ef4fa43df8
fix: prevent nodes media base64 context bloat ( #34332 )
2026-03-04 16:53:30 +05:30
257e2f5338
fix: relay ACP sessions_spawn parent streaming ( #34310 ) (thanks @vincentkoc) ( #34310 )
...
Co-authored-by: Onur Solmaz <2453968+osolmaz@users.noreply.github.com>
2026-03-04 11:44:20 +01:00
646817dd80
fix(outbound): unify resolved cfg threading across send paths ( #33987 )
2026-03-04 00:20:44 -06:00
4d183af0cf
fix: code/cli acpx reliability 20260304 ( #34020 )
...
* agents: switch claude-cli defaults to bypassPermissions
* agents: add claude-cli default args coverage
* agents: emit watchdog stall system event for cli runs
* agents: test cli watchdog stall system event
* acpx: fallback to sessions new when ensure returns no ids
* acpx tests: mock sessions new fallback path
* acpx tests: cover ensure-empty fallback flow
* skills: clarify claude print mode without pty
* docs: update cli-backends claude default args
* docs: refresh cli live test default args
* gateway tests: align live claude args defaults
* changelog: credit claude/acpx reliability fixes
* Agents: normalize legacy Claude permission flag overrides
* Tests: cover legacy Claude permission override normalization
* Changelog: note legacy Claude permission flag auto-normalization
* ACPX: fail fast when ensure/new return no session IDs
* ACPX tests: support empty sessions new fixture output
* ACPX tests: assert ensureSession failure when IDs missing
* CLI runner: scope watchdog heartbeat wake to session
* CLI runner tests: assert session-scoped watchdog wake
* Update CHANGELOG.md
2026-03-04 01:15:28 -05:00
230fea1ca6
feat(web-search): switch Perplexity to native Search API ( #33822 )
...
* feat: Add Perplexity Search API as web_search provider
* docs fixes
* domain_filter validation
* address comments
* provider-specific options in cache key
* add validation for unsupported date filters
* legacy fields
* unsupported_language guard
* cache key matches the request's precedence order
* conflicting_time_filters guard
* unsupported_country guard
* invalid_date_range guard
* pplx validate for ISO 639-1 format
* docs: add Perplexity Search API changelog entry
* unsupported_domain_filter guard
---------
Co-authored-by: Shadow <hi@shadowing.dev>
2026-03-03 22:57:19 -06:00
6962d2d79f
fix: harden sessions_spawn attachment schema landing ( #33648 ) (thanks @anisoptera)
2026-03-04 10:05:41 +05:30
965ce31d84
fix(sessions-spawn): remove maxLength from attachment content schema to fix llama.cpp GBNF grammar overflow
2026-03-04 10:05:41 +05:30
7f2708a8c3
fix(routing): unify session delivery invariants for duplicate suppression ( #33786 )
...
* Routing: unify session delivery invariants
* Routing: address PR review feedback
* Routing: tighten topic and session-scope suppression
* fix(chat): inherit routes for per-account channel-peer sessions
2026-03-03 21:40:38 -06:00
9889c6da53
Runtime: stabilize tool/run state transitions under compaction and backpressure
...
Synthesize runtime state transition fixes for compaction tool-use integrity and long-running handler backpressure.
Sources: #33630 , #33583
Co-authored-by: Kevin Shenghui <shenghuikevin@gmail.com>
Co-authored-by: Theo Tarr <theodore@tarr.com>
2026-03-03 21:25:32 -06:00
1c200ca7ae
follow-up: align ingress, atomic paths, and channel tests with credential semantics ( #33733 )
...
Merged via squash.
Prepared head SHA: c290c2ab6a
2026-03-03 20:29:46 -06:00
6842877b2e
build: prevent mixed static/dynamic pi-model-discovery imports
2026-03-03 21:27:14 -05:00
21e8d88c1d
build: fix ineffective dynamic imports with lazy boundaries ( #33690 )
...
Merged via squash.
Prepared head SHA: 38b3c23d6f
2026-03-03 20:14:41 -05:00
e8cb0484ce
fix(security): strip partial API token from status labels ( #33262 )
...
