2 Commits

Author	SHA1	Message	Date
Michal	9481d394a1	feat: completions update, create promptrequest, LLM flag rename, ACP content fix ... - Add prompts/promptrequests to shell completions (fish + bash) - Add approve, setup, prompt, promptrequest commands to completions - Add `create promptrequest` CLI command (POST /projects/:name/promptrequests) - Rename --proxy-mode-llm-provider/model to --llm-provider/model - Fix ACP client: handle single-object content format from real Gemini - Add tests for single-object content and agent_thought_chunk filtering Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-02-25 00:21:31 +00:00
Michal	11da8b1fbf	feat: persistent Gemini ACP provider + status spinner ... Replace per-call gemini CLI spawning (~10s cold start each time) with persistent ACP (Agent Client Protocol) subprocess. First call absorbs the cold start, subsequent calls are near-instant over JSON-RPC stdio. - Add AcpClient: manages persistent gemini --experimental-acp subprocess with lazy init, auto-restart on crash/timeout, NDJSON framing - Add GeminiAcpProvider: LlmProvider wrapper with serial queue for concurrent calls, same interface as GeminiCliProvider - Add dispose() to LlmProvider interface + disposeAll() to registry - Wire provider disposal into mcplocal shutdown handler - Add status command spinner with progressive output and color-coded LLM health check results (green checkmark/red cross) - 25 new tests (17 ACP client + 8 provider) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-02-24 23:52:04 +00:00