Commit Graph

25 Commits

Author SHA1 Message Date
Shakker
9d37d06233 test: isolate model selection normalization 2026-05-09 13:26:45 +01:00
pashpashpash
02fe0d8978 Keep OpenAI Codex migrations on automatic runtime routing (#79238)
* fix: keep migrated openai codex routes automatic

* scope runtime policy to providers and models

* fix runtime policy surfaces

* fix ci runtime policy checks

* fix doctor stale session runtime pins
2026-05-08 16:05:35 +09:00
pashpashpash
1c33990108 Route OpenAI agents through Codex by default (#78899)
* route openai agent runs through codex

* fix: load codex plugin for implicit openai runtime

* fix: preserve explicit OpenAI PI Codex auth routing

* fix: show codex auth for openai model listing

* fix: map codex auth into configured openai list rows

* fix: preserve explicit openai pi auth routes

* docs: keep openai model route examples canonical

* fix: clean openai codex test fixtures

* fix: scope codex auth status fallback

* fix: repair current ci boundary drift
2026-05-07 19:46:49 +09:00
Edionwheels
58f81b0e04 fix(codex): honor OAuth contextTokens in native harness
Fixes #77858.

Co-authored-by: Edionwheels <267595845+lilesjtu@users.noreply.github.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
2026-05-06 08:54:52 +01:00
Peter Steinberger
f4a9d34f98 fix(model): explain rejected session overrides 2026-04-28 23:33:24 +01:00
Peter Steinberger
b09afa2993 fix: keep auto model fallbacks pinned until reset 2026-04-27 09:27:19 +01:00
Tak Hoffman
87eee6e640 fix(thinking): default implicit reasoning models to medium (#70601)
* fix(thinking): default implicit reasoning models to medium

* fix(thinking): preserve reasoning metadata during default resolution
2026-04-23 07:55:47 -05:00
Peter Steinberger
215d5fb320 fix: clear auto-failover model overrides (#69365) (thanks @Chevron7Locked) 2026-04-21 03:35:16 +01:00
Kevin O'Neill
dc0e966ed2 fix(model-selection): address Codex review P2 feedback on auto-heal override clearing
Three corrections to the auto-failover self-healing introduced in the prior commit:

1. Reset in-memory provider/model to configured primary after clearing auto override.
   get-reply-directives.ts preloads provider/model from the stored override before
   calling createModelSelectionState, so clearing only session state still ran the
   current turn on the fallback. Now provider/model are reset to defaultProvider/
   defaultModel so this turn retries the primary immediately, not on the next turn.

2. Remove resetModelOverride = true from the auto-heal path. That flag triggers a
   "Model override not allowed for this agent" system event in
   applyInlineDirectiveOverrides, which is incorrect: the override was valid and set
   by the fallback loop — it just expired once the primary recovered. Auto-heal is
   not an allowlist violation.

3. Add a test case that verifies the in-memory reset when the caller pre-loads the
   fallback provider/model (simulating the get-reply-directives.ts preload path).

Known limitation (noted in comment): channel model overrides (channels.modelByChannel)
are skipped on the recovery turn because hasSessionModelOverride was true when they
were evaluated at preload time. They resume on the following turn once session state
is clear. Fixing this cleanly requires changes to the get-reply-directives preload
flow and is out of scope for this PR.
2026-04-21 03:35:16 +01:00
Kevin O'Neill
f2abe28d40 fix(model-selection): clear auto-failover overrides so primary is retried on each turn
When runWithModelFallback falls back to a secondary provider it writes
providerOverride/modelOverride/modelOverrideSource:"auto" to the session.
On subsequent turns createModelSelectionState read this stored override and
passed the fallback provider directly to runWithModelFallback, so the
configured primary was never retried — the session was permanently pinned to
the fallback even after the primary recovered.

Fix: at model-selection ingress, when the direct session override has
modelOverrideSource "auto" (set by a previous automatic fallback, not a user
/model command), clear the override and retry the configured primary. If the
primary is still down runWithModelFallback will fall back and re-set the auto
override for that turn. Once the primary recovers the override stays clear.

