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

7 files changed, 395 insertions, 19 deletions

diff --git a/docs/plans/local-oss-runner.md b/docs/plans/local-oss-runner.md
index de16e05..108495b 100644
--- a/docs/plans/local-oss-runner.md
+++ b/docs/plans/local-oss-runner.md
@@ -183,3 +183,67 @@ This is the only phase we execute in this pass. Phases 2–4 will get their own
 - Branch pushed to remote
 
 After Phase 1 lands, we stop and decide whether to begin Phase 2 (elaboration). At that point we'll write a Phase 2 focused plan in `docs/plans/local-oss-runner.md`.
+
+---
+
+# Post-epic follow-up: deep cleanup
+
+After all four phases land, plan and execute a deep cleanup pass. Things noticed in flight that we deliberately did not chase mid-epic:
+
+- **Sandbox/git tests fail in this environment** because `git commit` invokes a signing server that returns 400 ("missing source"). Affected: `TestSandboxCloneSource_*`, `TestSetupSandbox_*`, `TestTeardownSandbox_*`, `TestBlockedError_IncludesSandboxDir`, `TestClaudeRunner_Run_StaleSandboxDir_ClonesAfresh`. Fix: set `commit.gpgsign=false` in test setup so sandbox tests run hermetically.
+- **`TestParseGeminiStream_ParsesStructuredOutput` is currently `t.Skip`** as a pre-existing gemini-stub gap. Either implement result-error/cost parsing in `parseGeminiStream` or delete the test until the stub is finished.
+- **`TestPool_ActivePerAgent_DeletesZeroEntries` flakes** under `-race` when run with the full suite (passes in isolation and on `-count=3`). Likely goroutine-ordering in the `activePerAgent` map cleanup path. Audit dispatch/finish ordering.
+- **`setupSandbox` test signature drift** was just fixed; audit other tests for similar staleness from prior refactors.
+- **Pre-existing `executor` tests didn't compile on trunk** until the setupSandbox fix landed. Verify CI reality — is it green via something we're missing, or quietly broken?
+- **GeminiRunner is still simulated** (`gemini.go:107-116`). Decide: finish it (real subprocess + cost parsing + sandbox) or delete it and leave only Claude + Local.
+- **Frontend "Local" agent option** — UI dropdown still says "Auto / Claude / Gemini". Add Local once token telemetry has a place to render.
+- **Audit `*_test.go` for `t.Skip` and other dormant breakage** before shipping more code on top.
+- **`TestGeminiLogs_ParsedCorrectly`** in `internal/api` returns 404 from `GET /log` for a gemini execution — pre-existing on Phase 1 baseline. Some routing or log-path resolution mismatch specific to gemini executions. Likely related to the GeminiRunner stub status above.
+
+Goal: clean `go test -race ./...` with zero skips and zero environmental failures on whatever platform CI runs on.
+
+---
+
+# Phase 2 — Focused Plan (Elaboration)
+
+## Phase 2 scope
+
+`internal/api/elaborate.go` currently has two paths: Claude and Gemini. Add a third (local) and make it the preferred path when local model is configured. Try-order: local → claude → gemini, with each next attempt only on hard failure of the prior.
+
+Second-cheapest, second-highest-volume LLM call after classification (one per task creation, sub-second target). Routing through local removes another cost line and lets elaboration work offline.
+
+## What ships
+
+- `Server` (`internal/api/server.go`) gains `llm *llm.Client` threaded through `NewServer`
+- `internal/api/elaborate.go` gains `elaborateWithLocal(ctx, *llm.Client, input string) (string, error)`
+- Dispatch in `Server.elaborate` reorders to: local → claude → gemini, gated by `PreferLocalForElaborate`
+- `Config` gains `PreferLocalForElaborate bool`, defaulted true when `LocalModel.Endpoint != ""`
+- Wiring in `internal/cli/serve.go` passes the LLM client into `NewServer`
+
+## Explicit non-goals
+
+- No prompt rework — reuse existing elaboration prompt template verbatim
+- No streaming the response into SSE/WebSocket (one-shot RPC)
+- No changes to webhook (Phase 3) or summary (Phase 4)
+- No UI changes — `/elaborate` endpoint signature stays the same
+
+## Task list
+
+1. Read `internal/api/elaborate.go` end-to-end: dispatch site, Claude path, Gemini path, prompt template
+2. Read `internal/api/server.go` `NewServer` signature and `Server` fields
+3. Thread `llm *llm.Client` through `NewServer` and update callers (`internal/cli/serve.go`)
+4. Implement `elaborateWithLocal` using the same prompt template as Claude/Gemini, returning `(string, error)`
+5. Add `PreferLocalForElaborate bool` to `config.Config`, default true when local endpoint configured
+6. Reorder dispatch: `if s.llm != nil && cfg.PreferLocalForElaborate { try local; else fall through }` then existing claude → gemini chain
+7. httptest-based unit test for `elaborateWithLocal`
+8. Dispatch fallback test: local fails → claude attempted
+9. `go build ./... && go test -race ./...`
+10. Commit Phase 2 on the same branch
+11. Push
+
+## Stop conditions
+
+- Tests green under `-race`
+- `prefer_local_for_elaborate=false` short-circuits to Claude path (preserves current behavior when user opts out)
+- Local-failure fallback to Claude verified by test
+- Branch pushed
diff --git a/internal/api/elaborate.go b/internal/api/elaborate.go
index 0c681ae..30095c8 100644
--- a/internal/api/elaborate.go
+++ b/internal/api/elaborate.go
@@ -12,6 +12,8 @@ import (
 	"sort"
 	"strings"
 	"time"
+
+	"github.com/thepeterstone/claudomator/internal/llm"
 )
 
