-
-
Notifications
You must be signed in to change notification settings - Fork 0
Provider Ollama
Talks to a locally-running Ollama instance.
Note
No API key, no per-token cost — but you supply the GPU/CPU time.
provider: ollama
providers:
ollama:
base_url: http://localhost:11434
model: qwen2.5-coder:14bEquivalent CLI / env:
commitbrief config set provider ollama
commitbrief config set providers.ollama.base_url http://localhost:11434
commitbrief config set providers.ollama.model qwen2.5-coder:14b
# Or via env (sets base_url only — model still needs config/wizard):
export OLLAMA_HOST=http://localhost:11434- Ollama installed and running.
- At least one model pulled —
ollama pull qwen2.5-coder:14betc. - The configured
base_urlreachable from the machine runningcommitbrief. The defaulthttp://localhost:11434works for a local Ollama install.
The setup wizard queries <base_url>/api/tags to list models you
have pulled, then offers them as a pick-list. If discovery fails
(Ollama not running, wrong URL, network issue), the wizard falls
back to a free-text input — you can type any model identifier and
it is stored verbatim.
provider.Pricing{} — all zero. The cost preflight
short-circuits and the verbose footer shows — instead of a
dollar figure. The token counts are still reported.
Reported by the Ollama API per model. Defaults vary by model — a 14B-parameter model typically declares 32k–128k depending on configuration.
Ollama supports OpenAI-compatible JSON mode for many models;
CommitBrief uses the standard chat-completion endpoint with a
prompt-side JSON contract. Reliability depends on the model — a
small instruct model may produce malformed JSON more often than
the API providers, in which case the recovery ladder kicks in
(ADR-0031): valid JSON wrapped in ```json fences is salvaged
with no retry, a genuine parse failure triggers one repair-oriented
retry, and only a second failure degrades (a warning: LLM produced malformed JSON; falling back to plain-text view. on stderr).
- Providers — overview.
- Configuration files — full YAML schema.
Home · Installation · Quick start · Troubleshooting · GitHub repo · Issues
CommitBrief — local, LLM-powered code review for git diffs. This wiki documents only what ships in the binary.
Getting started
Commands · reviewing
Commands · summarizing
Commands · committing
Commands · setup
Commands · integration
Commands · inspect
Commands · maintenance
Configuration
Providers
Output
Operations
Reference