Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/master' into codex/agent-session-jsonl-location

Browse Source 
# Conflicts:
#	examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/skill-load/session.jsonl
#	examples/acp-agent/tests/snapshots/text-turn/session.jsonl
#	examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl
This commit is contained in:
Yichen Jiang
2026-07-12 13:01:26 +08:00
parent d118d85147 4cda9dd03d
commit acdbe7b828
38 changed files with 742 additions and 191 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/acp-agent/both-mode.cordis.snapshot.yml
View File

@@ -20,11 +20,9 @@
tools:
mode: both
persona: |
You are a coding assistant powered by the {{model}} model. Your working
directory is {{cwd}}.
You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}.
Verify your work by running the code or tests. Keep answers brief and
factual.
Verify your work by running the code or tests. Keep answers brief and factual.
- insert:
- id: code-runtime
name: '@deepseek-ai/dsh-code-runtime-worker'

6
examples/acp-agent/both-mode.cordis.yml
View File

@@ -19,11 +19,9 @@
tools:
mode: both
persona: |
You are a coding assistant powered by the {{model}} model. Your working
directory is {{cwd}}.
You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}.
Verify your work by running the code or tests. Keep answers brief and
factual.
Verify your work by running the code or tests. Keep answers brief and factual.
- insert:
- id: code-runtime
name: '@deepseek-ai/dsh-code-runtime-worker'

6
examples/acp-agent/code-mode.cordis.snapshot.yml
View File

@@ -20,11 +20,9 @@
tools:
mode: code
persona: |
You are a coding assistant powered by the {{model}} model. Your working
directory is {{cwd}}.
You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}.
Verify your work by running the code or tests. Keep answers brief and
factual.
Verify your work by running the code or tests. Keep answers brief and factual.
- insert:
- id: code-runtime
name: '@deepseek-ai/dsh-code-runtime-worker'

6
examples/acp-agent/code-mode.cordis.yml
View File

@@ -20,11 +20,9 @@
tools:
mode: code
persona: |
You are a coding assistant powered by the {{model}} model. Your working
directory is {{cwd}}.
You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}.
Verify your work by running the code or tests. Keep answers brief and
factual.
Verify your work by running the code or tests. Keep answers brief and factual.
- insert:
- id: code-runtime
name: '@deepseek-ai/dsh-code-runtime-worker'

6
examples/acp-agent/cordis.yml
View File

@@ -44,11 +44,9 @@
# loop resolves per session (every ACP session carries the client's cwd,
# so the persona can state the workspace).
persona: |
You are a coding assistant powered by the {{model}} model. Your working
directory is {{cwd}}.
You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}.
Verify your work by running the code or tests. Keep answers brief and
factual.
Verify your work by running the code or tests. Keep answers brief and factual.
# The subagent seam + both in-process backends + two model-facing tools, as leaf
# entries after the app (which provides ctx.agents/ctx.tools). spawn (a fresh

5
examples/acp-agent/tests/acp.snapshot.ts
View File

@@ -45,9 +45,8 @@ function snapshotModeFromEnv(value: string | undefined): SnapshotSuiteOptions['m
const SCENARIOS: Scenario[] = [
{ name: 'handshake', hasModelTurn: false, recorded: false },
{ name: 'reject-extra-dirs', hasModelTurn: false, recorded: false },
// text-turn is the pinned-header scenario: the minimal single text turn,
// whose fixture is the ONE place the full system prompt + tool schemas are
// committed and compared verbatim.
// text-turn is the pinned-header scenario: the minimal single text turn.
// Its system-prompt.golden.md and JSONL tool list pin the composed header.
{ name: 'text-turn', hasModelTurn: true, recorded: true, pinsHeader: true },
{ name: 'tool-call-turn', hasModelTurn: true, recorded: true },
{ name: 'fs-terminal-card', hasModelTurn: true, recorded: true },

2
examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl
View File

File diff suppressed because one or more lines are too long

136
examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md Normal file
View File

