Ollama native adapter #41

Merged

approver_agent merged 2 commits from task/ollama-adapter_51289131-5abf-48c3-b553-7e3809c09076 into feature/5dd6e253-cc9b-41f3-9091-bb834f7a373a-llm-provider-layer 2026-10-04 08:47:05 -04:00

Conversation 2 Commits 2 Files Changed 7

+1043

2 Commits

Author	SHA1	Message	Date
dev_agentandClaude Opus 5.5	1d4c0bd0e1	Ollama: only treat a 404 as model-not-found when the body says so ... A 404 from a proxy without /api/chat, or any other 404 error, was reported as the configured model being missing. Generate now checks the {"error": ...} payload for Ollama's model-not-found message naming the configured model (double- or single-quoted); any other 404 stays a ProviderError with its redacted body excerpt. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-04 08:37:22 -04:00
dev_agentandClaude Opus 5.5	d5fe7548c5	Ollama native adapter ... internal/ai/llm/ollama implements llm.Provider over plain net/http: POST {base}/api/chat with "stream": false, the request schema in "format", and options.temperature / options.num_predict only when the request sets them; GET {base}/api/tags for ListModels and Verify. No Authorization header is sent and redirects are not followed. Usage comes from prompt_eval_count/eval_count. A schema reply that is not a JSON object is ErrBadOutput. HTTP 404 on /api/chat is an ErrProvider naming the configured model, without quoting the body. Refused connections and timeouts match ErrTimeout and say "Ollama not reachable at {base}"; a cancelled context stays context.Canceled. The base URL is required, absolute http or https (LAN hosts allowed), and may not carry userinfo, a query or a fragment. Contract tests replay sanitized fixtures adapted from Ollama's public API docs against httptest servers: success, schema output, model missing and unreachable host. Maestro task: 51289131-5abf-48c3-b553-7e3809c09076 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-04 08:30:17 -04:00