Merged via squash.
Prepared head SHA: 5fe81704e6
2026-03-03 15:11:49 -08:00
e4b4486a96
Agent: unify bootstrap truncation warning handling ( #32769 )
...
Merged via squash.
Prepared head SHA: 5d6d4ddfa6
2026-03-03 16:28:38 -05:00
e28ff1215c
fix: discord auto presence health signal ( #33277 ) (thanks @thewilloftheshadow) ( #33277 )
2026-03-03 11:20:59 -06:00
606cd0d591
feat(tool-truncation): use head+tail strategy to preserve errors during truncation ( #20076 )
...
Merged via squash.
Prepared head SHA: 6edebf22b1
2026-03-03 08:11:14 -08:00
c8b45a4c5c
Compaction/Safeguard: preserve recent turns verbatim ( #25554 )
...
Merged via squash.
Prepared head SHA: 7fb33c411c
2026-03-03 07:00:49 -08:00
627813aba4
fix(heartbeat): scope exec wake dispatch to session key ( #32724 )
...
Merged via squash.
Prepared head SHA: 563fee0e65
2026-03-03 14:47:40 +03:00
4ffe15c6b2
fix(telegram): warn when accounts.default is missing in multi-account setup ( #32544 )
...
Merged via squash.
Prepared head SHA: 7ebc3f65b2
2026-03-03 03:27:19 -05:00
2370ea5d1b
agents: propagate config for embedded skill loading
2026-03-03 02:44:56 -05:00
5341b5c71c
Diffs: Migrate tool usage guidance from before_prompt_build to a plugin skill ( #32630 )
...
Merged via squash.
Prepared head SHA: 585697a4e1
2026-03-03 01:50:59 -05:00
de9031da22
fix: improve compaction summary instructions to preserve active work ( #8903 )
...
fix: improve compaction summary instructions to preserve active work
Expand staged-summary merge instructions to preserve active task status, batch progress, latest user request, and follow-up commitments so compaction handoffs retain in-flight work context.
Co-authored-by: joetomasone <56984887+joetomasone@users.noreply.github.com>
Co-authored-by: Josh Lehman <josh@martian.engineering>
2026-03-02 22:36:19 -08:00
fe92113472
test(e2e): isolate module mocks across harnesses
2026-03-03 05:52:14 +00:00
a9ec75fe81
fix(gateway): flush throttled delta before emitChatFinal ( #24856 )
...
* fix(gateway): flush throttled delta before emitChatFinal
The 150ms throttle in emitChatDelta can suppress the last text chunk
before emitChatFinal fires, causing streaming clients (e.g. ACP) to
receive truncated responses. The final event carries the complete text,
but clients that build responses incrementally from deltas miss the
tail end.
Flush one last unthrottled delta with the complete buffered text
immediately before sending the final event. This ensures all streaming
consumers have the full response without needing to reconcile deltas
against the final payload.
* fix(gateway): avoid duplicate delta flush when buffer unchanged
Track the text length at the time of the last broadcast. The flush in
emitChatFinal now only sends a delta if the buffer has grown since the
last broadcast, preventing duplicate sends when the final delta passed
the 150ms throttle and was already broadcast.
* fix(gateway): honor heartbeat suppression in final delta flush
* test(gateway): add final delta flush and dedupe coverage
* fix(gateway): skip final flush for silent lead fragments
* docs(changelog): note gateway final-delta flush fix credits
---------
Co-authored-by: Jonathan Taylor <visionik@pobox.com>
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
2026-03-02 23:45:46 -05:00
17bb87f432
fix(venice): retry model discovery on transient fetch failures
2026-03-03 03:21:00 +00:00
806803b7ef
feat(secrets): expand SecretRef coverage across user-supplied credentials ( #29580 )
...