@@ -0,0 +1,136 @@
You are an AI agent powered by the DeepSeek Harness SDK.
You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.
Verify your work by running the code or tests. Keep answers brief and factual.
Use 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.
Use 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.
Use 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.
Check the [exit code: N] marker on every bash result; investigate failures before moving on.
Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.
## Writing code for run_code
Pass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:
- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools["my-tool"](args)`. Every call resolves to the tool's text output as a string. Tool arguments must be JSON-serializable.
- A FAILED tool call rejects with an `Error` carrying the tool's error text — `try/catch` it to handle and continue.
- Calls execute sequentially, even under `Promise.all`.
- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.
The available tools:
```ts
declare const tools: {
/** 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]`. The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, `$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */
bash(args: {
/** The bash command to execute. */
command: string;
/** 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". */
description: string;
/** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */
timeoutMs?: number;
/** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */
workdir?: string;
/** Run in the background and return a task id immediately. No timeout applies. */
run_in_background?: boolean;
}): Promise<string>;
/** Ask the executor to kill a running background bash task by task id. */
bash_kill(args: {
/** Task id returned by the bash tool. */
task_id: string;
}): Promise<string>;
/** Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output. */
bash_output(args: {
/** Task id returned by the bash tool. */
task_id: string;
}): Promise<string>;
/** Edit an existing UTF-8 text file by replacing literal text. */
edit(args: {
/** Path to edit, resolved by the filesystem backend. */
file_path: string;
/** Literal text to replace. Must match exactly. */
old_string: string;
/** Literal replacement text. Use an empty string to delete the match. */
new_string: string;
/** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */
replace_all?: boolean;
}): Promise<string>;
/** Read a UTF-8 text file and return line-numbered content. */
read(args: {
/** Path to read, resolved by the filesystem backend. */
file_path: string;
/** 1-based first line to return. Defaults to 1. */
offset?: number;
/** Maximum number of lines to return. Defaults to 2000. */
limit?: number;
}): Promise<string>;
/** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */
skill(args: {
/** The exact skill name from the available skills list. */
name: string;
}): Promise<string>;
/** 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. */
subagent(args: {
/** A short (3-5 word) description of the delegated task, for display. */
description: string;
/** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */
prompt: string;
}): Promise<string>;
/** Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. */
subagent_fork(args: {
/** A short (3-5 word) description of the delegated task, for display. */
description: string;
/** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */
prompt: string;
}): Promise<string>;
/** 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). */
todo_write(args: {
/** The COMPLETE task list, replacing any previous list. */
todos: ({
/** What the task is — a short imperative line. */
content: string;
/** pending (not started) | in_progress (now) | completed (done). */
status: "pending" | "in_progress" | "completed";
})[];
}): Promise<string>;
/** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */
workflow(args: {
/** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`). */
script: string;
/** The workflow identity block (plain JSON — never code). */
meta: {
/** Short kebab-case workflow name. */
name: string;
/** One-line description of what the workflow does. */
description: string;
/** Optional guidance on when this workflow applies. */
whenToUse?: string;
/** Optional phase declarations matched by phase() calls. */
phases?: {
/** The phase title phase() calls match by exact string. */
title: string;
/** Optional one-line description of the phase. */
detail?: string;
/** Optional model override this phase is expected to use. */
model?: string;
}[];
};
/** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {"files": [...]}). */
args?: Record<string, unknown>;
}): Promise<string>;
/** Create or fully replace a UTF-8 text file. */
write(args: {
/** Path to write, resolved by the filesystem backend. */
file_path: string;
/** Full UTF-8 text content to write. */
content: string;
}): Promise<string>;
}
```

2
examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl
View File

File diff suppressed because one or more lines are too long

136
examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md Normal file
View File

