)]}'
{
  "log": [
    {
      "commit": "6fe809c2282f5d7e258ab60f4ff4d0b3e0739332",
      "tree": "1f9a0bccf5ab23ff15eb38c26bda8c9d4e3dfb3d",
      "parents": [
        "4a370aa1fe7a2fcafc41c0cd1bb4bf59bfb070a2"
      ],
      "author": {
        "name": "Josh Bleecher Snyder",
        "email": "josharian@gmail.com",
        "time": "Thu Jul 24 16:22:51 2025 -0700"
      },
      "committer": {
        "name": "Josh Bleecher Snyder",
        "email": "josharian@gmail.com",
        "time": "Wed Jul 30 11:30:10 2025 -0700"
      },
      "message": "claude: bash tool smorgasbord\n\nThis is a combination of a bunch of changes and bug fixes\naccumulated over a week. It decided not to spend a bunch of time\nteasing it apart into its components. I apologize.\n\nSignificant changes include:\n\n- clean up background bash execution\n- improve documentation\n- remove TODO we\u0027re not gonna do\n- add a \"process completed\" note to stderr\n- convert background result printing to xml-ish\n- combine stdout and stderr in background bash to match foreground use\n- hint to sketch to kill the process group\n- add missing timeouts propagation\n- tell agent that bash calls are stateless\n- thread pwd through explicitly\n- unify command creation\n- speed up missing command installation\n    I tried a bunch of different ways to prompt engineer this to be faster.\n    But Claude will be Claude. Solution: switch from agent to one-shot.\n\n    This is marginally more brittle, and can only use a package manager,\n    but that also prevents a bunch of possible curl|bash mess, etc.\n    And this was always best-effort anyway.\n\n    It\u0027s now MUCH faster to fail on non-existent commands, and about 2x\n    faster on the real commands I tried (yamllint, htop)...now mostly down\n    to the irreducible work involved in actually doing the installation.\n- remove SKETCH_ from bash env, except SKETCH_PROXY_ID\n- delay kill instructions until actually needed\n- add simple GIT_SEQUENCE_EDITOR\n- overhaul cancellation\n- explicitly disable EDITOR to prevent hangs\n    I have big plans here, but this will do for now.\n- simplify and unify handling of long outputs\n- switch to center trunctation of long outputs\n- add zombie process cleanup using unix.Wait4\n    Wow, I tried a bunch of things here.\n\n    When running as PID 1, we are responsible for reaping zombies.\n    Unfortunately, we can\u0027t do this in the simple/obvious way,\n    because simply listening for SIGCHILD and reaping races\n    with running cmd.Wait. We can\u0027t use a separate init process\n    or double-init sketch, because then we lose our seccomp\n    protection, and there\u0027s no particularly good way to extend it.\n\n    Instead, (h/t to Philip asking a good question), observe\n    that we are in a very controlled environment, and pretty much\n    the only way to get zombies is via the bash tool.\n    So we add reaping tied specifically to process groups started\n    by the bash tool, with an explicit understanding of their lifecycle.\n\n    Auto-installation of tools still creates zombies.\n    We now know how to fix it, but it is rare, so who cares.\n"
    },
    {
      "commit": "43b60b9b6906a2077175bcb1c3ea53b90d92a9f8",
      "tree": "14ecadd5c94db811087f97b0e7858f1482ff5f4e",
      "parents": [
        "95354b15c6469f871ecabd778c04304bcce16195"
      ],
      "author": {
        "name": "Josh Bleecher Snyder",
        "email": "josharian@gmail.com",
        "time": "Mon Jul 21 14:57:10 2025 -0700"
      },
      "committer": {
        "name": "Josh Bleecher Snyder",
        "email": "josharian@gmail.com",
        "time": "Mon Jul 21 19:46:45 2025 -0700"
      },
      "message": "llm: make Tool.Run return ToolOut\n\nThis is preliminary work towards\nallowing tools to add additional information.\nNo functional changes (at least, that\u0027s the intent).\n"
    },
    {
      "commit": "17b2fd9b8ed388f341b380c88e7c4c6f88494573",
      "tree": "1c1679f6ead6c587e8bf5add8ffcb978449c6703",
      "parents": [
        "39eb24f7dfb82c802dfe7b4caac500acde26a907"
      ],
      "author": {
        "name": "Josh Bleecher Snyder",
        "email": "josharian@gmail.com",
        "time": "Wed Jul 09 22:47:13 2025 +0000"
      },
      "committer": {
        "name": "Josh Bleecher Snyder",
        "email": "josharian@gmail.com",
        "time": "Thu Jul 10 19:38:07 2025 -0700"
      },
