Compare commits

...

2 Commits

Author SHA1 Message Date
ZhenYi
ecf9f33b26 refactor(agent/sync): remove OpenRouter dependency, use upstream /v1/models directly
Some checks are pending
CI / Rust Lint & Check (push) Waiting to run
CI / Rust Tests (push) Waiting to run
CI / Frontend Lint & Type Check (push) Waiting to run
CI / Frontend Build (push) Blocked by required conditions
The upstream AI endpoint already returns complete model metadata:
- name, owned_by, context_length, max_output_tokens
- capabilities (vision, tool_call, reasoning)
- pricing (input, output, cache_read, cache_write, currency)

Remove the OpenRouter fallback entirely and parse the upstream
response directly for all sync operations. Both sync_upstream_models
(API) and sync_once (background task) now use a single unified path.

Changes:
- Remove OpenRouter types and fetch_openrouter_models()
- Add UpstreamModel / UpstreamCapabilities / UpstreamPricing types
- Parse capabilities from upstream instead of inferring from name
- Use real pricing from upstream instead of defaulting to 0.00
- Simplify sync flow: list → parse → upsert (no filtering/matching)
- Add provider normalizations for moonshot, zai, minimax, qwen
2026-04-26 16:30:41 +08:00
ZhenYi
a8e3b0f5a8 fix(agent/sync): handle multiple /v1/models response formats
The upstream AI endpoint returns an OpenAI-compatible format, but the
response body parsing was fragile. Make it resilient:
1. Try standard OpenAI format: { "data": [{id}, ...] }
2. Try raw array: [{id}, ...]
3. Try alternate format: { "models": [{id}, ...] }
4. Log actual response body (first 500 chars) when all formats fail

Also adds a warning log with the raw response on parse failure so
future debugging is straightforward.
2026-04-26 16:26:57 +08:00

File diff suppressed because it is too large Load Diff