@@ -0,0 +1,136 @@
You are an AI agent powered by the DeepSeek Harness SDK.
You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.
Verify your work by running the code or tests. Keep answers brief and factual.
Use 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.
Use 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.
Use 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.
Check the [exit code: N] marker on every bash result; investigate failures before moving on.
Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.
## Writing code for run_code
Pass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:
- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools["my-tool"](args)`. Every call resolves to the tool's text output as a string. Tool arguments must be JSON-serializable.
- A FAILED tool call rejects with an `Error` carrying the tool's error text — `try/catch` it to handle and continue.
- Calls execute sequentially, even under `Promise.all`.
- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.
The available tools:
```ts
declare const tools: {
/** 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]`. The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, `$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */
bash(args: {
/** The bash command to execute. */
command: string;
/** 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". */
description: string;
/** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */
timeoutMs?: number;
/** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */
workdir?: string;
/** Run in the background and return a task id immediately. No timeout applies. */
run_in_background?: boolean;
}): Promise<string>;
/** Ask the executor to kill a running background bash task by task id. */
bash_kill(args: {
/** Task id returned by the bash tool. */
task_id: string;
}): Promise<string>;
/** Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output. */
bash_output(args: {
/** Task id returned by the bash tool. */
task_id: string;
}): Promise<string>;
/** Edit an existing UTF-8 text file by replacing literal text. */
edit(args: {
/** Path to edit, resolved by the filesystem backend. */
file_path: string;
/** Literal text to replace. Must match exactly. */
old_string: string;
/** Literal replacement text. Use an empty string to delete the match. */
new_string: string;
/** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */
replace_all?: boolean;
}): Promise<string>;
/** Read a UTF-8 text file and return line-numbered content. */
read(args: {
/** Path to read, resolved by the filesystem backend. */
file_path: string;
/** 1-based first line to return. Defaults to 1. */
offset?: number;
/** Maximum number of lines to return. Defaults to 2000. */
limit?: number;
}): Promise<string>;
/** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */
skill(args: {
/** The exact skill name from the available skills list. */
name: string;
}): Promise<string>;
/** 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. */
subagent(args: {
/** A short (3-5 word) description of the delegated task, for display. */
description: string;
/** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */
prompt: string;
}): Promise<string>;
/** Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. */
subagent_fork(args: {
/** A short (3-5 word) description of the delegated task, for display. */
description: string;
/** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */
prompt: string;
}): Promise<string>;
/** 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). */
todo_write(args: {
/** The COMPLETE task list, replacing any previous list. */
todos: ({
/** What the task is — a short imperative line. */
content: string;
/** pending (not started) | in_progress (now) | completed (done). */
status: "pending" | "in_progress" | "completed";
})[];
}): Promise<string>;
/** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */
workflow(args: {
/** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`). */
script: string;
/** The workflow identity block (plain JSON — never code). */
meta: {
/** Short kebab-case workflow name. */
name: string;
/** One-line description of what the workflow does. */
description: string;
/** Optional guidance on when this workflow applies. */
whenToUse?: string;
/** Optional phase declarations matched by phase() calls. */
phases?: {
/** The phase title phase() calls match by exact string. */
title: string;
/** Optional one-line description of the phase. */
detail?: string;
/** Optional model override this phase is expected to use. */
model?: string;
}[];
};
/** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {"files": [...]}). */
args?: Record<string, unknown>;
}): Promise<string>;
/** Create or fully replace a UTF-8 text file. */
write(args: {
/** Path to write, resolved by the filesystem backend. */
file_path: string;
/** Full UTF-8 text content to write. */
content: string;
}): Promise<string>;
}
```

2
examples/acp-agent/tests/snapshots/skill-load/session.jsonl
View File

File diff suppressed because one or more lines are too long

16
examples/acp-agent/tests/snapshots/skill-load/system-prompt.golden.md Normal file
View File

@@ -0,0 +1,16 @@
You are an AI agent powered by the DeepSeek Harness SDK.
You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.
Verify your work by running the code or tests. Keep answers brief and factual.
Use 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.
Use 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.
Use 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.
Check the [exit code: N] marker on every bash result; investigate failures before moving on.
Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.

2
examples/acp-agent/tests/snapshots/text-turn/session.jsonl
View File

File diff suppressed because one or more lines are too long

16
examples/acp-agent/tests/snapshots/text-turn/system-prompt.golden.md Normal file
View File

@@ -0,0 +1,16 @@
You are an AI agent powered by the DeepSeek Harness SDK.
You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.
Verify your work by running the code or tests. Keep answers brief and factual.
Use 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.
Use 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.
Use 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.
Check the [exit code: N] marker on every bash result; investigate failures before moving on.
Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.

6
examples/coding-agent/tests/code-mode-keyless-smoke.e2e.ts
View File

@@ -67,8 +67,8 @@ async function bootAndEof(): Promise<{ stdout: string; code: number }> {
const timer = setTimeout(() => {
proc.kill('SIGKILL')
reject(new Error(`code-mode overlay did not exit within 10s. stdout:\n${stdout}\nstderr:\n${stderr}`))
}, 10_000)
reject(new Error(`code-mode overlay did not exit within 30s. stdout:\n${stdout}\nstderr:\n${stderr}`))
}, 30_000)
proc.on('exit', (code) => {
clearTimeout(timer)
@@ -87,5 +87,5 @@ describe('code-mode overlay keyless smoke (real code-mode.cordis.yml via the Loa
const { stdout, code } = await bootAndEof()
expect(code).toBe(0)
expect(stdout).toContain('code-mode agent ready.')
}, 15_000)
}, 45_000)
})

