feat(agents): add thinking time logging between tool calls (#244)

* feat(agents): add thinking time logging between tool calls

Adds a ThinkingTimer utility that tracks the gap between tool results and
the next tool call. When the gap exceeds 3 seconds, it logs the duration
with a stopwatch emoji (⏱️ 4.2s).

Uses performance.now() for high-resolution timing and Intl.NumberFormat
for rendering duration in seconds with optional fraction digits.

Integrated across all 5 agents: Claude, Codex, Cursor, Gemini, OpenCode.

Closes #127

* fix: adjusting tests for mocking performance.now.

* fix: reducing diff for claude.

* fix: rm unused args for claude.

* rm unused args for codex.

* fix: rm unused args for gemini.

* fix: rm unused args for opencode.

* mv THINKING_THRESHOLD.

* rev: I decided to pospone node:perf_hooks integration since it requires more comprehensive refactoring.

* fix: using Intl unit formatting.

* tests for ThinkingTimer.

* fix: narrow unit.

* fix: making durationFormatter a class instance property since using one agent per run.

* fix: inverting condition in markToolCall.

* thinking timer improvements and fix actions/checkout v6 auth

- thinking timer: use » chevron and "thought for X seconds" format
- thinking timer: add debug timestamps for sanity checking
- demote PID namespace isolation logs to debug
- remove redundant "setting up git authentication" log
- fix duplicate Authorization header with actions/checkout v6: clean up
  includeIf credential entries that v6 persists via external config files

Co-authored-by: Cursor <cursoragent@cursor.com>

* standardize tool call log prefix to » double chevron

Co-authored-by: Cursor <cursoragent@cursor.com>

* update timer tests for new thinking log format

Co-authored-by: Cursor <cursoragent@cursor.com>

---------

Co-authored-by: pullfrog[bot] <226033991+pullfrog[bot]@users.noreply.github.com>
Co-authored-by: Robin Tail <robin_tail@me.com>
Co-authored-by: Colin McDonnell <colinmcd94@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>

agents/claude.ts

@@ -11,6 +11,7 @@ import { markActivity } from "../utils/activity.ts";
 import { log } from "../utils/cli.ts";
 import { installFromNpmTarball } from "../utils/install.ts";
 import { spawn } from "../utils/subprocess.ts";
+import { ThinkingTimer } from "../utils/timer.ts";
 import { type AgentRunContext, agent } from "./shared.ts";
 
 // model selection based on effort level
@@ -119,6 +120,7 @@ export const claude = agent({
 
     // Track bash tool IDs to identify when bash tool results come back
     const bashToolIds = new Set<string>();
+    const thinkingTimer = new ThinkingTimer();
 
     const result = await spawn({
       cmd: "node",
@@ -147,7 +149,7 @@ export const claude = agent({
 
             const handler = messageHandlers[message.type];
             if (handler) {
-              await handler(message as never, bashToolIds);
+              await handler(message as never, bashToolIds, thinkingTimer);
             }
           } catch {
             // ignore parse errors - might be non-JSON output
@@ -192,7 +194,8 @@ type SDKMessageType = SDKMessage["type"];
 
 type SDKMessageHandler<type extends SDKMessageType = SDKMessageType> = (
   data: Extract<SDKMessage, { type: type }>,
-  bashToolIds: Set<string>
+  bashToolIds: Set<string>,
+  thinkingTimer: ThinkingTimer
 ) => void | Promise<void>;
 
 type SDKMessageHandlers = {
@@ -200,7 +203,7 @@ type SDKMessageHandlers = {
 };
 
 const messageHandlers: SDKMessageHandlers = {
-  assistant: (data, bashToolIds) => {
+  assistant: (data, bashToolIds, thinkingTimer) => {
     if (data.message?.content) {
       for (const content of data.message.content) {
         if (content.type === "text" && content.text?.trim()) {
@@ -211,6 +214,7 @@ const messageHandlers: SDKMessageHandlers = {
             bashToolIds.add(content.id);
           }
 
+          thinkingTimer.markToolCall();
           log.toolCall({
             toolName: content.name,
             input: content.input,
@@ -219,10 +223,12 @@ const messageHandlers: SDKMessageHandlers = {
       }
     }
   },
-  user: (data, bashToolIds) => {
+  user: (data, bashToolIds, thinkingTimer) => {
     if (data.message?.content) {
       for (const content of data.message.content) {
         if (content.type === "tool_result") {
+          thinkingTimer.markToolResult();
+
           const toolUseId = (content as any).tool_use_id;
           const isBashTool = toolUseId && bashToolIds.has(toolUseId);