* 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>
Ollama's OpenAI-compatible endpoint handles reasoning natively via the
`reasoning` field in streaming chunks. Treating Ollama as a
reasoning-tag provider incorrectly forces <think>/<final> tag
enforcement, which causes stripBlockTags() to discard all output
(since Ollama models don't emit <final> tags), resulting in
'(no output)' for every Ollama model.
This fix removes 'ollama' from the isReasoningTagProvider() check,
allowing Ollama models to work correctly through the standard
content/reasoning field separation.
- Enforces strict buffering when enforceFinalTag is enabled.
- Prevents 'thinking out loud' planning steps (e.g. '*Locating Manulife*') from leaking to WhatsApp.
- Hardens <final> tag stripping to remove nested/hallucinated tags.
- Added src/utils/provider-utils.ts to track reasoning provider logic
- Updated isReasoningTagProvider to loosely match 'google-antigravity' (fixes sub-models)
- Enabled enforceFinalTag in reply.ts when provider matches
- Verified <final> tag stripping logic in pi-embedded-subscribe.ts
- Updated pi-embedded-runner to use consistent provider check for prompt hints
