feat(api): route elaboration through local LLM when configured

Phase 2 of "local OSS models as agents" plan. Adds a third elaboration
path that calls the local OpenAI-compatible LLM via the internal/llm
client, and reorders dispatch so the cheap path is tried first:
local → claude → gemini, with each next attempt only on hard failure
of the prior.

Wiring is opt-out, not opt-in: when [local_model].endpoint is set,
elaboration prefers local by default. Users with a slow or low-quality
local model can disable just elaboration via:

    [local_model]
    endpoint = "..."
    prefer_for_elaborate = false

without giving up the runner or the classifier path.

Implementation:
- Server gains an optional *llm.Client field via SetLLM (matches the
  existing SetNotifier/SetWorkspaceRoot setter pattern, no NewServer
  signature break).
- elaborateWithLocal() reuses buildElaboratePrompt verbatim and asks
  for response_format=json_object so we skip markdown-fence cleanup.
- handleElaborateTask reorders try chain; existing Claude-first
  behavior is preserved exactly when SetLLM is not called.
- LocalModel.UseForElaborate() encapsulates the default-true gating
  with a *bool so explicit-false survives TOML parse.

Tests:
- elaborateWithLocal: parses valid response, errors on nil client,
  errors on bad JSON.
- handler: local preferred when wired; falls back to claude when
  local fails; unchanged behavior when no LLM is configured.
- config: UseForElaborate gating across empty/default/explicit-true/
  explicit-false cases.

Pre-existing test failures noted in docs/plans/local-oss-runner.md
(post-epic cleanup): TestGeminiLogs_ParsedCorrectly returns 404 for
gemini execution log fetch — predates this change.

Plan: docs/plans/local-oss-runner.md.

https://claude.ai/code/session_017Edeq947TpSm1vQTxMhi1J

1 files changed, 25 insertions, 8 deletions

diff --git a/internal/config/config.go b/internal/config/config.go
index 7f87391..5801239 100644
--- a/internal/config/config.go
+++ b/internal/config/config.go
@@ -16,15 +16,32 @@ type Project struct {
 }
 
 // LocalModel configures an OpenAI-compatible local LLM endpoint used for
-// internal helpers (classifier, future elaboration/summarization) and as the
-// backend for the "local" runner. If Endpoint is empty, the LocalRunner is
-// not registered and the classifier falls back to the Gemini CLI.
+// internal helpers (classifier, elaboration, future summarization) and as
+// the backend for the "local" runner. If Endpoint is empty, the LocalRunner
+// is not registered and the classifier falls back to the Gemini CLI.
+//
+// PreferForElaborate gates whether the API server's elaboration handler
+// uses this client. It defaults to true when Endpoint is set; users with a
+// slow or low-quality local model can disable it.
 type LocalModel struct {
-	Endpoint           string  `toml:"endpoint"`             // e.g. "http://localhost:11434/v1"
-	Model              string  `toml:"model"`                // e.g. "llama3.1:8b"
-	TimeoutSeconds     int     `toml:"timeout_seconds"`      // default 60
-	DefaultTemperature float64 `toml:"default_temperature"`  // default 0.2
-	APIKey             string  `toml:"api_key"`              // optional bearer token
+	Endpoint           string  `toml:"endpoint"`              // e.g. "http://localhost:11434/v1"
+	Model              string  `toml:"model"`                 // e.g. "llama3.1:8b"
+	TimeoutSeconds     int     `toml:"timeout_seconds"`       // default 60
+	DefaultTemperature float64 `toml:"default_temperature"`   // default 0.2
+	APIKey             string  `toml:"api_key"`               // optional bearer token
+	PreferForElaborate *bool   `toml:"prefer_for_elaborate"`  // pointer so default-true survives parse
+}
+
+// UseForElaborate returns true when elaboration should try this local model
+// before falling back to Claude/Gemini. Default is true when Endpoint is set.
+func (m LocalModel) UseForElaborate() bool {
+	if m.Endpoint == "" {
+		return false
+	}
+	if m.PreferForElaborate == nil {
+		return true
+	}
+	return *m.PreferForElaborate
 }
 
 type Config struct {