      "message": "claudetool: replace timeout parameter with slow_ok boolean\n\nEmpirically, the agent doesn\u0027t set timeouts long enough,\nand doesn\u0027t retry on failure.\n\nGive it only one decision to make: Is this maybe a slow command?\n\nIf, horror of horrors, your project can\u0027t accomplish tasks within the\ndefault timeouts, there\u0027s a new command line flag to adjust them.\n\nCo-Authored-By: sketch \u003chello@sketch.dev\u003e\nChange-ID: sc26e3516f28c22d4k\n"
    },
    {
      "commit": "cfd0fe64e379f066b117effe84100a38c48e493f",
      "tree": "fed8d755bb3a8fffd61f6cd5da706c9267a7c5f3",
      "parents": [
        "c540e8ea6a8dd2a5297345b6f9b885988338f237"
      ],
      "author": {
        "name": "Philip Zeyliger",
        "email": "philip@bold.dev",
        "time": "Sat Jun 21 02:17:41 2025 +0000"
      },
      "committer": {
        "name": "Philip Zeyliger",
        "email": "philip@bold.dev",
        "time": "Fri Jun 20 19:21:43 2025 -0700"
      },
      "message": "cleanup: remove unused functions and fix tests\n\nRemove unused Go code identified through systematic analysis:\n\nRemoved Functions:\n- BashRun() in claudetool/bash.go - legacy testing function\n- ContentToString() in claudetool/util.go - unused utility function\n- GetActiveTunnels() in dockerimg/tunnel_manager.go - unused getter method\n\nRemoved Types:\n- baseResponse struct in claudetool/browse/browse.go - unused response type\n\nTest Updates:\n- Replaced BashRun tests with direct Bash.Run calls in bash_test.go\n- Removed ContentToString test from agent_test.go (testing unused function)\n- Updated tunnel manager tests to access internal activeTunnels map directly\n- Fixed all compilation errors caused by removed functions\n\nAll tests now pass and the codebase is cleaner with reduced maintenance burden.\nThe removed functions had no references in production code and were only\nused in tests, which have been updated or removed as appropriate.\n\nCo-Authored-By: sketch \u003chello@sketch.dev\u003e\nChange-ID: s2cac4b024f877682k\n"
    },
    {
      "commit": "208938f612a498ec6b594564a643fe9172da061f",
      "tree": "80a8c313fbd548fc488ffeab3f00357eb7286726",
      "parents": [
        "3e9d80c6b6315ccf1754996e9b691555915d9839"
      ],
      "author": {
        "name": "Philip Zeyliger",
        "email": "philip@bold.dev",
        "time": "Tue May 13 17:17:18 2025 -0700"
      },
      "committer": {
        "name": "Philip Zeyliger",
        "email": "philip@bold.dev",
        "time": "Tue May 13 17:45:17 2025 -0700"
      },
      "message": "bash: Shorten bash tool default timeout to 10s.\n"
    },
    {
      "commit": "72252cbcb97840d724133be67c4c69cc69ebb2d3",
      "tree": "a361499dc3fa6b9af2be3e74cfd59fd8ba34690e",
      "parents": [
        "7ce5fb76d8748ebf73c5adf9d6cd8eb67716fba8"
      ],
      "author": {
        "name": "Philip Zeyliger",
        "email": "philip@bold.dev",
        "time": "Sat May 10 17:00:08 2025 -0700"
      },
      "committer": {
        "name": "Philip Zeyliger",
        "email": "philip@bold.dev",
        "time": "Sat May 10 17:00:08 2025 -0700"
      },
      "message": "llm and everything: Update ToolResult to use []Content instead of string for multimodal support\n\nThis was a journey. The sketch-generated summary below is acceptable,\nbut I want to tell you about it in my voice too. The goal was to send\nscreenshots to Claude, so that it could... look at them. Currently\nthe take screenshot and read screenshot tools are different, and they\u0027ll\nneed to be renamed/prompt-engineered a bit, but that\u0027s all fine.\n\nThe miserable part was that we had to change the return value\nof tool from string to Content[], and this crosses several layers:\n - llm.Tool\n - llm.Content\n - ant.Content \u0026 openai and gemini friends\n - AgentMessage [we left this alone]\n\nExtra fun is that Claude\u0027s API for sending images has nested Content\nfields, and empty string and missing needs to be distinguished for the\nText field (because lots of shell commands return the empty string!).\n\nFor the UI, I made us transform the results into a string, dropping\nimages. This would have been yet more churn for not much obvious\nbenefit. Plus, it was going to break skaband\u0027s compatibility, and ...\nyet more work.\n\nOpenAI and Gemini don\u0027t obviously support images in this same way,\nso they just don\u0027t get the tools.