User-selected overrides (modelOverrideSource "user" or legacy undefined+model)
are preserved unchanged.

Covered by four new unit tests in model-selection.test.ts:
- auto-failover override cleared and primary retried
- user-selected override preserved
- legacy override without source field preserved
- parent-session auto-override applied to child (not cleared by child logic)
2026-04-21 03:35:16 +01:00
Peter Steinberger
47563305a2 Tests: isolate full-suite state leaks 2026-04-07 14:39:28 +01:00
Peter Steinberger
87e0353b06 test(auto-reply): trim reply utility harnesses 2026-04-07 12:35:08 +01:00
Peter Steinberger
14cfcdba1a docs(test): refresh stale model refs 2026-04-04 08:05:49 +01:00
Peter Steinberger
32ebaa3757 refactor: share session model resolution helpers 2026-04-03 19:37:56 +09:00
Gustavo Madeira Santana
bea53d7a3f Fix: move bootstrap session grammar into plugin-owned session-key surfaces (#58400)
Merged via squash.

Prepared head SHA: b062b18b03
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
2026-03-31 19:41:01 -04:00
Neerav Makwana
68d854cb9c fix: use provider-aware context window lookup (#54796) (thanks @neeravmakwana)
* fix(status): use provider-aware context window lookup

* test(status): cover provider-aware context lookup

* fix: use provider-aware context window lookup (#54796) (thanks @neeravmakwana)

---------

Co-authored-by: Ayaan Zaidi <hi@obviy.us>
2026-03-26 09:28:20 +05:30
Peter Steinberger
2833b27f52 test: continue vitest threads migration 2026-03-24 08:37:00 +00:00
Vincent Koc
c96a12aeb9 Agents: add per-agent defaults and safe model fallback (#51974)
* Agents: add per-agent defaults and safe model fallback

* Docs: add per-agent thinking/reasoning/fast defaults to config reference and thinking docs

* Format get-reply directives

* Auto-reply: guard agent reasoning defaults

* Docs: update config baseline
2026-03-21 22:27:24 -07:00
Vincent Koc
805aaa4ee8 fix(agents): avoid model catalog startup tax on telegram replies 2026-03-21 15:03:55 -07:00
Jaaneek
916f496b51 Add Grok 4.20 reasoning and non-reasoning to xAI model catalog (#50772)
Merged via squash.

Prepared head SHA: 095e645ea5
Co-authored-by: Jaaneek <25470423+Jaaneek@users.noreply.github.com>
Co-authored-by: huntharo <5617868+huntharo@users.noreply.github.com>
Reviewed-by: @huntharo
2026-03-20 15:28:30 -04:00
Peter Steinberger
c64f6adc83 refactor: finish provider auth extraction and canonicalize kimi 2026-03-16 20:49:38 -07:00
Peter Steinberger
9617ac9dd5 refactor: dedupe agent and reply runtimes 2026-03-02 19:57:33 +00:00
zwffff
c543994e90 Default reasoning to on when model has reasoning: true (fix #22456) (#22513)
* Default reasoning to on when model has reasoning: true (fix #22456)

What: When a model is configured with reasoning: true in openclaw.json (e.g. OpenRouter x-ai/grok-4.1-fast), the session now defaults reasoningLevel to on if the user has not set it via /reasoning or session store.

Why: Users expected setting reasoning: true on the model to enable reasoning; previously only session/directive reasoningLevel was used and it always defaulted to off, so Think stayed off despite the model config.

* Chore: sync formatted files from main for CI

* Changelog: note zwffff/main OpenRouter fix

* Changelog: fix OpenRouter entry text

* Update msteams.md

* Update msteams.md

* Update msteams.md

---------

Co-authored-by: 曾文锋0668000834 <zeng.wenfeng@xydigit.com>
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
2026-02-22 12:19:36 -05:00
Peter Steinberger
f717a13039 refactor(agent): dedupe harness and command workflows 2026-02-16 14:59:30 +00:00
Peter Steinberger
51709c63fe perf(test): consolidate model selection suites 2026-02-15 23:14:42 +00:00