Commit Graph

509 Commits

Author SHA1 Message Date
Frank Yang
01674c575e fix(agents): preserve blank local custom-provider API keys after onboarding
Co-authored-by: Xinhua Gu <xinhua.gu@gmail.com>
2026-03-14 11:08:19 +08:00
Peter Steinberger
d4b193b581 test: share embedded workspace attempt helpers 2026-03-14 01:41:17 +00:00
Peter Steinberger
fb93acb046 test: share compaction retry timer helpers 2026-03-14 01:41:16 +00:00
Peter Steinberger
6e3f0f9fcb refactor: share tool result char estimation 2026-03-14 01:41:16 +00:00
Peter Steinberger
e794417623 fix: resolve current ci regressions 2026-03-14 00:51:12 +00:00
Peter Steinberger
91b9c47dad test: share embedded compaction hook helpers 2026-03-14 00:30:14 +00:00
Peter Steinberger
41fa63a49e refactor: share anthropic compat flag checks 2026-03-13 23:35:27 +00:00
Vincent Koc
28b0d8e8bd fix(cron): prevent isolated cron nested lane deadlocks (#45459)
* fix(cron): resolve isolated session deadlock (#44805)

Map cron lane to nested in resolveGlobalLane to prevent deadlock when
isolated cron jobs trigger inner operations (e.g. compaction). Outer
execution holds the cron lane slot; inner work now uses nested lane.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* docs(changelog): add cron isolated deadlock note

---------

Co-authored-by: zhujian <zhujianxyz@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-13 14:19:40 -07:00
Peter Steinberger
92dbb59b79 refactor: share stream payload patch helper 2026-03-13 20:19:39 +00:00
Peter Steinberger
df2bda63c6 refactor: share compact hook success harness 2026-03-13 20:19:39 +00:00
Peter Steinberger
07dacec904 refactor: share embedded attempt test harness 2026-03-13 18:38:12 +00:00
정우용
72b6a11a83 fix: preserve persona and language continuity in compaction summaries (#10456)
Merged via squash.

Prepared head SHA: 4518fb20e1
Co-authored-by: keepitmello <71975659+keepitmello@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
2026-03-13 07:40:32 -07:00
Frank Yang
5ca0233db0 fix(agents): drop Anthropic thinking blocks on replay (#44843)
* agents: drop Anthropic thinking blocks on replay

* fix: extend anthropic replay sanitization openclaw#44429 thanks @jmcte

* fix: extend anthropic replay sanitization openclaw#44843 thanks @jmcte

* test: add bedrock replay sanitization coverage openclaw#44843

* test: cover anthropic provider drop-thinking hints openclaw#44843

---------

Co-authored-by: johnmteneyckjr <john.m.teneyck@gmail.com>
2026-03-13 16:57:56 +08:00
Efe Büken
771066d122 fix(compaction): use full-session token count for post-compaction sanity check (#28347)
Merged via squash.

Prepared head SHA: cf4eab1c51
Co-authored-by: efe-arv <259833796+efe-arv@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
2026-03-12 21:26:30 -07:00
Peter Steinberger
d5b3f2ed71 fix(models): keep codex spark codex-only 2026-03-13 00:53:21 +00:00
Peter Steinberger
35aafd7ca8 feat: add Anthropic fast mode support 2026-03-12 23:39:03 +00:00
Peter Steinberger
d5bffcdeab feat: add fast mode toggle for OpenAI models 2026-03-12 23:31:31 +00:00
ToToKr
9cd54ea882 fix: skip cache-ttl append after compaction to prevent double compaction (#28548)
Merged via squash.

Prepared head SHA: a4114a52bc
Co-authored-by: MoerAI <26067127+MoerAI@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
2026-03-12 15:17:18 -07:00
Rodrigo Uroz
143e593ab8 Compaction Runner: wire post-compaction memory sync (#25561)
Merged via squash.

Prepared head SHA: 6d2bc02cc1
Co-authored-by: rodrigouroz <384037+rodrigouroz@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
2026-03-12 14:24:29 -07:00
Josh Lehman
50cc375c11 feat(context-engine): plumb sessionKey into all ContextEngine methods (#44157)
Merged via squash.

Prepared head SHA: 0b341f6f4c
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
2026-03-12 12:43:36 -07:00
Marcus Castro
e525957b4f fix(sandbox): restore spawned workspace handoff (#44307) 2026-03-12 16:12:08 -03:00
Vincent Koc
4ca84acf24 fix(runtime): duplicate messages, share singleton state across bundled chunks (#43683)
* Tests: add fresh module import helper

