Commit graph

6 commits

Author SHA1 Message Date
teknium1
b800e63137 fix: clean up API server — remove dead code, deduplicate model resolution, cache streaming config, add setup integration and security docs
- Remove unused _write_sse_chat_completion pseudo-streaming method (dead code)
- Extract _resolve_model() helper in gateway/run.py, use from api_server
- Cache streaming config at GatewayRunner init instead of YAML parsing per-message
- Add API_SERVER_* env vars to OPTIONAL_ENV_VARS for hermes setup integration
- Add security warning about network exposure without API_SERVER_KEY
2026-03-11 09:01:17 -07:00
teknium1
95d221c31c feat: add streaming LLM response support across all platforms
Cherry-picked from PR #828, resolved conflicts with main.
2026-03-11 08:56:37 -07:00
teknium1
b3c798d1b6 feat: add pseudo-streaming SSE + conversation parameter
Cherry-picked from PR #828.
2026-03-11 08:54:07 -07:00
teknium1
7ae208bfee feat: add conversation parameter + named session chaining
Cherry-picked from PR #828.
2026-03-11 08:54:00 -07:00
teknium1
7d771c2b1b feat: enhance Responses API — retrieval, deletion, tool calls, usage, CORS
Cherry-picked from PR #828.
2026-03-11 08:53:54 -07:00
teknium1
58dc5c4af1 feat: add OpenAI-compatible API server platform adapter (Phase 1)
Cherry-picked from PR #828, rebased onto current main with conflict resolution.
2026-03-11 08:53:47 -07:00