all: update tests for claude 4
diff --git a/loop/testdata/agent_loop.httprr b/loop/testdata/agent_loop.httprr
index 9db732a..9da5ea3 100644
--- a/loop/testdata/agent_loop.httprr
+++ b/loop/testdata/agent_loop.httprr
@@ -1,14 +1,14 @@
httprr trace v1
-17928 2464
+18097 2496
POST https://api.anthropic.com/v1/messages HTTP/1.1
Host: api.anthropic.com
User-Agent: Go-http-client/1.1
-Content-Length: 17730
+Content-Length: 17899
Anthropic-Version: 2023-06-01
Content-Type: application/json
{
- "model": "claude-3-7-sonnet-20250219",
+ "model": "claude-sonnet-4-20250514",
"messages": [
{
"role": "user",
@@ -543,7 +543,7 @@
],
"system": [
{
- "text": "You are the expert software engineer and architect powering Sketch,\nan agentic coding environment that helps users accomplish coding tasks through autonomous analysis and implementation.\n\n\u003cworkflow\u003e\nStart by asking concise clarifying questions as needed.\nOnce the intent is clear, work autonomously.\nAim for a small diff size while thoroughly completing the requested task.\nPrioritize thoughtful analysis and critical engagement over agreeability.\n\nCall the title tool as soon as the topic of conversation is clear, often immediately.\n\nBreak down the overall goal into a series of smaller steps.\n(The first step is often: \"Make a plan.\")\nThen execute each step using tools.\nUpdate the plan if you have encountered problems or learned new information.\n\nWhen in doubt about a step, follow this broad workflow:\n\n- Think about how the current step fits into the overall plan.\n- Do research. Good tool choices: bash, think, keyword_search\n- Make edits.\n- Repeat.\n\nTo make edits reliably and efficiently, first think about the intent of the edit,\nand what set of patches will achieve that intent.\nThen use the patch tool to make those edits. Combine all edits to any given file into a single patch tool call.\n\nComplete every task exhaustively - no matter how repetitive or tedious.\nPartial work, pattern demonstrations, or stubs with TODOs are not acceptable, unless explicitly permitted by the user.\n\nThe done tool provides a checklist of items you MUST verify and\nreview before declaring that you are done. Before executing\nthe done tool, run all the tools the done tool checklist asks\nfor, including creating a git commit. Do not forget to run tests.\n\u003c/workflow\u003e\n\n\u003csystem_info\u003e\n\u003cplatform\u003e\nlinux/amd64\n\u003c/platform\u003e\n\u003cpwd\u003e\n/\n\u003c/pwd\u003e\n\u003c/system_info\u003e\n\n\u003cgit_info\u003e\n\u003cgit_root\u003e\n\n\u003c/git_root\u003e\n\u003cHEAD\u003e\nHEAD\n\u003c/HEAD\u003e\n\u003c/git_info\u003e\n\n",
+ "text": "You are the expert software engineer and architect powering Sketch,\nan agentic coding environment that helps users accomplish coding tasks through autonomous analysis and implementation.\n\n\u003cworkflow\u003e\nStart by asking concise clarifying questions as needed.\nOnce the intent is clear, work autonomously.\nAim for a small diff size while thoroughly completing the requested task.\nPrioritize thoughtful analysis and critical engagement over agreeability.\n\nCall the title tool as soon as the topic of conversation is clear, often immediately.\n\nBreak down the overall goal into a series of smaller steps.\n(The first step is often: \"Make a plan.\")\nThen execute each step using tools.\nUpdate the plan if you have encountered problems or learned new information.\n\nWhen in doubt about a step, follow this broad workflow:\n\n- Think about how the current step fits into the overall plan.\n- Do research. Good tool choices: bash, think, keyword_search\n- Make edits.\n- Repeat.\n\nTo make edits reliably and efficiently, first think about the intent of the edit,\nand what set of patches will achieve that intent.\nThen use the patch tool to make those edits. Combine all edits to any given file into a single patch tool call.\n\nComplete every task exhaustively - no matter how repetitive or tedious.\nPartial work, pattern demonstrations, or stubs with TODOs are not acceptable, unless explicitly permitted by the user.\n\nThe done tool provides a checklist of items you MUST verify and\nreview before declaring that you are done. Before executing\nthe done tool, run all the tools the done tool checklist asks\nfor, including creating a git commit. Do not forget to run tests.\n\u003c/workflow\u003e\n\n\u003cstyle\u003e\nDefault coding guidelines:\n- Clear is better than clever.\n- Minimal inline comments: non-obvious logic and key decisions only.\n\u003c/style\u003e\n\n\u003csystem_info\u003e\n\u003cplatform\u003e\nlinux/amd64\n\u003c/platform\u003e\n\u003cpwd\u003e\n/\n\u003c/pwd\u003e\n\u003c/system_info\u003e\n\n\u003cgit_info\u003e\n\u003cgit_root\u003e\n\n\u003c/git_root\u003e\n\u003cHEAD\u003e\nHEAD\n\u003c/HEAD\u003e\n\u003c/git_info\u003e\n\n",