* Process: share command queue runtime state

* Agents: share embedded run runtime state

* Reply: share followup queue runtime state

* Reply: share followup drain callback state

* Reply: share queued message dedupe state

* Reply: share inbound dedupe state

* Tests: cover shared command queue runtime state

* Tests: cover shared embedded run runtime state

* Tests: cover shared followup queue runtime state

* Tests: cover shared inbound dedupe state

* Tests: cover shared Slack thread participation state

* Slack: share sent thread participation state

* Tests: document fresh import helper

* Telegram: share draft stream runtime state

* Tests: cover shared Telegram draft stream state

* Telegram: share sent message cache state

* Tests: cover shared Telegram sent message cache

* Telegram: share thread binding runtime state

* Tests: cover shared Telegram thread binding state

* Tests: avoid duplicate shared queue reset

* refactor(runtime): centralize global singleton access

* refactor(runtime): preserve undefined global singleton values

* test(runtime): cover undefined global singleton values

---------

Co-authored-by: Nimrod Gutman <nimrod.gutman@gmail.com>
2026-03-12 14:59:27 -04:00
Vincent Koc
1492ad20a9 Ollama/Kimi: apply Moonshot payload compatibility (#44274)
* Runner: extend Moonshot payload compat to Ollama Kimi

* Changelog: note Ollama Kimi tool routing

* Tests: cover Ollama Kimi payload compat

* Runner: narrow Ollama Kimi payload compat
2026-03-12 14:17:01 -04:00
Vincent Koc
86135d5889 Kimi Coding: set default subscription user agent (#44248)
* Providers: set default Kimi coding user agent

* Tests: cover Kimi coding header overrides

* Changelog: note Kimi coding user agent

* Tests: satisfy Kimi provider fixture type

* Update CHANGELOG.md

* Providers: preserve Kimi headers through models merge
2026-03-12 13:30:07 -04:00
yuweuii
b3e6f92fd2 runner: infer names from malformed toolCallId variants (#34485)
Merged via squash.

Prepared head SHA: 150ea1a7c9
Co-authored-by: yuweuii <82372187+yuweuii@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
2026-03-12 09:58:23 -07:00
Jacob Riff
3fa91cd69d feat: add sessions_yield tool for cooperative turn-ending (#36537)
Merged via squash.

Prepared head SHA: 75d9204c86
Co-authored-by: jriff <50276+jriff@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
2026-03-12 08:46:47 -07:00
Rodrigo Uroz
688e3f0863 Compaction Runner: emit transcript updates post-compact (#25558)
Merged via squash.

Prepared head SHA: 8a858436ed
Co-authored-by: rodrigouroz <384037+rodrigouroz@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
2026-03-12 08:22:12 -07:00
Vincent Koc
2f037f0930 Agents: adapt pi-ai oauth and payload hooks 2026-03-12 10:19:14 -04:00
rabsef-bicrym
ff47876e61 fix: carry observed overflow token counts into compaction (#40357)
Merged via squash.

Prepared head SHA: b99eed4329
Co-authored-by: rabsef-bicrym <52549148+rabsef-bicrym@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
2026-03-12 06:58:42 -07:00
Vincent Koc
9aeaa19e9e Agents: clear invalidated Kimi tool arg repair (#43824) 2026-03-12 03:53:06 -04:00
Vincent Koc
d8ee97c466 Agents: recover malformed Anthropic-compatible tool call args (#42835)
* Agents: recover malformed anthropic tool call args

* Agents: add malformed tool call regression test

* Changelog: note Kimi tool call arg recovery

* Agents: repair toolcall end message snapshots

* Agents: narrow Kimi tool call arg repair
2026-03-12 03:28:22 -04:00
Toven
ade748176f OpenRouter: surface free Hunter and Healer stealth models for the next week (#43642)
* Models: add temporary Hunter and Healer alpha to OpenRouter catalog

* Add temporary OpenRouter stealth catalog entries

---------

Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
2026-03-11 22:58:48 -05:00
David Rudduck
f01c41b27a fix(context-engine): guard compact() throw + fire hooks for ownsCompaction engines (#41361)
Merged via squash.

Prepared head SHA: 0957b32dc6
Co-authored-by: davidrudduck <47308254+davidrudduck@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
2026-03-11 20:19:20 -07:00
Peter Steinberger
980619b9be fix: harden openai websocket replay 2026-03-12 02:13:06 +00:00
zhoulf1006
453c8d7c1b fix(hooks): add missing trigger and channelId to agent_end, llm_input, and llm_output hook contexts (#42362)
Merged via squash.

Prepared head SHA: e6d7b7e31a
Co-authored-by: zhoulf1006 <35586967+zhoulf1006@users.noreply.github.com>
Co-authored-by: hydro13 <6640526+hydro13@users.noreply.github.com>
Reviewed-by: @hydro13
2026-03-11 23:40:13 +01:00
ingyukoh
2a18cbb110 fix(agents): prevent false billing error replacing valid response text (#40616)
Merged via squash.

Prepared head SHA: 05179362b4
Co-authored-by: ingyukoh <6015960+ingyukoh@users.noreply.github.com>
Co-authored-by: altaywtf <9790196+altaywtf@users.noreply.github.com>
Reviewed-by: @altaywtf
2026-03-11 22:00:11 +03:00
VibhorGautam
4473242b4f fix: use unknown instead of rate_limit as default cooldown reason (#42911)
Merged via squash.

