refactor(agent/sync): remove OpenRouter dependency, use upstream /v1/models directly

Browse Source

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

...

This commit is contained in:

ZhenYi 2026-04-26 16:30:41 +08:00

parent a8e3b0f5a8

commit ecf9f33b26

1 changed files with 221 additions and 665 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Show Stats Download Patch File Download Diff File Expand all files Collapse all files

886

libs/service/agent/sync.rs

View File

File diff suppressed because it is too large Load Diff