6
examples/coding-agent/tests/keyless-smoke.e2e.ts
View File

@@ -78,8 +78,8 @@ async function bootAndEof(): Promise<{ stdout: string; code: number }> {
const timer = setTimeout(() => {
proc.kill('SIGKILL')
reject(new Error(`coding-agent did not exit within 10s. stdout:\n${stdout}\nstderr:\n${stderr}`))
}, 10_000)
reject(new Error(`coding-agent did not exit within 30s. stdout:\n${stdout}\nstderr:\n${stderr}`))
}, 30_000)
proc.on('exit', (code) => {
clearTimeout(timer)
@@ -98,5 +98,5 @@ describe('coding-agent keyless smoke (real cordis.yml via the Loader)', () => {
const { stdout, code } = await bootAndEof()
expect(code).toBe(0)
expect(stdout).toContain('agent REPL ready.')
}, 15_000)
}, 45_000)
})

6
examples/cordis-agent/tests/keyless-smoke.e2e.ts
View File

@@ -70,8 +70,8 @@ async function bootAndEof(): Promise<{ stdout: string; code: number }> {
const timer = setTimeout(() => {
proc.kill('SIGKILL')
reject(new Error(`cordis-agent did not exit within 10s. stdout:\n${stdout}\nstderr:\n${stderr}`))
}, 10_000)
reject(new Error(`cordis-agent did not exit within 30s. stdout:\n${stdout}\nstderr:\n${stderr}`))
}, 30_000)
proc.on('exit', (code) => {
clearTimeout(timer)
@@ -90,5 +90,5 @@ describe('cordis-agent keyless smoke (real cordis.yml via the Loader)', () => {
const { stdout, code } = await bootAndEof()
expect(code).toBe(0)
expect(stdout).toContain('cordis-agent ready.')
}, 15_000)
}, 45_000)
})

12
examples/echo-agent/tests/echo.e2e.ts
View File

@@ -51,7 +51,7 @@ afterEach(async () => {
/**
* Boot echo-agent, write `lines` to its stdin, close stdin, and resolve with
* the full stdout once the process exits (the stdio UI exits on EOF after the
* agent settles). Rejects on a non-zero exit or a 10s timeout.
* agent settles). Rejects on a non-zero exit or a 30s timeout.
*/
async function runEcho(lines: string[]): Promise<{ stdout: string; code: number }> {
workdir = await mkdtemp(join(tmpdir(), 'echo-smoke-'))
@@ -84,8 +84,8 @@ async function runEcho(lines: string[]): Promise<{ stdout: string; code: number
const timer = setTimeout(() => {
proc.kill('SIGKILL')
reject(new Error(`echo-agent did not exit within 10s. stdout:\n${stdout}\nstderr:\n${stderr}`))
}, 10_000)
reject(new Error(`echo-agent did not exit within 30s. stdout:\n${stdout}\nstderr:\n${stderr}`))
}, 30_000)
proc.on('exit', (code) => {
clearTimeout(timer)
@@ -105,19 +105,19 @@ describe('echo-agent keyless smoke (real cordis.yml via the Loader)', () => {
const { stdout, code } = await runEcho([])
expect(code).toBe(0)
expect(stdout).toContain('echo-agent ready.')
}, 15_000)
}, 45_000)
it('runs the echo tool round-trip for an "echo …" line', async () => {
const { stdout } = await runEcho(['echo hello world'])
// mock-llm.ts emits a tool-call for the echo tool; echo-tool.ts uppercases.
expect(stdout).toContain('[tool call] echo')
expect(stdout).toContain('[tool result] ECHO: HELLO WORLD')
}, 15_000)
}, 45_000)
it('streams a direct canned reply for a non-echo line', async () => {
const { stdout } = await runEcho(['just chatting'])
// The direct-response branch of mock-llm.ts quotes the input back.
expect(stdout).toContain('just chatting')
expect(stdout).not.toContain('[tool call]')
}, 15_000)
}, 45_000)
})

7
examples/sandbox-acp-agent/cordis.yml
View File

@@ -55,9 +55,6 @@
# else the local ./.sessions default.
persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
persona: |
You are a coding assistant powered by the {{model}} model. Your working
directory is {{cwd}}. Your bash tool runs under a file sandbox — a
`[sandbox: file access denied …]` result is policy, not a command bug.
You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug.
Verify your work by running the code or tests. Keep answers brief and
factual.
Verify your work by running the code or tests. Keep answers brief and factual.

