d42069b11e
fix(replay): preserve synthetic tool repair aliases
...
* fix(replay): preserve synthetic tool repair aliases
* test(replay): cover Bedrock repair ownership
2026-04-23 19:33:05 -07:00
a958b6e723
fix(runner): surface provider errors to webchat ( #70848 )
...
Surface non-retryable assistant provider failures from the embedded runner instead of letting surface_error fall through to continue_normal.
- Preserve external abort and plain timeout fall-through paths.
- Preserve raw provider error diagnostics on surfaced FailoverError.
- Add regression coverage for billing/auth/rate-limit/null-reason/error fall-through cases.
- Update changelog.
Fixes #70124 .
Thanks @truffle-dev.
2026-04-24 03:28:38 +01:00
3aa3551491
test: cover OpenAI server compaction docs
2026-04-24 03:15:47 +01:00
d289e400d5
fix: keep model catalog reads read-only
2026-04-24 02:01:58 +01:00
c7af4dcb31
fix: make models list read-only
2026-04-24 02:01:58 +01:00
93e95a2057
perf: speed up cli prepare tests
2026-04-24 01:55:02 +01:00
79066f5cab
fix(openai): synthesize codex gpt-5.5 oauth model
2026-04-24 01:49:00 +01:00
d4d307e07a
test: cover OpenAI GPT xhigh reasoning
2026-04-24 01:30:44 +01:00
f04a3dced0
build: update Pi model dependencies
2026-04-24 01:24:46 +01:00
cd8822cc5f
fix: preserve OpenAI-compatible image parts
2026-04-24 00:45:42 +01:00
a3aa13df9b
fix: prevent embedded runs from lowering undici timeouts
2026-04-24 00:34:47 +01:00
de3f3b8f93
feat(openai): pass image output options ( #70503 )
...
Co-authored-by: Peter Steinberger <steipete@gmail.com >
Co-authored-by: Otto Deng <ottodeng@users.noreply.github.com >
2026-04-24 00:17:12 +01:00
f0a7a85e7a
feat(agents): add generation tool timeouts
2026-04-24 00:05:38 +01:00
07049c8eba
fix(models): support Codex model add metadata ( #70820 )
2026-04-23 18:02:04 -05:00
6259f6addc
fix: harden provider and gateway test seams
2026-04-23 23:48:04 +01:00
f523bbfcd1
fix: align claude cli permissions with exec policy
...
Derive Claude CLI bypass mode from OpenClaw exec YOLO policy, preserve raw Claude permission-mode overrides, update docs/changelog, and cover global/per-agent policy behavior.
2026-04-23 23:11:34 +01:00
f718ba6601
fix(agents): preserve Codex model capacity guidance
2026-04-23 14:29:34 -07:00
f0300253c1
fix: add agent hook history helpers
2026-04-23 22:29:26 +01:00
51f9f94cc3
fix(hooks): harden cli transcript loading ( #70786 )
2026-04-23 14:25:27 -07:00
bceda6089a
fix(gateway): fail closed on runtime config edits ( #70726 )
...
* fix(gateway): fail closed on runtime config edits
* changelog + telegram topic requireMention depth
Append a user-facing Unreleased/Fixes entry describing the fail-closed
gateway config-mutation allowlist, and extend the allowlist so Telegram
topic-level paths like
channels.telegram.groups.<group>.topics.<topic>.requireMention stay
agent-tunable instead of being rejected as protected after this change.
2026-04-23 15:23:44 -06:00
02a8c13501
fix(codex): stop materializing auth bridges
2026-04-23 22:23:21 +01:00
d40dd9088e
feat(memory): configurable local embedding contextSize (default 4096) ( #70544 )
...
node-llama-cpp defaults contextSize to "auto", which on large embedding
models like Qwen3-Embedding-8B (trained context 40,960) inflates gateway
VRAM from ~8.8 GB to ~32 GB and causes OOM on single-GPU hosts that share
the gateway with an LLM runtime.
Expose memorySearch.local.contextSize in openclaw.json (number | "auto"),
default to 4096 which comfortably covers typical memory-search chunks
(128–512 tokens) while keeping non-weight VRAM bounded.