"type": "text",
"cache_control": {
"type": "ephemeral"
@@ -554,24 +554,24 @@
Anthropic-Organization-Id: 3c473a21-7208-450a-a9f8-80aebda45c1b
Anthropic-Ratelimit-Input-Tokens-Limit: 200000
Anthropic-Ratelimit-Input-Tokens-Remaining: 200000
-Anthropic-Ratelimit-Input-Tokens-Reset: 2025-05-21T17:48:02Z
+Anthropic-Ratelimit-Input-Tokens-Reset: 2025-05-24T19:19:39Z
Anthropic-Ratelimit-Output-Tokens-Limit: 80000
Anthropic-Ratelimit-Output-Tokens-Remaining: 80000
-Anthropic-Ratelimit-Output-Tokens-Reset: 2025-05-21T17:48:07Z
+Anthropic-Ratelimit-Output-Tokens-Reset: 2025-05-24T19:19:45Z
Anthropic-Ratelimit-Requests-Limit: 4000
Anthropic-Ratelimit-Requests-Remaining: 3999
-Anthropic-Ratelimit-Requests-Reset: 2025-05-21T17:48:00Z
+Anthropic-Ratelimit-Requests-Reset: 2025-05-24T19:19:37Z
Anthropic-Ratelimit-Tokens-Limit: 280000
Anthropic-Ratelimit-Tokens-Remaining: 280000
-Anthropic-Ratelimit-Tokens-Reset: 2025-05-21T17:48:02Z
+Anthropic-Ratelimit-Tokens-Reset: 2025-05-24T19:19:39Z
Cf-Cache-Status: DYNAMIC
-Cf-Ray: 9435e6f92a33eb30-SJC
+Cf-Ray: 944f254d6862171a-SJC
Content-Type: application/json
-Date: Wed, 21 May 2025 17:48:07 GMT
-Request-Id: req_011CPM6VoDtiCGdVBSXHKwyJ
+Date: Sat, 24 May 2025 19:19:45 GMT
+Request-Id: req_011CPStukaCC4JCpQWvySWrY
Server: cloudflare
Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
Via: 1.1 google
X-Robots-Tag: none
-{"id":"msg_01SHazCNqLKJF4tFzepoU6h1","type":"message","role":"assistant","model":"claude-3-7-sonnet-20250219","content":[{"type":"text","text":"Here are the tools available to me:\n\n- `bash`: Executes shell commands\n- `keyword_search`: Searches for files with specific terms\n- `think`: Records thoughts, notes, or plans without external effects\n- `title`: Sets the conversation title\n- `precommit`: Creates a git branch for tracking work\n- `done`: Marks completion of user's goal with checklist evaluation\n- `codereview`: Runs automated code review\n- `about_sketch`: Provides information about Sketch\n- `multiplechoice`: Presents quick answer options to questions\n- `browser_navigate`: Navigates to a URL\n- `browser_click`: Clicks elements matching CSS selectors\n- `browser_type`: Types text into input elements\n- `browser_wait_for`: Waits for DOM elements\n- `browser_get_text`: Gets text from elements\n- `browser_eval`: Evaluates JavaScript\n- `browser_scroll_into_view`: Scrolls elements into view\n- `browser_resize`: Resizes browser window\n- `browser_recent_console_logs`: Gets browser console logs\n- `browser_clear_console_logs`: Clears console logs\n- `browser_take_screenshot`: Takes screenshots\n- `browser_read_image`: Reads image files\n- `patch`: Makes precise text edits to files"}],"stop_reason":"end_turn","stop_sequence":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":4125,"cache_read_input_tokens":0,"output_tokens":303}}
\ No newline at end of file
+{"id":"msg_01LmNpBXK7SGcuZNpqBXDbY8","type":"message","role":"assistant","model":"claude-sonnet-4-20250514","content":[{"type":"text","text":"Here are the tools available to me:\n\n**File & Code Operations:**\n- `bash` - Execute shell commands\n- `patch` - Modify files with precise text edits\n- `keyword_search` - Search codebase for relevant files\n- `codereview` - Run automated code review\n\n**Git Operations:**\n- `precommit` - Create git branch and get commit guidance\n\n**Browser Automation:**\n- `browser_navigate` - Navigate to URLs\n- `browser_click` - Click elements\n- `browser_type` - Type into inputs\n- `browser_wait_for` - Wait for elements\n- `browser_get_text` - Read element text\n- `browser_eval` - Execute JavaScript\n- `browser_scroll_into_view` - Scroll to elements\n- `browser_resize` - Resize browser window\n- `browser_take_screenshot` - Capture screenshots\n- `browser_read_image` - Read image files\n- `browser_recent_console_logs` - Get console logs\n- `browser_clear_console_logs` - Clear console logs\n\n**Workflow & Communication:**\n- `think` - Internal reasoning and planning\n- `title` - Set conversation title\n- `multiplechoice` - Present multiple choice questions\n- `about_sketch` - Get help with Sketch functionality\n- `done` - Complete tasks with verification checklist"}],"stop_reason":"end_turn","stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":4163,"cache_read_input_tokens":0,"output_tokens":311,"service_tier":"standard"}}
\ No newline at end of file