Custom providers using `api: "google-generative-ai"` (e.g. a paid
Google tier) resolved in the model picker but failed at runtime with
HTTP 404 because the base URL lacked the required `/v1beta` path
segment and provider normalization was gated on the provider key
being exactly `"google"`.
Two targeted fixes, both keyed on the semantic `api` field rather
than provider name strings:
1. `models-config.providers.ts` — change the normalization gate from
`normalizedKey === "google"` to
`normalizedProvider?.api === "google-generative-ai"` and add
`normalizeGoogleBaseUrl()` to ensure the canonical `/v1beta` suffix.
2. `pi-embedded-runner/model.ts` — apply
`normalizeGoogleGenerativeAiBaseUrl()` in three resolution paths
(`applyConfiguredProviderOverrides`, `buildInlineProviderModels`,
fallback model construction) so the base URL is corrected at
runtime regardless of how the model was discovered.
No changes to name-only call sites (`model-selection`,
`live-model-filter`, `model-forward-compat`); those paths are not
required for custom provider resolution and broadening their provider
checks would incorrectly capture unrelated providers like
`google-antigravity`.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: fetch OpenRouter model capabilities at runtime for unknown models
When an OpenRouter model is not in the built-in static snapshot from
pi-ai, the fallback hardcodes input: ["text"], silently dropping images.
Query the OpenRouter API at runtime to detect actual capabilities
(image support, reasoning, context window) for models not in the
built-in list. Results are cached in memory for 1 hour. On API
failure/timeout, falls back to text-only (no regression).
* feat(openrouter): add disk cache for OpenRouter model capabilities
Persist the OpenRouter model catalog to ~/.openclaw/cache/openrouter-models.json
so it survives process restarts. Cache lookup order:
1. In-memory Map (instant)
2. On-disk JSON file (avoids network on restart)
3. OpenRouter API fetch (populates both layers)
Also triggers a background refresh when a model is not found in the cache,
in case it was newly added to OpenRouter.
* refactor(openrouter): remove pre-warm, use pure lazy-load with disk cache
- Remove eager ensureOpenRouterModelCache() from run.ts
- Remove TTL — model capabilities are stable, no periodic re-fetching
- Cache lookup: in-memory → disk → API fetch (only when needed)
- API is only called when no cache exists or a model is not found
- Disk cache persists across gateway restarts
* fix(openrouter): address review feedback
- Fix timer leak: move clearTimeout to finally block
- Fix modality check: only check input side of "->" separator to avoid
matching image-generation models (text->image)
- Use resolveStateDir() instead of hardcoded homedir()/.openclaw
- Separate cache dir and filename constants
- Add utf-8 encoding to writeFileSync for consistency
- Add data validation when reading disk cache
* ci: retrigger checks
* fix: preload unknown OpenRouter model capabilities before resolve
* fix: accept top-level OpenRouter max token metadata
* fix: update changelog for OpenRouter runtime capability lookup (#45824) (thanks @DJjjjhao)
* fix: avoid redundant OpenRouter refetches and preserve suppression guards
---------
Co-authored-by: Ayaan Zaidi <hi@obviy.us>