 const elaborateTimeout = 30 * time.Second
@@ -245,6 +247,33 @@ func (s *Server) elaborateWithClaude(ctx context.Context, workDir, fullPrompt st
 	return &result, nil
 }
 
+// elaborateWithLocal runs elaboration through an OpenAI-compatible local LLM.
+// It uses the same prompt template as the Claude/Gemini paths and requests
+// json_object response format so we can decode directly without the
+// markdown-fence cleanup needed for the CLI paths.
+func elaborateWithLocal(ctx context.Context, c *llm.Client, workDir, fullPrompt string) (*elaboratedTask, error) {
+	if c == nil {
+		return nil, fmt.Errorf("local llm: no client configured")
+	}
+	systemPrompt := buildElaboratePrompt(workDir)
+	resp, err := c.Chat(ctx, llm.ChatRequest{
+		Messages: []llm.Message{
+			{Role: "system", Content: systemPrompt},
+			{Role: "user", Content: fullPrompt},
+		},
+		ResponseJSON: true,
+	})
+	if err != nil {
+		return nil, fmt.Errorf("local llm: %w", err)
+	}
+	body := strings.TrimSpace(resp.Content)
+	var result elaboratedTask
+	if jerr := json.Unmarshal([]byte(extractJSON(body)), &result); jerr != nil {
+		return nil, fmt.Errorf("local llm: parse JSON: %w (response: %s)", jerr, body)
+	}
+	return &result, nil
+}
+
 func (s *Server) elaborateWithGemini(ctx context.Context, workDir, fullPrompt string) (*elaboratedTask, error) {
 	combinedPrompt := fmt.Sprintf("%s\n\n%s", buildElaboratePrompt(workDir), fullPrompt)
 	cmd := exec.CommandContext(ctx, s.geminiBinaryPath(),
@@ -314,18 +343,27 @@ func (s *Server) handleElaborateTask(w http.ResponseWriter, r *http.Request) {
 	var result *elaboratedTask
 	var err error
 
-	// Try Claude first.
-	result, err = s.elaborateWithClaude(ctx, workDir, fullPrompt)
-	if err != nil {
-		s.logger.Warn("elaborate: claude failed, falling back to gemini", "error", err)
-		// Fallback to Gemini.
-		result, err = s.elaborateWithGemini(ctx, workDir, fullPrompt)
+	// Try local LLM first when configured. Falls back to Claude → Gemini on
+	// hard failure of each prior attempt.
+	if s.llm != nil {
+		result, err = elaborateWithLocal(ctx, s.llm, workDir, fullPrompt)
+		if err != nil {
+			s.logger.Warn("elaborate: local llm failed, falling back to claude", "error", err)
+			result = nil
+		}
+	}
+	if result == nil {
+		result, err = s.elaborateWithClaude(ctx, workDir, fullPrompt)
 		if err != nil {
-			s.logger.Error("elaborate: fallback gemini also failed", "error", err)
-			writeJSON(w, http.StatusBadGateway, map[string]string{
-				"error": fmt.Sprintf("elaboration failed: %v", err),
-			})
-			return
+			s.logger.Warn("elaborate: claude failed, falling back to gemini", "error", err)
+			result, err = s.elaborateWithGemini(ctx, workDir, fullPrompt)
+			if err != nil {
+				s.logger.Error("elaborate: gemini also failed", "error", err)
+				writeJSON(w, http.StatusBadGateway, map[string]string{
+					"error": fmt.Sprintf("elaboration failed: %v", err),
+				})
+				return
+			}
 		}
 	}
 