* feat(secrets): expand secret target coverage and gateway tooling
* docs(secrets): align gateway and CLI secret docs
* chore(protocol): regenerate swift gateway models for secrets methods
* fix(config): restore talk apiKey fallback and stabilize runner test
* ci(windows): reduce test worker count for shard stability
* ci(windows): raise node heap for test shard stability
* test(feishu): make proxy env precedence assertion windows-safe
* fix(gateway): resolve auth password SecretInput refs for clients
* fix(gateway): resolve remote SecretInput credentials for clients
* fix(secrets): skip inactive refs in command snapshot assignments
* fix(secrets): scope gateway.remote refs to effective auth surfaces
* fix(secrets): ignore memory defaults when enabled agents disable search
* fix(secrets): honor Google Chat serviceAccountRef inheritance
* fix(secrets): address tsgo errors in command and gateway collectors
* fix(secrets): avoid auth-store load in providers-only configure
* fix(gateway): defer local password ref resolution by precedence
* fix(secrets): gate telegram webhook secret refs by webhook mode
* fix(secrets): gate slack signing secret refs to http mode
* fix(secrets): skip telegram botToken refs when tokenFile is set
* fix(secrets): gate discord pluralkit refs by enabled flag
* fix(secrets): gate discord voice tts refs by voice enabled
* test(secrets): make runtime fixture modes explicit
* fix(cli): resolve local qr password secret refs
* fix(cli): fail when gateway leaves command refs unresolved
* fix(gateway): fail when local password SecretRef is unresolved
* fix(gateway): fail when required remote SecretRefs are unresolved
* fix(gateway): resolve local password refs only when password can win
* fix(cli): skip local password SecretRef resolution on qr token override
* test(gateway): cast SecretRef fixtures to OpenClawConfig
* test(secrets): activate mode-gated targets in runtime coverage fixture
* fix(cron): support SecretInput webhook tokens safely
* fix(bluebubbles): support SecretInput passwords across config paths
* fix(msteams): make appPassword SecretInput-safe in onboarding/token paths
* fix(bluebubbles): align SecretInput schema helper typing
* fix(cli): clarify secrets.resolve version-skew errors
* refactor(secrets): return structured inactive paths from secrets.resolve
* refactor(gateway): type onboarding secret writes as SecretInput
* chore(protocol): regenerate swift models for secrets.resolve
* feat(secrets): expand extension credential secretref support
* fix(secrets): gate web-search refs by active provider
* fix(onboarding): detect SecretRef credentials in extension status
* fix(onboarding): allow keeping existing ref in secret prompt
* fix(onboarding): resolve gateway password SecretRefs for probe and tui
* fix(onboarding): honor secret-input-mode for local gateway auth
* fix(acp): resolve gateway SecretInput credentials
* fix(secrets): gate gateway.remote refs to remote surfaces
* test(secrets): cover pattern matching and inactive array refs
* docs(secrets): clarify secrets.resolve and remote active surfaces
* fix(bluebubbles): keep existing SecretRef during onboarding
* fix(tests): resolve CI type errors in new SecretRef coverage
* fix(extensions): replace raw fetch with SSRF-guarded fetch
* test(secrets): mark gateway remote targets active in runtime coverage
* test(infra): normalize home-prefix expectation across platforms
* fix(cli): only resolve local qr password refs in password mode
* test(cli): cover local qr token mode with unresolved password ref
* docs(cli): clarify local qr password ref resolution behavior
* refactor(extensions): reuse sdk SecretInput helpers
* fix(wizard): resolve onboarding env-template secrets before plaintext
* fix(cli): surface secrets.resolve diagnostics in memory and qr
* test(secrets): repair post-rebase runtime and fixtures
* fix(gateway): skip remote password ref resolution when token wins
* fix(secrets): treat tailscale remote gateway refs as active
* fix(gateway): allow remote password fallback when token ref is unresolved
