Commit graph

5 commits

Author SHA1 Message Date
nesquena-hermes
58528a4d88
Release v0.51.270 — Release IL (stage-u1 — un-hold batch: #3517 #3624 #3613) (#3674)
* feat(commands): add /use to force a skill for the next turn (#3517, #2977)

Co-authored-by: Rod Boev <rod.boev@gmail.com>

* fix(auth): cap pending passkey challenges by evicting oldest, not rejecting (#3624)

Co-authored-by: Hinotobi <paperlantern.agent@gmail.com>

* fix(providers): expose model-provider plugins in WebUI (#3613)

Co-authored-by: Pamnard <pamnard@users.noreply.github.com>

* docs(changelog): v0.51.270 — Release IL (stage-u1, 3-PR un-hold batch; #3448 + #3618 dropped)

---------

Co-authored-by: nesquena-hermes <[email protected]>
Co-authored-by: Rod Boev <rod.boev@gmail.com>
Co-authored-by: Hinotobi <paperlantern.agent@gmail.com>
Co-authored-by: Pamnard <pamnard@users.noreply.github.com>
2026-06-05 11:35:26 -07:00
Michael Lam
8ef8fae831 fix: show config-managed custom providers 2026-05-20 06:27:00 -07:00
Frank Song
f6115b78c6 Fix custom provider name slugs with ports 2026-05-11 17:24:53 +08:00
fxd-jason
26f51b7190 fix: address review feedback — restore V3 as legacy, fix zai base_url
- Restore deepseek-chat-v3-0324 and deepseek-reasoner with '(legacy)' labels;
  these are deprecated 2026-07-24 but still live until then
- Fix zai (Z.AI/GLM) default_base_url: use /api/paas/v4 instead of /api/coding/paas/v4;
  the coding plan path is for the glmcode custom provider, not the general API
- Update test assertions to match
2026-04-29 04:31:16 +00:00
fxd-jason
544d5222a1 test: add unit tests for custom_providers scanning and DeepSeek V4 models
- Test custom_providers entries (glmcode, deepseek) appear in get_providers()
- Test env var reference detection (${VAR_NAME} pattern)
- Test bare API key, missing key, empty/malformed entries
- Assert DeepSeek V4 models present, V3 deprecated models removed
- Assert GLM model series in _PROVIDER_MODELS and onboarding setup
2026-04-29 04:31:15 +00:00