diff --git a/internal/api/elaborate_local_test.go b/internal/api/elaborate_local_test.go
new file mode 100644
index 0000000..09a8f9e
--- /dev/null
+++ b/internal/api/elaborate_local_test.go
@@ -0,0 +1,214 @@
+package api
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"fmt"
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"sync/atomic"
+	"testing"
+
+	"github.com/thepeterstone/claudomator/internal/llm"
+)
+
+// fakeChatCompletionsServer returns an httptest server that responds to a
+// /chat/completions POST with the given assistant content (which should be a
+// JSON-encoded elaboratedTask). Returns the server and a counter of calls
+// received so tests can assert dispatch ordering.
+func fakeChatCompletionsServer(t *testing.T, assistantContent string) (*httptest.Server, *int32) {
+	t.Helper()
+	var calls int32
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		atomic.AddInt32(&calls, 1)
+		w.Header().Set("Content-Type", "application/json")
+		// The assistant content has to be JSON-encoded inside the wire format.
+		escaped, _ := json.Marshal(assistantContent)
+		fmt.Fprintf(w, `{
+			"model":"local",
+			"choices":[{"message":{"role":"assistant","content":%s},"finish_reason":"stop"}],
+			"usage":{"prompt_tokens":10,"completion_tokens":50}
+		}`, string(escaped))
+	}))
+	t.Cleanup(srv.Close)
+	return srv, &calls
+}
+
+func TestElaborateWithLocal_ParsesValidResponse(t *testing.T) {
+	taskBody, _ := json.Marshal(elaboratedTask{
+		Name:        "Test elaborated task",
+		Description: "From local llm",
+		Agent: elaboratedAgent{
+			Type:         "claude",
+			Model:        "sonnet",
+			Instructions: "Run go build.",
+			MaxBudgetUSD: 0.25,
+			AllowedTools: []string{"Bash"},
+		},
+		Timeout:  "10m",
+		Priority: "normal",
+		Tags:     []string{"build"},
+	})
+	srv, calls := fakeChatCompletionsServer(t, string(taskBody))
+
+	c := &llm.Client{Endpoint: srv.URL + "/v1", Model: "fake"}
+	result, err := elaborateWithLocal(context.Background(), c, "/some/dir", "build the project")
+	if err != nil {
+		t.Fatalf("elaborateWithLocal: %v", err)
+	}
+	if result.Name != "Test elaborated task" {
+		t.Errorf("Name: %q", result.Name)
+	}
+	if result.Agent.Instructions != "Run go build." {
+		t.Errorf("Instructions: %q", result.Agent.Instructions)
+	}
+	if got := atomic.LoadInt32(calls); got != 1 {
+		t.Errorf("expected 1 call, got %d", got)
+	}
+}
+
+func TestElaborateWithLocal_NilClient(t *testing.T) {
+	_, err := elaborateWithLocal(context.Background(), nil, "", "p")
+	if err == nil || !strings.Contains(err.Error(), "no client") {
+		t.Errorf("expected nil-client error, got %v", err)
+	}
+}
+
+func TestElaborateWithLocal_BadJSON(t *testing.T) {
+	srv, _ := fakeChatCompletionsServer(t, "this is not JSON at all")
+	c := &llm.Client{Endpoint: srv.URL + "/v1", Model: "fake"}
+	_, err := elaborateWithLocal(context.Background(), c, "", "p")
+	if err == nil || !strings.Contains(err.Error(), "parse JSON") {
+		t.Errorf("expected parse error, got %v", err)
+	}
+}
+
+// TestElaborateTask_LocalLLMPreferred verifies the dispatcher uses local LLM
+// when SetLLM is configured, and does not invoke claude.
+func TestElaborateTask_LocalLLMPreferred(t *testing.T) {
+	srv, _ := testServer(t)
+
+	taskBody, _ := json.Marshal(elaboratedTask{
+		Name:        "Local-elaborated",
+		Description: "From local",
+		Agent: elaboratedAgent{
+			Type:         "claude",
+			Model:        "sonnet",
+			Instructions: "Do work. Tests pass when complete.",
+			MaxBudgetUSD: 0.25,
+			AllowedTools: []string{"Bash"},
+		},
+		Timeout:  "10m",
+		Priority: "normal",
+	})
+	llmSrv, _ := fakeChatCompletionsServer(t, string(taskBody))
+	srv.SetLLM(&llm.Client{Endpoint: llmSrv.URL + "/v1", Model: "fake"})
+	// Point Claude binary at a path that would fail if called.