* fix(gateway): ignore stale local password refs for none and trusted-proxy
* fix(gateway): skip remote secret ref resolution on local call paths
* test(cli): cover qr remote tailscale secret ref resolution
* fix(secrets): align gateway password active-surface with auth inference
* fix(cli): resolve inferred local gateway password refs in qr
* fix(gateway): prefer resolvable remote password over token ref pre-resolution
* test(gateway): cover none and trusted-proxy stale password refs
* docs(secrets): sync qr and gateway active-surface behavior
* fix: restore stability blockers from pre-release audit
* Secrets: fix collector/runtime precedence contradictions
* docs: align secrets and web credential docs
* fix(rebase): resolve integration regressions after main rebase
* fix(node-host): resolve gateway secret refs for auth
* fix(secrets): harden secretinput runtime readers
* gateway: skip inactive auth secretref resolution
* cli: avoid gateway preflight for inactive secret refs
* extensions: allow unresolved refs in onboarding status
* tests: fix qr-cli module mock hoist ordering
* Security: align audit checks with SecretInput resolution
* Gateway: resolve local-mode remote fallback secret refs
* Node host: avoid resolving inactive password secret refs
* Secrets runtime: mark Slack appToken inactive for HTTP mode
* secrets: keep inactive gateway remote refs non-blocking
* cli: include agent memory secret targets in runtime resolution
* docs(secrets): sync docs with active-surface and web search behavior
* fix(secrets): keep telegram top-level token refs active for blank account tokens
* fix(daemon): resolve gateway password secret refs for probe auth
* fix(secrets): skip IRC NickServ ref resolution when NickServ is disabled
* fix(secrets): align token inheritance and exec timeout defaults
* docs(secrets): clarify active-surface notes in cli docs
* cli: require secrets.resolve gateway capability
* gateway: log auth secret surface diagnostics
* secrets: remove dead provider resolver module
* fix(secrets): restore gateway auth precedence and fallback resolution
* fix(tests): align plugin runtime mock typings
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
2026-03-03 02:58:20 +00:00
6408b7f81c
refactor(agents): dedupe steer restart test replacement flow
2026-03-03 02:53:14 +00:00
1538813096
refactor(agents): dedupe ollama provider test scaffolding
2026-03-03 02:53:14 +00:00
1a52d943ed
refactor(tests): dedupe model compat assertions
2026-03-03 02:53:13 +00:00
6472e03412
refactor(agents): share failover error matchers
2026-03-03 02:51:00 +00:00
2d033d2aa8
refactor(agents): split tool-result char estimator
2026-03-03 02:42:43 +00:00
87977d7a19
fix: unblock build type errors
2026-03-03 08:11:51 +05:30
30ab9b2068
fix(agents): recognize connection errors as retryable timeout failures ( #31697 )
...
* fix(agents): recognize connection errors as retryable timeout failures
## Problem
When a model endpoint becomes unreachable (e.g., local proxy down,
relay server offline), the failover system fails to switch to the
next candidate model. Errors like "Connection error." are not
classified as retryable, causing the session to hang on a broken
endpoint instead of falling back to healthy alternatives.
## Root Cause
Connection/network errors are not recognized by the current failover
classifier:
- Text patterns like "Connection error.", "fetch failed", "network error"
- Error codes like ECONNREFUSED, ENOTFOUND, EAI_AGAIN (in message text)
While `failover-error.ts` handles these as error codes (err.code),
it misses them when they appear as plain text in error messages.
## Solution
Extend timeout error patterns to include connection/network failures:
**In `errors.ts` (ERROR_PATTERNS.timeout):**
- Text: "connection error", "network error", "fetch failed", etc.
- Regex: /\beconn(?:refused|reset|aborted)\b/i, /\benotfound\b/i, /\beai_again\b/i
**In `failover-error.ts` (TIMEOUT_HINT_RE):**
- Same patterns for non-assistant error paths
## Testing
Added test cases covering:
- "Connection error."
