture |
||
|
viettranxandClaude Opus 4.6
|
ed32e68c68 |
feat(quota): channel quota limiter + per-run tool budget + config UI
Part A — Channel quota limiter (managed mode): - DB-backed per-user/group request quotas with in-memory 60s TTL cache - Config merge priority: Groups > Channels > Providers > Default - Per-group quota override via channels.telegram.groups[chatID].quota - Migration 000009: index on channel_requests for quota queries - Hot-reload quota config via pub/sub (TopicConfigChanged) Part B — Per-run tool call budget: - Soft stop at configurable limit (default 25, per-agent override) - MaxToolCalls field on AgentDefaults + AgentSpec + LoopConfig - LLM gets one final call to summarize when budget exceeded Part C — Web UI + config page refactor: - QuotaSection with provider/channel dropdowns (useProviders, useChannelInstances) - Config page refactored to vertical sidebar tabs layout - Categories: General, Quota, Agents, Tools, Connections, Advanced, Raw Editor - Fixed config.patch RPC to serialize raw JSON + baseHash correctly - Config change pub/sub broadcast from handleApply/handlePatch Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> |
||
|
viettranx
|
a4325e2abe | feat: Improve agent context management with new compaction settings, session-level context window tracking, and calibrated token estimation for adaptive throttling. | ||
|
viettranx
|
67b19e4746 | feat: Implement standalone gateway mode with file-based agent storage and add path denial capabilities to filesystem tools. | ||
|
Viet TranandClaude Opus 4.6
|
f3f4c67b36 |
Initial commit: GoClaw AI agent gateway
Multi-agent AI gateway with WebSocket RPC, HTTP API, and messaging channel integrations. Go port of OpenClaw with multi-tenant PostgreSQL, per-user isolation, security hardening, and production observability. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> |