apunkt/webclaw
1
0
Fork 0
mirror of https://github.com/0xMassi/webclaw.git synced 2026-07-22 07:11:01 +02:00
Code Issues Projects Releases Packages Wiki Activity

feat(llm): add Gemini CLI provider as primary; set qwen3.5:9b as default Ollama model

Browse source 
- Add GeminiCliProvider: shells out to `gemini -p` with --output-format json,
  injection-safe prompt passing, MCP server suppression via temp workdir,
  6-slot concurrency semaphore, 60s subprocess deadline
- Add --llm-provider, --llm-model, --llm-base-url CLI flags for per-call overrides
- Provider chain: Gemini CLI → OpenAI → Ollama → Anthropic
- Move LLM timing to dispatch layer (LLM: Xs on stderr)
- Default Ollama model: qwen3:8b → qwen3.5:9b (benchmark shows better schema extraction)
- Add noxa mcp subcommand
- Add docs/reports/llm-benchmark-2026-04-11.md (Gemini vs qwen3.5:4b vs qwen3.5:9b)
- Bump version 0.3.11 → 0.4.0

Co-authored-by: Claude <claude@anthropic.com>
This commit is contained in:
Jacob Magar 2026-04-12 00:52:53 -04:00
parent 464eb1baec
commit adf4b6ba55
39 changed files with 1999 additions and 1789 deletions
Download patch file Download diff file Expand all files Collapse all files

2
CLAUDE.md
View file

@ -50,7 +50,7 @@ Two binaries: `noxa` (CLI), `noxa-mcp` (MCP server).
### LLM Modules (`noxa-llm`)
- Provider chain: Gemini CLI (primary) -> OpenAI -> Ollama -> Anthropic
- Gemini CLI requires the `gemini` binary on PATH; `GEMINI_MODEL` env var controls model (default: `gemini-2.5-pro`)
- JSON schema extraction with jsonschema validation; parse failures retry once; schema mismatches fail immediately
- JSON schema extraction with jsonschema validation; retries once with a correction prompt on both parse failures and schema mismatches.
- Prompt-based extraction, summarization
### PDF Modules (`noxa-pdf`)