4
examples/sandbox-acp-agent/tests/snapshots/escalation-approved/session.jsonl
View File

@@ -114,8 +114,8 @@
{"type":"assistant/chunk","seq":112,"time":1783486771232,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":113,"time":1783486771236,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to retry the command with sandbox_permissions set to workspace-write. They explicitly said they will approve the permission prompt. Let me proceed."},{"type":"tool-call","id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt and cat its content\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}],"usage":{"inputTokens":1255,"outputTokens":160,"cacheReadTokens":0,"reasoningTokens":34}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112],"surfaceOp":"append"}
{"type":"tool/call","seq":114,"time":1783486771236,"data":{"turn":1,"step":1,"callId":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt and cat its content\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}}
{"type":"approval/asked","seq":115,"time":1783486771238,"data":{"id":"4766a1b9-6cf5-4504-a6cc-97037b478964","toolName":"bash","callId":"call_00_ZSEIrZNdgQhL2QJgVHww8689","reason":"escalate sandbox to workspace-write: the user asked to write escalated.txt in the workspace"}}
{"type":"approval/decided","seq":116,"time":1783486771243,"data":{"id":"4766a1b9-6cf5-4504-a6cc-97037b478964","outcome":"allowed-once"}}
{"type":"approval/asked","seq":115,"time":1783486771238,"data":{"id":"3ec45405-5add-4929-a755-e8c077ec7a7e","toolName":"bash","callId":"call_00_ZSEIrZNdgQhL2QJgVHww8689","reason":"escalate sandbox to workspace-write: the user asked to write escalated.txt in the workspace"}}
{"type":"approval/decided","seq":116,"time":1783486771243,"data":{"id":"3ec45405-5add-4929-a755-e8c077ec7a7e","outcome":"allowed-once"}}
{"type":"tool/result","seq":117,"time":1783486771442,"data":{"turn":1,"step":1,"callId":"call_00_ZSEIrZNdgQhL2QJgVHww8689","content":[{"type":"text","text":"escalated\n"}],"isError":false},"sourceEventSeqs":[114],"surfaceOp":"append"}
{"type":"step/end","seq":118,"time":1783486771443,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":119,"time":1783486771443,"data":{"turn":1,"step":2}}

4
examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/session.jsonl
View File

@@ -151,8 +151,8 @@
{"type":"assistant/chunk","seq":149,"time":1783486774569,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":150,"time":1783486774572,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to retry the exact command `printf 'escalated\\n' > escalated.txt && cat escalated.txt` with `sandbox_permissions` set to `workspace-write` and the justification they specified. They explicitly say they will reject the permission prompt, so after rejection I should explain in one short sentence and stop."},{"type":"tool-call","id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt with workspace-write permission\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}],"usage":{"inputTokens":1269,"outputTokens":197,"cacheReadTokens":0,"reasoningTokens":70}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149],"surfaceOp":"append"}
{"type":"tool/call","seq":151,"time":1783486774572,"data":{"turn":1,"step":1,"callId":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt with workspace-write permission\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}}
{"type":"approval/asked","seq":152,"time":1783486774574,"data":{"id":"774d5e97-a3af-4fc9-ae83-25dc2617909b","toolName":"bash","callId":"call_00_ODln9LCQtuvTw4FDZEfe3479","reason":"escalate sandbox to workspace-write: the user asked to write escalated.txt in the workspace"}}
{"type":"approval/decided","seq":153,"time":1783486774578,"data":{"id":"774d5e97-a3af-4fc9-ae83-25dc2617909b","outcome":"rejected"}}
{"type":"approval/asked","seq":152,"time":1783486774574,"data":{"id":"ed977255-38a3-4c1d-9f4e-0e258ef86e94","toolName":"bash","callId":"call_00_ODln9LCQtuvTw4FDZEfe3479","reason":"escalate sandbox to workspace-write: the user asked to write escalated.txt in the workspace"}}
{"type":"approval/decided","seq":153,"time":1783486774578,"data":{"id":"ed977255-38a3-4c1d-9f4e-0e258ef86e94","outcome":"rejected"}}
{"type":"tool/result","seq":154,"time":1783486774579,"data":{"turn":1,"step":1,"callId":"call_00_ODln9LCQtuvTw4FDZEfe3479","content":[{"type":"text","text":"Error: the user rejected escalating this command to \"workspace-write\""}],"isError":true},"sourceEventSeqs":[151],"surfaceOp":"append"}
{"type":"step/end","seq":155,"time":1783486774579,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":156,"time":1783486774580,"data":{"turn":1,"step":2}}

4
examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl
View File

File diff suppressed because one or more lines are too long

15
examples/sandbox-acp-agent/tests/snapshots/mode-switching/system-prompt.golden.md Normal file
View File

@@ -0,0 +1,15 @@
You are an AI agent powered by the DeepSeek Harness SDK.
You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug.
Verify your work by running the code or tests. Keep answers brief and factual.
Check the [exit code: N] marker on every bash result; investigate failures before moving on.
<!-- dsh-user-approval-policy:ask -->
<!-- request/header-delta 1: keepStart=9, keepEnd=0 -->
Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).
<!-- dsh-user-approval-policy:never -->