loop: tell the agent that it is powering sketch
This makes the knowledge base verbiage make more sense,
while avoiding anthropomorphization.
diff --git a/loop/testdata/agent_loop.httprr b/loop/testdata/agent_loop.httprr
index 35417c1..3d1ad5b 100644
--- a/loop/testdata/agent_loop.httprr
+++ b/loop/testdata/agent_loop.httprr
@@ -1,9 +1,9 @@
httprr trace v1
-16361 2314
+16446 2070
POST https://api.anthropic.com/v1/messages HTTP/1.1
Host: api.anthropic.com
User-Agent: Go-http-client/1.1
-Content-Length: 16163
+Content-Length: 16248
Anthropic-Version: 2023-06-01
Content-Type: application/json
@@ -514,7 +514,7 @@
],
"system": [
{
- "text": "You are an expert coding assistant and architect.\nYou are assisting the user to achieve their goals.\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.\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\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\n\n\u003c/HEAD\u003e\n\u003c/git_info\u003e\n\n",
+ "text": "You are the expert coding assistant 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.\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\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\n\n\u003c/HEAD\u003e\n\u003c/git_info\u003e\n\n",
"type": "text",
"cache_control": {
"type": "ephemeral"
@@ -525,24 +525,24 @@
Anthropic-Organization-Id: 3c473a21-7208-450a-a9f8-80aebda45c1b
Anthropic-Ratelimit-Input-Tokens-Limit: 200000
Anthropic-Ratelimit-Input-Tokens-Remaining: 199000
-Anthropic-Ratelimit-Input-Tokens-Reset: 2025-05-13T01:15:55Z
+Anthropic-Ratelimit-Input-Tokens-Reset: 2025-05-13T02:19:49Z
Anthropic-Ratelimit-Output-Tokens-Limit: 80000
Anthropic-Ratelimit-Output-Tokens-Remaining: 80000
-Anthropic-Ratelimit-Output-Tokens-Reset: 2025-05-13T01:15:59Z
+Anthropic-Ratelimit-Output-Tokens-Reset: 2025-05-13T02:19:53Z
Anthropic-Ratelimit-Requests-Limit: 4000
Anthropic-Ratelimit-Requests-Remaining: 3999
-Anthropic-Ratelimit-Requests-Reset: 2025-05-13T01:15:54Z
+Anthropic-Ratelimit-Requests-Reset: 2025-05-13T02:19:48Z
Anthropic-Ratelimit-Tokens-Limit: 280000
Anthropic-Ratelimit-Tokens-Remaining: 279000
-Anthropic-Ratelimit-Tokens-Reset: 2025-05-13T01:15:55Z
+Anthropic-Ratelimit-Tokens-Reset: 2025-05-13T02:19:49Z
Cf-Cache-Status: DYNAMIC
-Cf-Ray: 93ee4eb0491e6426-SJC
+Cf-Ray: 93eeac4d2e40250d-SJC
Content-Type: application/json
-Date: Tue, 13 May 2025 01:15:59 GMT
-Request-Id: req_011CP4eNXNcezPCsgHD8gg2Q
+Date: Tue, 13 May 2025 02:19:53 GMT
+Request-Id: req_011CP4jFATfD5sh1tYAhwA8n
Server: cloudflare
Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
Via: 1.1 google
X-Robots-Tag: none
-{"id":"msg_01RPSRVLryPQEH6xYWh1qZng","type":"message","role":"assistant","model":"claude-3-7-sonnet-20250219","content":[{"type":"text","text":"Here's a brief list of the tools available to me:\n\n1. bash - Execute shell commands\n2. keyword_search - Search files using keywords\n3. think - For thought process without external effects\n4. title - Set conversation title (not calling as requested)\n5. precommit - Create a git branch for tracking work\n6. done - Mark task completion with a checklist\n7. codereview - Run automated code review\n8. multiplechoice - Present user with answer options\n9. browser_navigate - Navigate to a URL\n10. browser_click - Click on an element\n11. browser_type - Type text into an element\n12. browser_wait_for - Wait for an element\n13. browser_get_text - Get text from an element\n14. browser_eval - Evaluate JavaScript\n15. browser_scroll_into_view - Scroll to an element\n16. browser_resize - Resize browser window\n17. browser_take_screenshot - Take a screenshot\n18. browser_read_image - Read an image file\n19. patch - Modify files with precise text edits\n\nIs there a specific tool you'd like me to elaborate on?"}],"stop_reason":"end_turn","stop_sequence":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":3765,"cache_read_input_tokens":0,"output_tokens":259}}
\ No newline at end of file
+{"id":"msg_017ZjPLV2KNbvMP9GbZxxEB4","type":"message","role":"assistant","model":"claude-3-7-sonnet-20250219","content":[{"type":"text","text":"I have access to the following tools:\n\n1. bash - Executes shell commands\n2. keyword_search - Locates files with search terms\n3. think - For reasoning and note-taking (no external effects)\n4. title - Sets conversation title\n5. precommit - Creates git branches for tracking work\n6. done - Used when the user's goal is achieved\n7. codereview - Runs automated code review\n8. multiplechoice - Presents quick answer options to the user\n9. browser_* tools (navigate, click, type, wait_for, get_text, eval, scroll_into_view, resize, take_screenshot, read_image) - For browser automation\n10. patch - For precise text edits in files\n\nThese tools allow me to help with various coding tasks, file exploration, text editing, git operations, browser automation, and more."}],"stop_reason":"end_turn","stop_sequence":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":3776,"cache_read_input_tokens":0,"output_tokens":196}}
\ No newline at end of file