- "fetch failed"
- "network error: ECONNREFUSED"
- "ENOTFOUND" / "EAI_AGAIN" in message text
## Impact
- **Compatibility:** High - only expands retryable error detection
- **Behavior:** Connection failures now trigger automatic fallback
- **Risk:** Low - changes are additive and well-tested
* style: fix code formatting for test file
2026-03-03 02:37:23 +00:00
4c32411bee
fix(exec): suggest increasing timeout on timeouts
2026-03-03 02:35:10 +00:00
91cdb703bd
Agents: add context metadata warmup retry backoff
2026-03-02 21:34:55 -05:00
62582fc088
perf(agents): cache per-pass context char estimates
2026-03-03 02:32:13 +00:00
6ab9e00e17
fix: resolve pi-tools typing regressions
2026-03-03 02:27:59 +00:00
d380ed710d
refactor(agents): split pi-tools param and host-edit wrappers
2026-03-03 02:19:34 +00:00
70db52de71
test(agents): centralize AgentMessage fixtures and remove unsafe casts
2026-03-03 02:14:15 +00:00
0fb3f188b2
fix(agents): only recover edit when oldText no longer in file (review feedback)
2026-03-03 02:06:59 +00:00
bf6aa7ca67
fix(agents): treat host edit tool as success when file contains newText after upstream throw ( fixes #32333 )
2026-03-03 02:06:59 +00:00
3eec79bd6c
feat(memory): add Ollama embedding provider ( #26349 )
...
Merged via /review-pr -> /prepare-pr -> /merge-pr.
Prepared head SHA: ac41386543
2026-03-02 20:56:40 -05:00
39520ad21b
test(agents): tighten pi message typing and dedupe malformed tool-call cases
2026-03-03 01:44:21 +00:00
bd8c3230e8
fix: force supportsDeveloperRole=false for non-native OpenAI endpoints ( #29479 )
...
Merged via squash.
Prepared head SHA: 1416c584ac
2026-03-02 20:43:49 -05:00
11e1363d2d
feat(hooks): add trigger and channelId to plugin hook agent context ( #28623 )
...
* feat(hooks): add trigger and channelId to plugin hook agent context
Adds `trigger` and `channelId` fields to `PluginHookAgentContext` so
plugins can determine what initiated the agent run and which channel
it originated from, without session-key parsing or Redis bridging.
trigger values: "user", "heartbeat", "cron", "memory"
channelId values: "telegram", "discord", "whatsapp", etc.
Both fields are threaded through run.ts and attempt.ts hookCtx so all
hook phases receive them (before_model_resolve, before_prompt_build,
before_agent_start, llm_input, llm_output, agent_end).
channelId falls back from messageChannel to messageProvider when the
former is not set. followup-runner passes originatingChannel so queued
followup runs also carry channel context.
* docs(changelog): note hook context parity fix for #28623
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
2026-03-02 17:39:20 -08:00
6b6af1a64f
refactor(tests): dedupe web fetch and embedded tool hook fixtures
2026-03-03 01:37:12 +00:00
c1b37f29f0
refactor(tests): dedupe browser and telegram tool test fixtures
2026-03-03 01:37:12 +00:00
a3b674cc98
refactor(tests): dedupe agent lock and loop detection fixtures
2026-03-03 01:37:12 +00:00
747902a26a
fix(hooks): propagate run/tool IDs for tool hook correlation ( #32360 )
...
* Plugin SDK: add run and tool call fields to tool hooks
* Agents: propagate runId and toolCallId in before_tool_call
* Agents: thread runId through tool wrapper context
* Runner: pass runId into tool hook context
* Compaction: pass runId into tool hook context
* Agents: scope after_tool_call start data by run
* Tests: cover run and tool IDs in before_tool_call hooks
* Tests: add run-scoped after_tool_call collision coverage
* Hooks: scope adjusted tool params by run
* Tests: cover run-scoped adjusted param collisions
* Hooks: preserve active tool start metadata until end
* Changelog: add tool-hook correlation note
2026-03-02 17:23:08 -08:00
61adcea68e
fix(test): tighten tool result typing in context pruning tests
2026-03-03 01:18:29 +00:00
Ayaan Zaidi
Bob
Josh Avant
Vincent Koc
Kesku
Isis Anisoptera
Tak Hoffman
Gustavo Madeira Santana
Cui Chen
Shadow
Jason L. West, Sr.
Rodrigo Uroz
Altay
Sid
Eugene
JT
Peter Steinberger
Viz
AI南柯(KingMo)
AaronWander
倪汉杰0668001185
nico-hoff
Sk Akram
David Rudduck