fix(ollama): resolve context window per model via POST /api/show (#1437)

The Ollama integration never applied a correct context window, so agents
with real prompts (20k-100k tokens) were rejected with HTTP 400
exceed_context_size_error against a 4096-token default.

Three root causes fixed:

1. FetchOllamaModelContext issued a GET to /api/show, which Ollama answers
   with 405 (the endpoint is POST-only). Now POSTs {"model": "<name>"}.

2. The response parser expected a flat model_info.context_length, but a real
   Ollama server namespaces the key by architecture (gemma4.context_length,
   qwen3.context_length, ...). extractContextLength now matches "context_length"
   or any "*.context_length" key.

3. num_ctx was resolved once at startup for a hardcoded "llama3.3" model and
   never for the model an agent actually uses. Resolution now happens per
   request for the real model inside OllamaProvider.resolveNumCtx, cached under
   an RWMutex, with an explicit settings override winning and the fetched value
   bounded by OllamaDefaultNumCtx so an enormous advertised window (Qwen3.5
   reports 262144) cannot balloon the KV cache beyond VRAM.

Also classify Ollama's "exceed_context_size" 400 as a context-overflow error so
the pipeline's emergency-compaction+retry path (Issue 958) engages gracefully
instead of surfacing a raw error.

Co-authored-by: Bruno Clermont <bruno.clermont@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

internal/providers/error_classify.go

@@ -169,6 +169,7 @@ func isContextOverflow(lower string) bool {
 		"prompt exceeds max length", // ZAI/GLM-5
 		"request_too_large",         // Generic
 		"input is too long",         // DashScope
+		"exceed_context_size",       // Ollama native /api/chat 400
 		"请求输入过长",                    // Chinese generic
 	)
 }