Commit graph

16 commits

Author SHA1 Message Date
Vegard Stikbakke
7c22a93d0e
feat(ai): add totalFromProvider flag to usage cost (#11178)
Add Usage.cost.totalFromProvider to record whether cost.total is the
billed cost reported by the provider or an estimate from catalog rates.
Catalog-derived totals set it to false; a missing value also means
false. combineUsage marks a sum as provider-reported only when both
parts are.
2026-10-22 09:02:01 +02:00
David Brailovsky
ee409a85f6
feat(ai,coding-agent): list only the OpenRouter models a key may use (#10672)
On each OpenRouter refresh, combine the catalog (built-in models plus a newer pi.dev catalog) with GET /models/user for the user's key: keep only the listed chat models and take their context size, max output and prices from it. Image and classifier models are kept. The combined list is saved and replaces the OpenRouter catalog, including offline.

- ai: add personalizeOpenRouterCatalog and RefreshModelsContext.baseUrl, so the request follows a base URL configured in models.json (regional endpoints)
- ai: share OpenRouter price conversion with the generator; negative prices (router models such as openrouter/auto) become 0
- coding-agent: add withPersonalizedCatalog next to withRemoteCatalog
- docs: OpenRouter section in providers.md

fixes #10353
2026-10-12 10:17:40 +02:00
Armin Ronacher
bde882c747 fix(ai,coding-agent): persist rotated OAuth tokens when a refresh is cancelled
Cancelling a request or model refresh while an OAuth token refresh was in
flight discarded the rotated credential. Providers that rotate refresh tokens
(e.g. Sign in with ChatGPT) had already invalidated the old token, so the next
request failed with refresh_token_invalidated.

The caller's signal now cancels only the wait for the credential lock. Once a
refresh starts, it completes and is persisted, bounded by the refresh timeout.
Request auth and model-list refresh share this path.
2026-10-04 21:48:12 +02:00
Armin Ronacher
a328aa89ad
feat(ai,coding-agent): unify image and classifier model infrastructure (#9948) 2026-09-23 17:41:19 +02:00
Vegard Stikbakke
d3da2e968a fix(ai): test composite OAuth refresh cancellation 2026-08-04 13:01:11 +02:00
Mario Zechner
fed6009cc9 fix(coding-agent): make model refresh cancellation caller-owned
Add generation-safe catalog publication, cancellable auth and storage operations, locally consistent credential mutations, and cache-first interactive model flows.
2026-08-04 00:03:52 +02:00
Cristina Poncela Cubeiro
99e34013d1
feat: auth print (#7168)
Some checks are pending
CI / build-check-test (push) Waiting to run
2026-07-27 16:13:06 +02:00
Armin Ronacher
4cf0a729c4 fix(ai): keep the underlying cause in ModelsError messages
Auth failures surfaced only the wrapper text, so CI logs showed a bare
"OAuth refresh failed for openai-codex" with no provider response.
2026-07-25 12:41:15 +02:00
Armin Ronacher
97f9978fa6 feat(coding-agent): add model catalog refresh flag 2026-07-16 12:46:49 +02:00
Mario Zechner
cd7cad4ee2 feat(coding-agent): merge origin/main into model runtime facade 2026-07-15 12:25:36 +02:00
Mario Zechner
9993c96907 feat(coding-agent): replace model registry with model runtime
Move provider auth and OAuth flows onto pi-ai Models, compose models.json and extension overlays through ModelRuntime, and retain ModelRegistry as an extension compatibility facade.
2026-07-14 17:48:45 +02:00
Armin Ronacher
a9ecf301fb feat(ai): add input-based pricing tiers 2026-07-09 22:44:29 +02:00
Mario Zechner
ef231c4910 fix(ai): resolve request-scoped auth before provider calls
closes #6021
2026-06-23 23:27:00 +02:00
Mario Zechner
49fbe6834f fix(ai): align api key credentials with auth json 2026-06-23 22:29:46 +02:00
Mario Zechner
6e98573f24 feat(ai): sync model reads, explicit async refresh
Provider.getModels() is sync-only (last-known list; must not throw) with
an optional refreshModels() where dynamic providers fetch. The
sync-or-async union invited latent sync assumptions that would detonate
on the first dynamic provider; async-only reads would force sync
consumer surfaces (extension find/getAll) through Promises. Sync reads
plus an explicit refresh verb keeps the contract single and the
staleness visible.

Models.getModels()/getModel() are sync best-effort reads;
Models.refresh(provider?) rejects with ModelsError(model_source) for a
single provider and is concurrent best-effort across all providers.
createProvider() takes a models array plus an optional refreshModels
fetcher (stored on success, in-flight calls deduped, list unchanged on
rejection). forceRefresh options are gone.

Also finishes the in-progress AuthStorage fallbackResolver removal
(drops the now-unused includeFallback option from getApiKey).
2026-06-10 23:30:04 +02:00
Mario Zechner
f63095cfff feat(ai): add Models runtime with provider-owned auth (phase 1)
New Models/MutableModels/createModels collection: provider map, async
model listing (best-effort aggregation), getAuth decision tree with
double-checked locked OAuth refresh, stream/complete with per-field
auth merge over lazyStream.

Auth substrate: ProviderAuth { apiKey?, oauth? }, one type-tagged
credential per provider, CredentialStore (read/modify/delete; modify
is the only write path, serialized RMW), OAuthAuth login/refresh/toAuth
split, prompt()/notify() login callbacks, browser-safe default
AuthContext.

types.ts: Provider alias renamed to ProviderId; ApiOptionsMap and
ApiStreamOptions<TApi> for typed per-API stream options; hasApi()
runtime narrowing guard.
2026-06-10 18:49:10 +02:00