+	srv.elaborateCmdPath = "/nonexistent/claude-should-not-run"
+
+	body := `{"prompt":"do work"}`
+	req := httptest.NewRequest("POST", "/api/tasks/elaborate", bytes.NewBufferString(body))
+	req.Header.Set("Content-Type", "application/json")
+	w := httptest.NewRecorder()
+	srv.Handler().ServeHTTP(w, req)
+
+	if w.Code != http.StatusOK {
+		t.Fatalf("status: want 200, got %d; body: %s", w.Code, w.Body.String())
+	}
+	var got elaboratedTask
+	if err := json.NewDecoder(w.Body).Decode(&got); err != nil {
+		t.Fatalf("decode response: %v", err)
+	}
+	if got.Name != "Local-elaborated" {
+		t.Errorf("Name: want Local-elaborated got %q", got.Name)
+	}
+}
+
+// TestElaborateTask_LocalFails_FallsBackToClaude verifies the dispatcher
+// falls back to the Claude path when the local LLM returns an error.
+func TestElaborateTask_LocalFails_FallsBackToClaude(t *testing.T) {
+	srv, _ := testServer(t)
+
+	// Local LLM server that always 500s.
+	failSrv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		http.Error(w, "boom", http.StatusInternalServerError)
+	}))
+	t.Cleanup(failSrv.Close)
+	srv.SetLLM(&llm.Client{Endpoint: failSrv.URL + "/v1", Model: "fake"})
+
+	// Configure a working fake Claude binary.
+	taskBody, _ := json.Marshal(elaboratedTask{
+		Name:        "Claude-fallback",
+		Description: "From claude after local failed",
+		Agent: elaboratedAgent{
+			Type:         "claude",
+			Model:        "sonnet",
+			Instructions: "Run tests.",
+			MaxBudgetUSD: 0.25,
+			AllowedTools: []string{"Bash"},
+		},
+		Timeout:  "10m",
+		Priority: "normal",
+	})
+	wrapper, _ := json.Marshal(map[string]string{"result": string(taskBody)})
+	srv.elaborateCmdPath = createFakeClaude(t, string(wrapper), 0)
+
+	body := `{"prompt":"run tests"}`
+	req := httptest.NewRequest("POST", "/api/tasks/elaborate", bytes.NewBufferString(body))
+	req.Header.Set("Content-Type", "application/json")
+	w := httptest.NewRecorder()
+	srv.Handler().ServeHTTP(w, req)
+
+	if w.Code != http.StatusOK {
+		t.Fatalf("status: want 200, got %d; body: %s", w.Code, w.Body.String())
+	}
+	var got elaboratedTask
+	if err := json.NewDecoder(w.Body).Decode(&got); err != nil {
+		t.Fatalf("decode response: %v", err)
+	}
+	if got.Name != "Claude-fallback" {
+		t.Errorf("Name: want Claude-fallback (fallback path) got %q", got.Name)
+	}
+}
+
+// TestElaborateTask_NoLocalLLM_UsesClaude verifies that when SetLLM is not
+// called, behavior is unchanged (Claude path still primary).
+func TestElaborateTask_NoLocalLLM_UsesClaude(t *testing.T) {
+	srv, _ := testServer(t)
+
+	taskBody, _ := json.Marshal(elaboratedTask{
+		Name:        "Claude-only",
+		Description: "no local llm configured",
+		Agent: elaboratedAgent{
+			Type:         "claude",
+			Model:        "sonnet",
+			Instructions: "Do work.",
+			MaxBudgetUSD: 0.25,
+			AllowedTools: []string{"Bash"},
+		},
+		Timeout:  "10m",
+		Priority: "normal",
+	})
+	wrapper, _ := json.Marshal(map[string]string{"result": string(taskBody)})
+	srv.elaborateCmdPath = createFakeClaude(t, string(wrapper), 0)
+
+	body := `{"prompt":"do work"}`
+	req := httptest.NewRequest("POST", "/api/tasks/elaborate", bytes.NewBufferString(body))
+	req.Header.Set("Content-Type", "application/json")
+	w := httptest.NewRecorder()
+	srv.Handler().ServeHTTP(w, req)
+
+	if w.Code != http.StatusOK {
+		t.Fatalf("status: want 200, got %d; body: %s", w.Code, w.Body.String())
+	}
+	var got elaboratedTask
+	if err := json.NewDecoder(w.Body).Decode(&got); err != nil {
+		t.Fatalf("decode response: %v", err)
+	}
+	if got.Name != "Claude-only" {
+		t.Errorf("Name: %q", got.Name)
+	}
+}
+
diff --git a/internal/api/server.go b/internal/api/server.go
index 8a20349..33048e4 100644
--- a/internal/api/server.go
+++ b/internal/api/server.go
@@ -12,6 +12,7 @@ import (
 