Closes #69667 .
2026-04-23 14:21:53 -07:00
2f14461976
test(openai): cover automatic image auth readiness
2026-04-23 22:14:55 +01:00
f1ad5e27e0
fix(agents): surface OpenAI model capacity errors
2026-04-23 14:04:35 -07:00
137dbc71f0
feat: expose harness selection decisions ( #70760 )
...
Codex harness selection now keeps the decision helper internal, logs debug-only selection reasons and candidates, and documents `/status` as the primary user-facing signal.
Thanks @100yenadmin.
Co-authored-by: Eva <eva@100yen.org >
2026-04-23 21:57:09 +01:00
10202f9279
fix(codex): approve bundled MCP loopback tools
2026-04-23 21:55:36 +01:00
f5042adf27
feat: add forked subagent context
2026-04-23 21:28:58 +01:00
f6336c5521
fix(openai): retire removed Codex Spark model
2026-04-23 21:16:46 +01:00
058e6f588a
fix(openai): align Codex fallback with GPT-5.5
2026-04-23 21:03:26 +01:00
ff56a9d41b
test(openai): prefer canonical GPT refs
2026-04-23 20:47:39 +01:00
f40f8a60cc
fix(agents): harden cli runner hook followups ( #70747 )
...
* fix(agents): harden cli runner hook followups
* fix(agents): harden cli runner hook followups
* fix(agents): harden cli runner hook followups
* fix(agents): harden cli runner hook followups
* fix(agents): harden cli runner hook followups
* fix(agents): harden cli runner hook followups
2026-04-23 12:32:30 -07:00
cd5bc2fc93
test(openai): cover GPT-5.5 defaults
2026-04-23 20:19:15 +01:00
a36903b94c
feat(openai): default to GPT-5.5
2026-04-23 20:19:15 +01:00
1d980cca6f
perf: trim cli prepare hook tests
2026-04-23 20:07:35 +01:00
7d30894c4a
fix(anthropic): stop forcing claude permission bypass
2026-04-23 12:03:00 -07:00
6590bc9037
fix: harden image generation directive output ( #70710 )
...
Co-authored-by: Vincent Koc <vincentkoc@ieee.org >
2026-04-23 19:44:06 +01:00
9cae47a956
fix: preserve Kimi tool call ids ( #70693 ) ( #70693 )
...
Co-authored-by: Peter Steinberger <steipete@gmail.com >
Co-authored-by: geri4 <2748115+geri4@users.noreply.github.com >
2026-04-23 19:34:09 +01:00
f7537faa21
fix(agents): emit cli runner llm lifecycle hooks ( #70731 )
2026-04-23 11:33:27 -07:00
32a38f125e
fix: keep codex cli images in workspace
2026-04-23 19:06:19 +01:00
9d8690d6b3
test: share temp plugin extension fixtures
2026-04-23 18:46:42 +01:00
961ab165ad
test: dedupe coding tool session store fixtures
2026-04-23 18:46:42 +01:00
ce681be084
test: dedupe subagent announcement fixtures
2026-04-23 18:46:42 +01:00
844f1dd87a
test: dedupe session lock symlink fixtures
2026-04-23 18:46:42 +01:00
359a656fdf
test: dedupe Anthropic cache policy fixtures
2026-04-23 18:46:42 +01:00
fc3aa07fbc
test: dedupe CLI attempt setup
2026-04-23 18:29:32 +01:00
060467ef83
test: dedupe OpenAI stream wrapper assertions
2026-04-23 18:29:32 +01:00
91a165c6af
test: align group prompt invariant
2026-04-23 18:21:05 +01:00
7a8d304a65
refactor: share core helper logic
2026-04-23 18:09:20 +01:00
3ae15cd746
test: cover codex transport fallback path
2026-04-23 17:58:19 +01:00
f4891b083d
fix(agents/failover): classify undici terminated and codex Request failed as timeout ( #69368 )
2026-04-23 17:58:19 +01:00
Vincent Koc