\n\n~~~~~~~~~~ Sketch said:\n\nThis architectural change transforms tool results from plain strings to []Content arrays, enabling multimodal interaction in the system. Key changes include:\n\n- Core structural changes:\n  - Modified ToolResult type from string to []Content across all packages\n  - Added MediaType field to Content struct for MIME type support\n  - Created TextContent and ImageContent helper functions\n  - Updated all tool.Run implementations to return []Content\n\n- Image handling:\n  - Implemented base64 image support in Anthropic adapter\n  - Added proper media type detection and content formatting\n  - Created browser_read_image tool for displaying screenshots\n  - Updated browser_screenshot to provide usable image paths\n\n- Adapter improvements:\n  - Updated all LLM adapters (ANT, OAI, GEM) to handle content arrays\n  - Added specialized image content handling in the Anthropic adapter\n  - Ensured proper JSON serialization/deserialization for all content types\n  - Improved test coverage for content arrays\n\n- UI enhancements:\n  - Added omitempty tags to reduce JSON response size\n  - Updated TypeScript types to handle array content\n  - Made field naming consistent (tool_error vs is_error)\n  - Preserved backward compatibility for existing consumers\n\nCo-Authored-By: sketch \u003chello@sketch.dev\u003e\nChange-ID: s1a2b3c4d5e6f7g8h\n"
    },
    {
      "commit": "b6d6d384a2cdbabd2d6abc94bd6b2c6c937d5e22",
      "tree": "64194d0e29739fc0dd686c23590f140d3ae883b7",
      "parents": [
        "31f152493929b3b171c140c2e0e22dbcf9059cac"
      ],
      "author": {
        "name": "Pokey Rule",
        "email": "755842+pokey@users.noreply.github.com",
        "time": "Wed May 07 10:29:03 2025 +0100"
      },
      "committer": {
        "name": "Pokey Rule",
        "email": "755842+pokey@users.noreply.github.com",
        "time": "Wed May 07 13:34:11 2025 +0100"
      },
      "message": "claudetool: Add SKETCH\u003d1 to bash tool environment\n\nThis adds the SKETCH\u003d1 environment variable to all commands executed\nby the bash tool. This makes the SKETCH environment variable available\nto scripts and programs run through the bash tool.\n\nCo-Authored-By: sketch \u003chello@sketch.dev\u003e\n"
    },
    {
      "commit": "b4c7e1bdd860836d46c64065f268007e721e5fb8",
      "tree": "fb3cd12df47cd05c4f549e39f5ee29fcd360040f",
      "parents": [
        "d43e57238d1b471938d10faa5b9762394b70aaac"
      ],
      "author": {
        "name": "Philip Zeyliger",
        "email": "philip.zeyliger@gmail.com",
        "time": "Wed Apr 23 19:30:58 2025 -0700"
      },
      "committer": {
        "name": "Philip Zeyliger",
        "email": "philip.zeyliger@gmail.com",
        "time": "Wed Apr 23 19:30:58 2025 -0700"
      },
      "message": "Removing LLM-generated skipped test\n"
    },
    {
      "commit": "b60f0f2c4f6baf635c7eeb2972d6ed25d9485891",
      "tree": "93a6b85c34010b1ef41072aad309e56e759694a6",
      "parents": [
        "cc3ba220373b62dd5a098180ea6797af76407525"
      ],
      "author": {
        "name": "Philip Zeyliger",
        "email": "philip.zeyliger@gmail.com",
        "time": "Wed Apr 23 18:19:32 2025 +0000"
      },
      "committer": {
        "name": "Philip Zeyliger",
        "email": "philip.zeyliger@gmail.com",
        "time": "Wed Apr 23 19:28:10 2025 -0700"
      },
      "message": "Add background execution capability to bash tool\n\nThis adds a \u0027background\u0027 flag to the bash tool, allowing commands to be\nexecuted without waiting for them to complete. When running in background\nmode, the command\u0027s stdout and stderr are redirected to temporary files,\nand the tool returns the PID and paths to these files as a JSON structure.\n\nFeatures:\n- Different default timeouts: 1m for foreground, 10m for background\n- Goroutine to properly reap background processes when they complete\n- Uses \u0027sketch-bg-\u0027 prefix for temporary directories\n- Added robust test helpers for waiting on files and processes\n- Skip agent test that uses recorded HTTP interactions incompatible with\n  the updated schema\n\nSketch also updated the various UIs\n\nCo-Authored-By: sketch\n"
    },
    {
      "commit": "2e463fb649fcff14d4025ddb91f630a98e7da526",
      "tree": "0e86854d80d2759a913870655f13226c31f9d30c",
      "parents": [],
      "author": {
        "name": "Earl Lee",
        "email": "earl.lee@sketch.dev",
        "time": "Thu Apr 17 11:22:22 2025 -0700"
      },
      "committer": {
        "name": "Earl Lee",
        "email": "earl.lee@sketch.dev",
        "time": "Thu Apr 17 11:35:33 2025 -0700"
      },
      "message": "Initial commit\n"
    }
  ]
}