c52df32878
refactor: move bundled replay policy ownership into plugins ( #60452 )
...
* refactor: move bundled replay policy ownership into plugins
* test: preserve replay fallback until providers adopt hooks
* test: cover response replay branches for ollama and zai
---------
Co-authored-by: Shakker <shakkerdroid@gmail.com>
2026-04-03 19:08:10 +01:00
799c6f40aa
refactor: move provider replay runtime ownership into plugins ( #60126 )
...
* refactor: move provider replay runtime ownership into plugins
* fix(provider-runtime): address review followups
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
2026-04-03 23:14:37 +09:00
71346940ad
refactor: add provider replay runtime hook surfaces ( #59143 )
...
Merged via squash.
Prepared head SHA: 56b41e87a5
2026-04-01 13:45:41 -07:00
34b0a19a16
fix: use azure-openai-responses for Azure custom providers ( #50851 ) (thanks @kunalk16)
...
* Add azure-openai-responses
* Unit tests update for updated API
* Add entry for PR #50851
* Add comma to address PR comment
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* Address PR comment on sanitization of output
* Address review comment
* Revert commits
* Revert commit
* Update changelog stating Azure OpenAI only
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* Add references
* Address PR comment on sanitization of output
* Address review comment
* Revert commits
* Revert commit
* Address PR comment on sanitization of output
* Address review comment
* Revert commits
* Revert commit
* Fix generated file
* Add azure openai responses to OPENAI_RESPONSES_APIS
* Add azure openai responses to createParallelToolCallsWrapper
* Adding azure openai responses to attempt.ts
* Add azure openai responses to google.ts
* Address PR comment on sanitization of output
* Revert commit
* Address PR comment on sanitization of output
* Revert commit
* Address PR comment on sanitization of output
* Revert commit
* Fix changelog
* Fix linting
* fix: cover azure responses wrapper path (#50851 ) (thanks @kunalk16)
---------
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Co-authored-by: Ayaan Zaidi <hi@obviy.us>
2026-03-30 16:17:03 +05:30
5c5c64b612
Deduplicate repeated tool call IDs for OpenAI-compatible APIs ( #40996 )
...
Merged via squash.
Prepared head SHA: 38d8048359
2026-03-15 19:46:07 +08:00
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
ef2541ceb3
refactor: centralize transcript provider quirks
2026-03-08 18:26:35 +00:00
b41bcb08a2
refactor: expand provider capability registry
2026-03-08 16:22:52 +00:00
eba9dcc67a
Refactor release hardening follow-ups ( #39959 )
...
* build: fail fast on stale host-env swift policy
* build: sync generated host env swift policy
* build: guard bundled extension root dependency gaps
* refactor: centralize provider capability quirks
* test: table-drive provider regression coverage
* fix: block merge when prep branch has unpushed commits
* refactor: simplify models config merge preservation
2026-03-08 14:49:58 +00:00
097c588a6b
transcript-policy: use named Set for anthropic signature-excluded providers
2026-03-08 14:16:21 +00:00
2bf53c2cb6
transcript-policy: don't preserve thinking signatures for kimi-coding ( #39798 )
2026-03-08 14:16:21 +00:00
f304ca09b1
fix(agents): sanitize strict openai-compatible turn ordering from #39252 (thanks @scoootscooob)
...
Co-authored-by: scoootscooob <zhentongfan@gmail.com>
2026-03-07 23:42:19 +00:00
591264ef52
fix(agents): set preserveSignatures to isAnthropic in resolveTranscriptPolicy ( #32813 )
...
Merged via squash.
Prepared head SHA: f522d21ca5
2026-03-05 11:55:06 -08:00
a6489ab5e9
fix(agents): cap openai-completions tool call ids to provider-safe format ( #31947 )
...
Co-authored-by: bmendonca3 <bmendonca3@users.noreply.github.com>
2026-03-02 18:08:20 +00:00
252079f001
fix(agents): repair orphaned tool results for OpenAI after history truncation
...
repairToolUseResultPairing was gated behind !isOpenAi, skipping orphaned
tool_result cleanup for OpenAI providers. When limitHistoryTurns truncated
conversation history, tool_result messages whose matching tool_call was
before the truncation point survived and were sent as function_call_output
items with stale call_id references. OpenAI rejects these with:
"No tool call found for function call output with call_id ..."
Enable the repair universally — all providers need it after truncation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
(cherry picked from commit 97b065aa6e
2026-02-24 04:33:50 +00:00
792bd6195c
fix: recognize Bedrock as Anthropic-compatible in transcript policy
...
(cherry picked from commit 3b5154081c
2026-02-24 04:33:50 +00:00
13f32e2f7d
feat: Add Kilo Gateway provider ( #20212 )
...
* feat: Add Kilo Gateway provider
Add support for Kilo Gateway as a model provider, similar to OpenRouter.
Kilo Gateway provides a unified API that routes requests to many models
behind a single endpoint and API key.
