From 4cf7603be427dd79910e68a14506385ff5fcbed0 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 28 Jul 2026 21:45:01 +0800 Subject: [PATCH] test(snapshot): enforce portable fixture invariants --- .../tests/snapshots/bash-tool/session.jsonl | 2 +- .../snapshots/subagent-spawn/session.1.jsonl | 2 +- .../snapshots/subagent-spawn/session.jsonl | 2 +- .../tests/snapshots/text-turn/session.jsonl | 2 +- .../acp-snapshot/tests/normalize.spec.ts | 34 +++++++++++++++---- 5 files changed, 31 insertions(+), 11 deletions(-) diff --git a/examples/jsonrpc-agent/tests/snapshots/bash-tool/session.jsonl b/examples/jsonrpc-agent/tests/snapshots/bash-tool/session.jsonl index b4f47e329b..c633ef6a37 100644 --- a/examples/jsonrpc-agent/tests/snapshots/bash-tool/session.jsonl +++ b/examples/jsonrpc-agent/tests/snapshots/bash-tool/session.jsonl @@ -3,7 +3,7 @@ {"type":"user/message","seq":1,"time":1785097395905,"data":{"content":[{"type":"text","text":"Run this exact command with your bash tool, then reply with its stdout only: echo dsh-sdk-proof-7391"}],"source":{"kind":"user"},"role":"user","id":"295507c3-4ba7-4695-a535-73e75046abb3"},"surfaceOp":"append"} {"type":"session/title","seq":2,"time":1785097395907,"data":{"title":"Run this exact command with","messageSeqs":[1],"source":{"kind":"fallback"}}} {"type":"step/start","seq":3,"time":1785097395908,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":4,"time":1785097395909,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are a coding agent.\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Background execution is not available; long-running commands must finish within the timeout.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."}},"required":["command","description"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","additionalProperties":false,"properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":4,"time":1785097395909,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":5,"time":1785097396437,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"reasoning-chunks","seq0":6,"time0":1785097396438,"data":{"turn":1,"step":1,"index":0,"dt":[219,22,1,0,0,0,1,24,25,0,0,25,1,24,1,0],"texts":["The"," user"," wants"," me"," to"," run"," a"," specific"," bash"," command"," and"," reply"," with"," its"," stdout"," only","."]}} {"type":"assistant/chunk","seq":23,"time":1785097396856,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} diff --git a/examples/jsonrpc-agent/tests/snapshots/subagent-spawn/session.1.jsonl b/examples/jsonrpc-agent/tests/snapshots/subagent-spawn/session.1.jsonl index d4bab038ea..2e121dfaba 100644 --- a/examples/jsonrpc-agent/tests/snapshots/subagent-spawn/session.1.jsonl +++ b/examples/jsonrpc-agent/tests/snapshots/subagent-spawn/session.1.jsonl @@ -3,7 +3,7 @@ {"type":"user/message","seq":1,"time":1785097410283,"data":{"content":[{"type":"text","text":"Reply with exactly: child answer 42."}],"source":{"kind":"user"},"role":"user","id":"fb1dfb09-5b8b-4343-8a04-49cc4c7c082e"},"surfaceOp":"append"} {"type":"session/title","seq":2,"time":1785097410283,"data":{"title":"Reply with exactly: child answer","messageSeqs":[1],"source":{"kind":"fallback"}}} {"type":"step/start","seq":3,"time":1785097410284,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":4,"time":1785097410284,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are a coding agent.\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Background execution is not available; long-running commands must finish within the timeout.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."}},"required":["command","description"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","additionalProperties":false,"properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":4,"time":1785097410284,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":5,"time":1785097410836,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"reasoning-chunks","seq0":6,"time0":1785097410836,"data":{"turn":1,"step":1,"index":0,"dt":[149,26,0,0,24,1,0,0,0,25,0,1,0],"texts":["The"," user"," wants"," me"," to"," reply"," with"," exactly"," \"","child"," answer"," ","42",".\""]}} {"type":"assistant/chunk","seq":20,"time":1785097411113,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} diff --git a/examples/jsonrpc-agent/tests/snapshots/subagent-spawn/session.jsonl b/examples/jsonrpc-agent/tests/snapshots/subagent-spawn/session.jsonl index c4e588b44f..7db65da9ba 100644 --- a/examples/jsonrpc-agent/tests/snapshots/subagent-spawn/session.jsonl +++ b/examples/jsonrpc-agent/tests/snapshots/subagent-spawn/session.jsonl @@ -3,7 +3,7 @@ {"type":"user/message","seq":1,"time":1785097408905,"data":{"content":[{"type":"text","text":"Use the subagent tool exactly once with description 'echo probe' and prompt: Reply with exactly: child answer 42. Then reply with the subagent's final answer verbatim."}],"source":{"kind":"user"},"role":"user","id":"e2664740-19d2-4e54-81e5-63ff154af28e"},"surfaceOp":"append"} {"type":"session/title","seq":2,"time":1785097408907,"data":{"title":"Use the subagent tool exactly","messageSeqs":[1],"source":{"kind":"fallback"}}} {"type":"step/start","seq":3,"time":1785097408908,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":4,"time":1785097408908,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are a coding agent.\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Background execution is not available; long-running commands must finish within the timeout.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."