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>

internal/ai/llm/ollama/testdata/README.md

@@ -0,0 +1,36 @@
+# Ollama adapter fixtures
+
+These are the native Ollama API response bodies the contract tests in
+`ollama_test.go` replay. They are **not live captures**. Product AI is tested
+with fakes and live vendor calls are opt-in, so no request was sent to an
+Ollama server to make them. Each fixture is a sanitized adaptation of the
+response shapes in Ollama's public API documentation
+(<https://github.com/ollama/ollama/blob/main/docs/api.md>):
+
+- Chat, non-streaming: `POST /api/chat` with `"stream": false`.
+- Structured outputs: `POST /api/chat` with a JSON schema in `"format"`.
+- List local models: `GET /api/tags`.
+- Errors: a JSON `{"error": "..."}` body with a non-2xx status; a model
+  that is not pulled is HTTP 404.
+
+Sanitizing:
+
+- Timestamps, durations, sizes, digests and token counts are illustrative
+  values in the documented format, not values from a real server.
+- Message content is replaced with MealQuest dinner text.
+- Ollama takes no credentials, so none appear.
+
+Below, *not in the public example* marks values that were added for a test
+case and do not come from the documented example.
+
+| Fixture | Case | Shape | Not in the public example |
+| --- | --- | --- | --- |
+| `chat_text.json` | Success | Finished chat message, `done_reason: stop`, `prompt_eval_count` and `eval_count`. | — |
+| `chat_schema.json` | Schema output | Finished chat message whose content is a JSON object string. | The dinner object. |
+| `error_model_not_found.json` | Model missing | `{"error": "model \"…\" not found, try pulling it first"}`, served with HTTP 404. | — |
+| `tags.json` | Model list | `{"models": [...]}` with `name`, `model`, `digest` and `details`. | — |
+
+The unreachable-host case has no fixture: there is no response to record.
+The tests close an `httptest` server and dial its address, so the
+connection is refused, and they hold a reply past a short deadline for the
+timeout.

internal/ai/llm/ollama/testdata/chat_schema.json

@@ -0,0 +1,16 @@
+{
+  "model": "llama3.2",
+  "created_at": "2026-10-04T12:20:11.009132Z",
+  "message": {
+    "role": "assistant",
+    "content": "{\"dinners\": [{\"name\": \"Sheet-pan gnocchi\", \"why\": \"Like your Regular tray bake, but quicker.\"}]}"
+  },
+  "done_reason": "stop",
+  "done": true,
+  "total_duration": 1416823291,
+  "load_duration": 12309083,
+  "prompt_eval_count": 147,
+  "prompt_eval_duration": 271802000,
+  "eval_count": 41,
+  "eval_duration": 1130948000
+}

internal/ai/llm/ollama/testdata/chat_text.json

@@ -0,0 +1,16 @@
+{
+  "model": "llama3.2",
+  "created_at": "2026-10-04T12:13:43.416799Z",
+  "message": {
+    "role": "assistant",
+    "content": "Try a crock pot chili: it is a Quick dinner."
+  },
+  "done": true,
+  "done_reason": "stop",
+  "total_duration": 5191566416,
+  "load_duration": 2154458,
+  "prompt_eval_count": 26,
+  "prompt_eval_duration": 383809000,
+  "eval_count": 298,
+  "eval_duration": 4799921000
+}

internal/ai/llm/ollama/testdata/error_model_not_found.json

@@ -0,0 +1 @@
+{"error":"model \"llama9\" not found, try pulling it first"}

internal/ai/llm/ollama/testdata/tags.json

@@ -0,0 +1,34 @@
+{
+  "models": [
+    {
+      "name": "llama3.2:latest",
+      "model": "llama3.2:latest",
+      "modified_at": "2026-09-30T08:06:48.639712648-07:00",
+      "size": 2019393189,
+      "digest": "a80c4f17acd55265feec403c7aef86be0c25983ab279d83f3bcd3abbcb5b8b72",
+      "details": {
+        "parent_model": "",
+        "format": "gguf",
+        "family": "llama",
+        "families": ["llama"],
+        "parameter_size": "3.2B",
+        "quantization_level": "Q4_K_M"
+      }
+    },
+    {
+      "name": "qwen3:8b",
+      "model": "qwen3:8b",
+      "modified_at": "2026-09-28T19:41:02.112408113-07:00",
+      "size": 5225388164,
+      "digest": "500a1f067a9f782620b40bee6f7b0c89e17ae61f686b92c24933e4ca4b2b8b41",
+      "details": {
+        "parent_model": "",
+        "format": "gguf",
+        "family": "qwen3",
+        "families": ["qwen3"],
+        "parameter_size": "8.2B",
+        "quantization_level": "Q4_K_M"
+      }
+    }
+  ]
+}