Prepared head SHA: bebf6704d7
Co-authored-by: VibhorGautam <55019395+VibhorGautam@users.noreply.github.com>
Co-authored-by: altaywtf <9790196+altaywtf@users.noreply.github.com>
Reviewed-by: @altaywtf
2026-03-11 21:34:14 +03:00
Tak Hoffman
87876a3e36 Fix env proxy bootstrap for model traffic (#43248)
* Fix env proxy bootstrap for model traffic

* Address proxy dispatcher review followups

* Fix proxy env precedence for empty lowercase vars
2026-03-11 10:21:35 -05:00
Andyliu
10e6e27451 fix(models): guard optional model input capabilities (#42096)
Merged via squash.

Prepared head SHA: d398fa0222
Co-authored-by: andyliu <2377291+andyliu@users.noreply.github.com>
Co-authored-by: hydro13 <6640526+hydro13@users.noreply.github.com>
Reviewed-by: @hydro13
2026-03-11 13:43:59 +01:00
MoerAI
a78674f115 fix(context-pruning): prune image-containing tool results instead of skipping them (#41789) 2026-03-11 18:07:37 +08:00
ademczuk
dc4441322f fix(agents): include azure-openai in Responses API store override (#42934)
Merged via squash.

Prepared head SHA: d3285fef41
Co-authored-by: ademczuk <5212682+ademczuk@users.noreply.github.com>
Co-authored-by: frankekn <4488090+frankekn@users.noreply.github.com>
Reviewed-by: @frankekn
2026-03-11 16:16:10 +08:00
Josh Avant
36d2ae2a22 SecretRef: harden custom/provider secret persistence and reuse (#42554)
* Models: gate custom provider keys by usable secret semantics

* Config: project runtime writes onto source snapshot

* Models: prevent stale apiKey preservation for marker-managed providers

* Runner: strip SecretRef marker headers from resolved models

* Secrets: scan active agent models.json path in audit

* Config: guard runtime-source projection for unrelated configs

* Extensions: fix onboarding type errors in CI

* Tests: align setup helper account-enabled expectation

* Secrets audit: harden models.json file reads

* fix: harden SecretRef custom/provider secret persistence (#42554) (thanks @joshavant)
2026-03-10 23:55:10 +00:00
Peter Steinberger
283570de4d fix: normalize stale openai completions transport 2026-03-10 20:23:03 +00:00
Ayaan Zaidi
ac88a39acc fix: align pi-ai 0.57.1 oauth imports and payload hooks 2026-03-10 20:29:03 +05:30
joshavant
59bc3c6630 Agents: align onPayload callback and OAuth imports 2026-03-10 08:50:30 -05:00
Daniel Reis
3495563cfe fix(sandbox): pass real workspace to sessions_spawn when workspaceAccess is ro (#40757)
Merged via squash.

Prepared head SHA: 0e8b27bf80
Co-authored-by: dsantoreis <66363641+dsantoreis@users.noreply.github.com>
Co-authored-by: mcaxtr <7562095+mcaxtr@users.noreply.github.com>
Reviewed-by: @mcaxtr
2026-03-10 04:12:50 -03:00
Frank Yang
8306eabf85 fix(agents): forward memory flush write path (#41761)
Merged via squash.

Prepared head SHA: 0a8ebf8e5b
Co-authored-by: frankekn <4488090+frankekn@users.noreply.github.com>
Co-authored-by: frankekn <4488090+frankekn@users.noreply.github.com>
Reviewed-by: @frankekn
2026-03-10 14:18:41 +08:00
Frank Yang
96e4975922 fix: protect bootstrap files during memory flush (#38574)
Merged via squash.

Prepared head SHA: a0b9a02e2e
Co-authored-by: frankekn <4488090+frankekn@users.noreply.github.com>
Co-authored-by: frankekn <4488090+frankekn@users.noreply.github.com>
Reviewed-by: @frankekn
2026-03-10 12:44:33 +08:00
Harold Hunt
de49a8b72c Telegram: exec approvals for OpenCode/Codex (#37233)
Merged via squash.

Prepared head SHA: f243379094
Co-authored-by: huntharo <5617868+huntharo@users.noreply.github.com>
Co-authored-by: huntharo <5617868+huntharo@users.noreply.github.com>
Reviewed-by: @huntharo
2026-03-09 23:04:35 -04:00
Altay
531e8362b1 Agents: add fallback error observations (#41337)
Merged via squash.

Prepared head SHA: 852469c82f
Co-authored-by: altaywtf <9790196+altaywtf@users.noreply.github.com>
Co-authored-by: altaywtf <9790196+altaywtf@users.noreply.github.com>
Reviewed-by: @altaywtf
2026-03-10 01:12:10 +03:00