}},"required":["command","description"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","additionalProperties":false,"properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":4,"time":1785097408908,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":5,"time":1785097409495,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"reasoning-chunks","seq0":6,"time0":1785097409496,"data":{"turn":1,"step":1,"index":0,"dt":[170,25,1,0,0,0,0,24,0,1,0,0,0,26,0,0,0,0,0,26,0,0,0,0,0,30,0,0,1,0,0,20,1,0,0,28,0,1,0,0,0,23,1,0,0,0,0,25,1,25,26,1,0,0],"texts":["The"," user"," wants"," me"," to",":\n","1","."," Use"," the"," sub","agent"," tool"," exactly"," once"," with"," description"," '","echo"," probe","'"," and"," prompt"," '","Reply"," with"," exactly",":"," child"," answer"," ","42",".'\n","2","."," Then"," reply"," with"," the"," sub","agent","'s"," final"," answer"," verb","atim",".\n\n","Let"," me"," do"," this"," step"," by"," step","."]}} {"type":"assistant/chunk","seq":61,"time":1785097410031,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} diff --git a/examples/jsonrpc-agent/tests/snapshots/text-turn/session.jsonl b/examples/jsonrpc-agent/tests/snapshots/text-turn/session.jsonl index 7658bbe1c7..4827a0548f 100644 --- a/examples/jsonrpc-agent/tests/snapshots/text-turn/session.jsonl +++ b/examples/jsonrpc-agent/tests/snapshots/text-turn/session.jsonl @@ -3,7 +3,7 @@ {"type":"user/message","seq":1,"time":1785097381469,"data":{"content":[{"type":"text","text":"Reply with exactly: SDK snapshot OK"}],"source":{"kind":"user"},"role":"user","id":"4cb523e7-19c9-45d0-8799-911a78c26207"},"surfaceOp":"append"} {"type":"session/title","seq":2,"time":1785097381471,"data":{"title":"Reply with exactly: SDK snapshot","messageSeqs":[1],"source":{"kind":"fallback"}}} {"type":"step/start","seq":3,"time":1785097381472,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":4,"time":1785097381472,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are a coding agent.\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Background execution is not available; long-running commands must finish within the timeout.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."}},"required":["command","description"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","additionalProperties":false,"properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":4,"time":1785097381472,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":5,"time":1785097381978,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"reasoning-chunks","seq0":6,"time0":1785097381979,"data":{"turn":1,"step":1,"index":0,"dt":[138,28,27,1,0,0,24,1,0,0,0,26,0,1,25,1,0,0],"texts":["The"," user"," wants"," me"," to"," reply"," with"," exactly"," \"","SD","K"," snapshot"," OK","\"."," Let"," me"," do"," that","."]}} {"type":"assistant/chunk","seq":25,"time":1785097382251,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} diff --git a/packages/support/acp-snapshot/tests/normalize.spec.ts b/packages/support/acp-snapshot/tests/normalize.spec.ts index cc4f4c7dbf..e882ac2c63 100644 --- a/packages/support/acp-snapshot/tests/normalize.spec.ts +++ b/packages/support/acp-snapshot/tests/normalize.spec.ts @@ -390,6 +390,14 @@ describe('tokenizeSessionFixtureTmpdir', () => { }, reportedCwd: '/tmp/acp-snap-cwd-abc123', }, + { + name: 'Windows', + context: { + sessionIds: [], + cwd: String.raw`C:\Users\runner\AppData\Local\Temp\acp-snap-cwd-abc123`, + }, + reportedCwd: String.raw`C:\Users\runner\AppData\Local\Temp\acp-snap-cwd-abc123`, + }, ])('stores $name temporary workspaces with one portable root token', ({ context, reportedCwd }) => { const raw = [ JSON.stringify({ type: 'session', id: 's', createdAt: 1, cwd: context.cwd }), @@ -400,7 +408,7 @@ describe('tokenizeSessionFixtureTmpdir', () => { data: { content: [{ type: 'text', - text: `wrote ${reportedCwd}/proof.txt. cwd ${context.cwd}. Next; kept ${context.cwd}-backup, ${context.cwd}.backup, and /tmp/authored.txt`, + text: `wrote ${reportedCwd}/proof.txt. alias /different/root/acp-snap-cwd-abc123/alias.txt. cwd ${context.cwd}. Next; kept ${context.cwd}-backup, ${context.cwd}.backup, and /tmp/authored.txt`, }], }, }), @@ -408,14 +416,26 @@ describe('tokenizeSessionFixtureTmpdir', () => { ].join('\n') const out = tokenizeSessionFixtureTmpdir(raw) + const result = JSON.parse(out.split('\n')[1] as string) as { + data: { content: { text: string }[] } + } + const resultText = (result.data.content[0] as { text: string }).text expect(out).toContain('"cwd":"{{tmpdir}}/acp-snap-cwd-abc123"') - expect(out).toContain('wrote {{tmpdir}}/acp-snap-cwd-abc123/proof.txt') - expect(out).toContain('cwd {{tmpdir}}/acp-snap-cwd-abc123. Next') - expect(out).toContain(`${context.cwd}-backup`) - expect(out).toContain(`${context.cwd}.backup`) - expect(out).toContain('/tmp/authored.txt') - expect(out).not.toContain(`${reportedCwd}/proof.txt`) + expect(resultText).toContain('wrote {{tmpdir}}/acp-snap-cwd-abc123/proof.txt') + expect(resultText).toContain('alias {{tmpdir}}/acp-snap-cwd-abc123/alias.txt') + expect(resultText).toContain('cwd {{tmpdir}}/acp-snap-cwd-abc123. Next') + expect(resultText).toContain(`${context.cwd}-backup`) + expect(resultText).toContain(`${context.cwd}.backup`) + expect(resultText).toContain('/tmp/authored.txt') + expect(resultText).not.toContain(`${reportedCwd}/proof.txt`) + expect(tokenizeSessionFixtureTmpdir(out)).toBe(out) + }) + + it('rejects a log without a session cwd', () => { + expect(() => tokenizeSessionFixtureTmpdir('')).toThrow( + 'acp-snapshot: cannot tokenize a cwd without a basename', + ) }) })