Commit graph

2 commits

Author SHA1 Message Date
ozymandiashh
17eada2aa1
fix: DeepSeek v4 Claude pricing through stale runtime cache (#367)
Some checks are pending
CI / semgrep (push) Waiting to run
2026-05-21 00:34:53 -07:00
AgentSeal
d043795855 Add Qwen provider and replace hardcoded pricing with LiteLLM snapshot
- Add Qwen CLI provider (discovers sessions from ~/.qwen/projects/)
- Replace FALLBACK_PRICING (40 hand-maintained entries) with auto-generated
  LiteLLM snapshot (3595 models including Azure, OpenRouter pricing)
- Build script fetches and bundles LiteLLM data before tsup
- Provider-prefixed lookups (azure/, openrouter/) resolve to correct pricing
- Add display names for all GPT-5.x model variants
- Add Qwen to menubar provider filter and tab strip
2026-04-28 19:49:14 +02:00