9 Commits

Author SHA1 Message Date
Peter Steinberger
a8907d80dd
feat: finish xai provider integration 2026-03-17 21:31:20 -07:00
Peter Steinberger
8e2a1d0941
feat(plugins): move bundled providers behind plugin hooks 2026-03-15 16:57:24 -07:00
Peter Steinberger
d5b3f2ed71
fix(models): keep codex spark codex-only 2026-03-13 00:53:21 +00:00
Peter Steinberger
5d22bd0297 fix: add google flash-lite forward compat 2026-03-08 05:22:38 +00:00
Peter Steinberger
59102a1ff7 fix: add gemini 3.1 flash-lite support 2026-03-08 05:12:48 +00:00
dorukardahan
5d4b04040d
feat(openai): add gpt-5.4 support for API and Codex OAuth (#36590)
* feat(openai): add gpt-5.4 support and priority processing

* feat(openai-codex): add gpt-5.4 oauth support

* fix(openai): preserve provider overrides in gpt-5.4 fallback

* fix(openai-codex): keep xhigh for gpt-5.4 default

* fix(models): preserve configured overrides in list output

* fix(models): close gpt-5.4 integration gaps

* fix(openai): scope service tier to public api

* fix(openai): complete prep followups for gpt-5.4 support (#36590) (thanks @dorukardahan)

---------

Co-authored-by: Tyler Yust <TYTYYUST@YAHOO.COM>
2026-03-05 21:01:37 -08:00
Byungsker
17578d77e1
fix(agents): add forward-compat fallback for google-gemini-cli gemini-3.1-pro/flash-preview (#26570)
* fix(agents): add "google" provider to isReasoningTagProvider to prevent reasoning leak

The gemini-api-key auth flow creates a profile with provider "google"
(e.g. google/gemini-3-pro-preview), but isReasoningTagProvider only
matched "google-gemini-cli" (OAuth) and "google-generative-ai". As a
result:
- reasoningTagHint was false → system prompt omitted <think>/<final>
  formatting instructions
- enforceFinalTag was false → <final> tag filtering was skipped

Raw <think> reasoning output was delivered to the end user.

Fix: add the bare "google" provider string to the match list and cover
it with two new test cases (exact match + case-insensitive).

Fixes #26551

* fix(agents): add forward-compat fallback for google-gemini-cli gemini-3.1-pro/flash-preview

gemini-3.1-pro-preview and gemini-3.1-flash-preview are not yet present in
pi-ai's built-in google-gemini-cli model catalog (only gemini-3-pro-preview
and gemini-3-flash-preview are registered). When users configure these models
they get "Unknown model" errors even though Gemini CLI OAuth supports them.

The codebase already has isGemini31Model() in extra-params.ts, which proves
intent to support these models. Add a resolveGoogleGeminiCli31ForwardCompatModel
entry to resolveForwardCompatModel following the same clone-template pattern
used for zai/glm-5 and anthropic 4.6 models.

- gemini-3.1-pro-* clones gemini-3-pro-preview (with reasoning: true)
- gemini-3.1-flash-* clones gemini-3-flash-preview (with reasoning: true)

Also add test helpers and three test cases to model.forward-compat.test.ts.

Fixes #26524

* Changelog: credit Google Gemini provider fallback fixes

---------

Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
2026-02-26 18:39:13 -05:00
Peter Steinberger
3c75bc0e41 refactor(test): dedupe agent and discord test fixtures 2026-02-22 20:04:51 +00:00
Peter Steinberger
713e2928b2 test: move duplicate local scenario suites out of agents e2e 2026-02-22 10:56:58 +00:00