Commit Graph

7 Commits

Author SHA1 Message Date
mushuiyu886
42e6972d35 fix(opencode): Zen GPT-5.6 models are missing from discovery (#110405)
* fix(opencode): add Zen GPT-5.6 models

* test(opencode): narrow GPT-5.6 policy fixture

* fix(opencode): align GPT-5.6 thinking levels

Co-authored-by: 杨浩宇0668001029 <yang.haoyu@xydigit.com>

---------

Co-authored-by: Peter Steinberger <steipete@gmail.com>
2026-07-18 11:14:05 +01:00
Peter Steinberger
4fa5092cdc docs: document small extension sources 2026-06-04 21:02:07 -04:00
Shakker
63e7776351 test: tighten opencode thinking profile assertions 2026-05-11 07:24:08 +01:00
Shakker
84c4a4fc5b test: tighten provider empty array assertions 2026-05-09 04:55:18 +01:00
Peter Steinberger
f4d5f9985b test: simplify provider thinking level scans 2026-05-08 23:09:23 +01:00
Peter Steinberger
6a20bbd166 test: clarify provider thinking level assertions 2026-05-08 08:21:47 +01:00
MkDev11
38eea33062 fix(opencode): expose Claude thinking policy (#76760)
Summary:
- Adds an OpenCode provider-policy public artifact that delegates Claude thinking profiles, plus regression tests and a changelog entry for preserving `xhigh` on `opencode/claude-opus-4-7`.
- Reproducibility: yes. Source inspection on current main shows the model-switch path remaps unsupported store ... vider-policy-api` artifact for the fallback resolver; the proposed test exercises that stored-`xhigh` path.

Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.

Validation:
- ClawSweeper review passed for head efa152cca5.
- Required merge gates passed before the squash merge.

Prepared head SHA: efa152cca5
Review: https://github.com/openclaw/openclaw/pull/76760#issuecomment-4366483080

Co-authored-by: mkdev11 <MkDev11@users.noreply.github.com>
2026-05-03 15:22:07 +00:00