 	"github.com/thepeterstone/claudomator/internal/config"
 	"github.com/thepeterstone/claudomator/internal/executor"
+	"github.com/thepeterstone/claudomator/internal/llm"
 	"github.com/thepeterstone/claudomator/internal/notify"
 	"github.com/thepeterstone/claudomator/internal/storage"
 	"github.com/thepeterstone/claudomator/internal/task"
@@ -50,6 +51,7 @@ type Server struct {
 	elaborateLimiter *ipRateLimiter // per-IP rate limiter for elaborate/validate endpoints
 	webhookSecret    string         // HMAC-SHA256 secret for GitHub webhook validation
 	projects         []config.Project // configured projects for webhook routing
+	llm              *llm.Client    // optional local LLM client; when set, elaboration prefers it
 }
 
 // SetAPIToken configures a bearer token that must be supplied to access the API.
@@ -73,6 +75,13 @@ func (s *Server) SetWorkspaceRoot(path string) {
 	s.workspaceRoot = path
 }
 
+// SetLLM wires a local OpenAI-compatible LLM client for use by elaboration
+// (and future internal helpers). When non-nil, elaboration will prefer it
+// over the Claude CLI; on failure it falls back to claude → gemini.
+func (s *Server) SetLLM(c *llm.Client) {
+	s.llm = c
+}
+
 func NewServer(store *storage.DB, pool *executor.Pool, logger *slog.Logger, claudeBinPath, geminiBinPath string) *Server {
 	wd, _ := os.Getwd()
 	s := &Server{
diff --git a/internal/cli/serve.go b/internal/cli/serve.go
index e183bfc..2263d01 100644
--- a/internal/cli/serve.go
+++ b/internal/cli/serve.go
@@ -99,6 +99,10 @@ func serve(addr string) error {
 	if cfg.WorkspaceRoot != "" {
 		srv.SetWorkspaceRoot(cfg.WorkspaceRoot)
 	}
+	if cfg.LocalModel.UseForElaborate() {
+		srv.SetLLM(localClient)
+		logger.Info("elaboration prefers local llm", "endpoint", cfg.LocalModel.Endpoint)
+	}
 	srv.SetGitHubWebhookConfig(cfg.WebhookSecret, cfg.Projects)
 
 	// Register scripts.
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 {
diff --git a/internal/config/config_test.go b/internal/config/config_test.go
index 2bba2c4..e4f1a5d 100644
--- a/internal/config/config_test.go
+++ b/internal/config/config_test.go
@@ -53,3 +53,33 @@ func TestLoadFile_MissingFile_ReturnsError(t *testing.T) {
 		t.Fatal("expected error for missing file, got nil")
 	}
 }
+
+func TestLocalModel_UseForElaborate_EmptyEndpoint(t *testing.T) {
+	m := LocalModel{}
+	if m.UseForElaborate() {
+		t.Error("empty endpoint should never opt into elaborate")
+	}
+}
+
+func TestLocalModel_UseForElaborate_DefaultTrue(t *testing.T) {
+	m := LocalModel{Endpoint: "http://localhost:11434/v1"}
+	if !m.UseForElaborate() {
+		t.Error("endpoint set + default flag should opt in")
+	}
+}
+
+func TestLocalModel_UseForElaborate_ExplicitFalse(t *testing.T) {
+	f := false
+	m := LocalModel{Endpoint: "http://localhost:11434/v1", PreferForElaborate: &f}
+	if m.UseForElaborate() {
+		t.Error("explicit false should opt out")
+	}
+}
+
+func TestLocalModel_UseForElaborate_ExplicitTrue(t *testing.T) {
+	tr := true
+	m := LocalModel{Endpoint: "http://localhost:11434/v1", PreferForElaborate: &tr}
+	if !m.UseForElaborate() {
+		t.Error("explicit true should opt in")
+	}
+}