feat: Phase 9 gaps closed — ApprovalService.Decide convergence, execlog fold, execworker poller

- ApprovalService (core/app/approval.go) + ApprovalRepo (postgres adapter) with
  full decide transaction: HMAC token verify, approval flip, execution un-gate,
  session-scoped window keys (+session suffix matching GovernanceStore gate),
  nomos session flip, audit+event on failure abort. httpapi DecideApproval now
  a thin presenter delegating to the service. ListPending payload format fixed
  (json.Unmarshal not raw-wrap).
- execlog folded into postgres adapter: internal/execlog deleted, NewExecutionLog
  / ReadExecutionLog live in the db package, callers updated (mcp, httpapi).
- execworker poller over ExecutionService.DispatchQueued: advisory lock leak
  fixed (defer/recover per execution), correlation_id preserved via Finalize
  event emission (ExecRunRepo.Finalize now emits execution.{status} with
  correlation_id from the row).
- Phase 8 session export-rename completed: Store, New, and all 53 methods
  exported; cmd/nomos/ agent.go fixed to use session.PendingContinuation etc.
- Coverage gates: ExecutionService.Submit 93.1%, PolicyService.Decide 100%.
- Plans index updated, VERSION bumped to 0.36.0.

cmd/nomos/agent.go

@@ -1,6 +1,7 @@
 package main
 
 import (
+	"bytes"
 	"context"
 	"encoding/json"
 	"fmt"
@@ -153,6 +154,40 @@ gated mutations through run. Be concise. Prefer tools over guessing.`
 // explicit typed confirmation regardless of the window.
 const assentWindowDuration = 30 * time.Minute
 
+// approveExecution calls the oikos API to approve a pending execution.
+// Returns true + new status on success, false on any error.
+func (a *agent) approveExecution(ctx context.Context, execID string) (bool, string, error) {
+	if a.apiBase == "" || a.apiToken == "" {
+		return false, "", fmt.Errorf("nomos: apiBase or apiToken not configured")
+	}
+	body, _ := json.Marshal(map[string]string{"status": "approved"})
+	req, err := http.NewRequestWithContext(ctx, http.MethodPost,
+		a.apiBase+"/api/v1/approvals/"+execID+"/decision", bytes.NewReader(body))
+	if err != nil {
+		return false, "", fmt.Errorf("nomos: create approval request: %w", err)
+	}
+	req.Header.Set("Authorization", "Bearer "+a.apiToken)
+	req.Header.Set("Content-Type", "application/json")
+	resp, err := a.httpClient.Do(req)
+	if err != nil {
+		return false, "", fmt.Errorf("nomos: approval request failed: %w", err)
+	}
+	defer resp.Body.Close()
+	if resp.StatusCode == http.StatusNotFound {
+		return false, "", fmt.Errorf("nomos: approval %s not found", execID)
+	}
+	if resp.StatusCode != http.StatusOK {
+		return false, "", fmt.Errorf("nomos: approval %s returned %d", execID, resp.StatusCode)
+	}
+	var result struct {
+		Status string `json:"status"`
+	}
+	if err := json.NewDecoder(resp.Body).Decode(&result); err != nil {
+		return false, "", fmt.Errorf("nomos: decode approval response: %w", err)
+	}
+	return true, result.Status, nil
+}
+
 // openAssentWindow records an active assent window in autonomy_settings so
 // the MCP run tool (separate process) can check it before requiring approval
 // for config_mutation commands. Key is scoped to this agent's UUID AND this
@@ -295,12 +330,12 @@ func (a *agent) chatWith(ctx context.Context, sessionID, message, systemInject s
 	// isTypedConfirmation ("I confirm ...", per SOUL.md's guidance for what
 	// to ask the operator to type).
 	pending := assent.ExtractPendingApprovals(func() []string {
-			texts := make([]string, len(lastAssistantCalls))
-			for i, c := range lastAssistantCalls {
-				texts[i] = c.resultText()
-			}
-			return texts
-		}())
+		texts := make([]string, len(lastAssistantCalls))
+		for i, c := range lastAssistantCalls {
+			texts[i] = c.resultText()
+		}
+		return texts
+	}())
 	operatorAssented := assent.IsAssent(message)
 	typedConfirm := assent.IsTypedConfirmation(message)
 	if len(pending) > 0 && (operatorAssented || typedConfirm) {
@@ -394,11 +429,11 @@ func (a *agent) chatWith(ctx context.Context, sessionID, message, systemInject s
 		var acc openai.ChatCompletionAccumulator
 
 		// Capture token usage from this LLM response for activity logging.
-	// Previously always NULL — every agent_activity row had no token
-	// count. Now each tool call in this iteration gets the same total.
-	totalTokens := 0
+		// Previously always NULL — every agent_activity row had no token
+		// count. Now each tool call in this iteration gets the same total.
+		totalTokens := 0
 
-	for attempt := 0; attempt <= maxLLMRetries; attempt++ {
+		for attempt := 0; attempt <= maxLLMRetries; attempt++ {
 			acc = openai.ChatCompletionAccumulator{}
 			stream := a.provider.Chat.Completions.NewStreaming(ctx, params, a.reqOpts...)
 			for stream.Next() {
@@ -437,12 +472,12 @@ func (a *agent) chatWith(ctx context.Context, sessionID, message, systemInject s
 
 			if len(msg.ToolCalls) == 0 {
 				if isRefusalOrEmpty(msg.Content) {
-				if attempt < maxLLMRetries {
-					slog.Warn("nomos: empty or refusal response, retrying",
-						"session", sessionID, "iter", i+1, "attempt", attempt+1,
-						"content_len", len(msg.Content), "finish_reason", finishReason)
-					continue
-				}
+					if attempt < maxLLMRetries {
+						slog.Warn("nomos: empty or refusal response, retrying",
+							"session", sessionID, "iter", i+1, "attempt", attempt+1,
+							"content_len", len(msg.Content), "finish_reason", finishReason)
+						continue
+					}
 					// B.4: surface the real error context (finish_reason +
 					// refusal text) instead of a generic "empty response" —
 					// the operator can tell "content_filter — rephrase" from