Changes:
- Add kilocode provider option to auth-choice and onboarding flows
- Add KILOCODE_API_KEY environment variable support
- Add kilocode/ model prefix handling in model-auth and extra-params
- Add provider documentation in docs/providers/kilocode.md
- Update model-providers.md with Kilo Gateway section
- Add design doc for the integration
* kilocode: add provider tests and normalize onboard auth-choice registration
* kilocode: register in resolveImplicitProviders so models appear in provider filter
* kilocode: update base URL from /api/openrouter/ to /api/gateway/
* docs: fix formatting in kilocode docs
* fix: address PR review — remove kilocode from cacheRetention, fix stale model refs and CLI name in docs, fix TS2742
* docs: fix stale refs in design doc — Moltbot to OpenClaw, MoltbotConfig to OpenClawConfig, remove extra-params section, fix doc path
* fix: use resolveAgentModelPrimaryValue for AgentModelConfig union type
---------
Co-authored-by: Mark IJbema <mark@kilocode.ai>
2026-02-23 23:29:27 +00:00
9757d2bb64
fix(agents): normalize strict openai-compatible turn ordering
...
Co-authored-by: liuwenyong1985 <48443240+liuwenyong1985@users.noreply.github.com>
2026-02-23 12:44:23 +00:00
382fe8009a
refactor!: remove google-antigravity provider support
2026-02-23 05:20:14 +01:00
9176571ec1
fix(gemini): sanitize thoughtSignatures for native Google provider
...
Native Google Gemini provider was accumulating 2K-8K tokens of Base64
thoughtSignature blobs per turn, causing premature context overflow.
The sanitizer was only enabled for OpenRouter Gemini, not native Google.
Fixes #23392
2026-02-22 12:24:53 +01:00
feccac6723
fix: sanitize thinking blocks for GitHub Copilot Claude models (openclaw#19459) thanks @jackheuberger
...
Verified:
- pnpm build
- pnpm check
- pnpm test:macmini
Co-authored-by: jackheuberger <12731288+jackheuberger@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
2026-02-20 19:48:09 -06:00
b8b43175c5
style: align formatting with oxfmt 0.33
2026-02-18 01:34:35 +00:00
31f9be126c
style: run oxfmt and fix gate failures
2026-02-18 01:29:02 +00:00
d0cb8c19b2
chore: wtf.
2026-02-17 13:36:48 +09:00
ed11e93cf2
chore(format)
2026-02-16 23:20:16 -05:00
90ef2d6bdf
chore: Update formatting.
2026-02-17 09:18:40 +09:00
68ea063958
🤖 fix: preserve openai reasoning replay ids ( #17792 )
...
What:
- disable tool-call id sanitization for OpenAI/OpenAI Codex transcript policy
- gate id sanitization in image sanitizer to full mode only
- keep orphan reasoning downgrade scoped to OpenAI model-switch replay path
- update transcript policy, session-history, sanitizer, and reasoning replay tests
- document OpenAI model-switch orphan-reasoning cleanup behavior in transcript hygiene reference
Why:
- OpenAI Responses replay depends on canonical call_id|fc_id pairings for reasoning followers
- strict id rewriting in OpenAI path breaks follower matching and triggers rs_* orphan 400s
- limiting scope avoids behavior expansion while fixing the identified regression
Tests:
- pnpm vitest run src/agents/transcript-policy.test.ts src/agents/pi-embedded-runner.sanitize-session-history.test.ts src/agents/openai-responses.reasoning-replay.test.ts
- pnpm vitest run --config vitest.e2e.config.ts src/agents/transcript-policy.e2e.test.ts src/agents/pi-embedded-runner.sanitize-session-history.e2e.test.ts src/agents/pi-embedded-helpers.sanitize-session-messages-images.removes-empty-assistant-text-blocks-but-preserves.e2e.test.ts src/agents/pi-embedded-helpers.sanitizeuserfacingtext.e2e.test.ts
- pnpm lint
- pnpm format:check
- pnpm check:docs
- pnpm test (fails in current macOS bash 3.2 env at test/git-hooks-pre-commit.integration.test.ts: mapfile not found)
2026-02-15 22:45:01 -08:00
94763cd87d
Fix OpenAI/Codex tool call id sanitization for transcript policy ( #15279 )
2026-02-13 11:39:51 +00:00
1d2c5783fd
fix(agents): enable tool call ID sanitization for Anthropic provider ( #13830 )
...
Co-authored-by: 0xRaini <0xRaini@users.noreply.github.com>
2026-02-12 08:42:24 +09:00
f06dd8df06
chore: Enable "experimentalSortImports" in Oxfmt and reformat all imorts.
2026-02-01 10:03:47 +09:00
5ceff756e1
chore: Enable "curly" rule to avoid single-statement if confusion/errors.
2026-01-31 16:19:20 +09:00
2496056886
fix(minimax): use correct API endpoint and format
...
MiniMax has updated their API. The previous configuration used an
incorrect endpoint (api.minimax.io/anthropic) with anthropic-messages
format, which no longer works.
Changes:
- Update MINIMAX_API_BASE_URL to https://api.minimax.chat/v1
- Change API format from anthropic-messages to openai-completions
- Remove minimax from isAnthropicApi check in transcript-policy
This fixes the issue where MiniMax API calls return no results.
2026-01-27 19:48:38 -06:00
2424404fb4
docs: add transcript hygiene reference
2026-01-23 01:34:21 +00:00
db0235a26a
fix: gate transcript sanitization by provider
2026-01-23 00:42:45 +00:00
Josh Lehman
Kunal Karmakar
助爪
Frank Yang
Peter Steinberger
Peter Steinberger
Varun Chopra
Sid
bmendonca3
Ben Marvell
JackyWay
John Fawcett
echoVic
jackheuberger
cpojer
Sebastian
the sun gif man
JINNYEONG KIM
0xRain
hlbbbbbbb