Merge remote-tracking branch 'origin/master' into codex/sandbox-policy-context
This commit is contained in:
NI0317
@@ -43,6 +43,8 @@ const RETRY_CONFIG = fileURLToPath(new URL('../retry.cordis.yml', import.meta.ur
|
||||
const SESSION_TITLE_CONFIG = fileURLToPath(new URL('../session-title.cordis.yml', import.meta.url))
|
||||
const LSP_CONFIG = fileURLToPath(new URL('./lsp.cordis.yml', import.meta.url))
|
||||
const WEB_CONFIG = fileURLToPath(new URL('../web.cordis.yml', import.meta.url))
|
||||
const FS_SEARCH_CONFIG = fileURLToPath(new URL('./fs-search.cordis.yml', import.meta.url))
|
||||
const FS_SEARCH_BIN = fileURLToPath(new URL('./fixtures/fs-search-bin', import.meta.url))
|
||||
const SNAPSHOTS_DIR = join(dirname(fileURLToPath(import.meta.url)), 'snapshots')
|
||||
const PACKED_CHUNKS_SOURCE = 'hook-cc-pretool-deny'
|
||||
|
||||
@@ -148,6 +150,19 @@ const SCENARIOS: Scenario[] = [
|
||||
hasModelTurn: true,
|
||||
recorded: true,
|
||||
},
|
||||
// The real Loader/app/bash path executes a deterministic rg stand-in at the
|
||||
// external-process seam, pinning over-cap glob sampling without depending on
|
||||
// a host-installed ripgrep binary.
|
||||
{
|
||||
name: 'fs-glob-sampling',
|
||||
hasModelTurn: true,
|
||||
recorded: false,
|
||||
pinsHeader: true,
|
||||
headerClass: 'fs-search',
|
||||
configPath: FS_SEARCH_CONFIG,
|
||||
env: { PATH: `${FS_SEARCH_BIN}:${process.env.PATH ?? ''}` },
|
||||
posixOnly: true,
|
||||
},
|
||||
{ name: 'fs-read', hasModelTurn: true, recorded: true },
|
||||
{ name: 'fs-write', hasModelTurn: true, recorded: true },
|
||||
{ name: 'fs-edit', hasModelTurn: true, recorded: true },
|
||||
|
||||
10
examples/acp-agent/tests/fixtures/fs-search-bin/rg
vendored
Executable file
10
examples/acp-agent/tests/fixtures/fs-search-bin/rg
vendored
Executable file
@@ -0,0 +1,10 @@
|
||||
#!/bin/sh
|
||||
printf '%s\n' \
|
||||
'archive/a.ts' \
|
||||
'archive/b.ts' \
|
||||
'archive/c.ts' \
|
||||
'old\one' \
|
||||
'old\two' \
|
||||
'src/index.ts' \
|
||||
'docs/guide.md' \
|
||||
'test/spec.ts'
|
||||
35
examples/acp-agent/tests/fs-search.cordis.snapshot.yml
Normal file
35
examples/acp-agent/tests/fs-search.cordis.snapshot.yml
Normal file
@@ -0,0 +1,35 @@
|
||||
# Minimal keyless composition: real app, bash, and search tool; replayed model.
|
||||
- id: llm-replay
|
||||
name: '@deepseek-ai/dsh-llm-replay'
|
||||
config:
|
||||
providers:
|
||||
- id: deepseek
|
||||
name: DeepSeek
|
||||
models:
|
||||
- id: deepseek-v4-pro
|
||||
|
||||
- id: subprocess
|
||||
name: '@deepseek-ai/dsh-subprocess-local'
|
||||
|
||||
- id: bash
|
||||
name: '@deepseek-ai/dsh-bash-local'
|
||||
|
||||
- id: acp-agent
|
||||
name: '@deepseek-ai/dsh-acp-demo'
|
||||
config:
|
||||
provider: deepseek
|
||||
model: deepseek-v4-pro
|
||||
persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
|
||||
persistenceCompression: none
|
||||
workspaceContext: false
|
||||
skills:
|
||||
enabled: false
|
||||
toolTasks: false
|
||||
goals: false
|
||||
persona: You are a concise snapshot agent working in {{cwd}}.
|
||||
|
||||
- id: tool-fs-search
|
||||
name: '@deepseek-ai/dsh-tool-fs-search'
|
||||
config:
|
||||
sampleOverCapGlobResults: true
|
||||
globMaxResults: 4
|
||||
33
examples/acp-agent/tests/fs-search.cordis.yml
Normal file
33
examples/acp-agent/tests/fs-search.cordis.yml
Normal file
@@ -0,0 +1,33 @@
|
||||
# Minimal live counterpart for the glob-sampling snapshot composition.
|
||||
- id: llm-deepseek
|
||||
name: '@deepseek-ai/dsh-llm-deepseek'
|
||||
config:
|
||||
apiKey: !!js process.env.DEEPSEEK_API_KEY
|
||||
baseURL: !!js process.env.DEEPSEEK_BASE_URL
|
||||
models:
|
||||
- id: deepseek-v4-pro
|
||||
|
||||
- id: subprocess
|
||||
name: '@deepseek-ai/dsh-subprocess-local'
|
||||
|
||||
- id: bash
|
||||
name: '@deepseek-ai/dsh-bash-local'
|
||||
|
||||
- id: acp-agent
|
||||
name: '@deepseek-ai/dsh-acp-demo'
|
||||
config:
|
||||
provider: deepseek
|
||||
model: deepseek-v4-pro
|
||||
persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
|
||||
workspaceContext: false
|
||||
skills:
|
||||
enabled: false
|
||||
toolTasks: false
|
||||
goals: false
|
||||
persona: You are a concise snapshot agent working in {{cwd}}.
|
||||
|
||||
- id: tool-fs-search
|
||||
name: '@deepseek-ai/dsh-tool-fs-search'
|
||||
config:
|
||||
sampleOverCapGlobResults: true
|
||||
globMaxResults: 4
|
||||
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"steps": [
|
||||
{ "op": "initialize" },
|
||||
{ "op": "newSession" },
|
||||
{ "op": "prompt", "text": "Call glob exactly once with pattern * and no path. Then reply with exactly GLOB_SAMPLED and nothing else." }
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,24 @@
|
||||
{"type":"session","version":0,"id":"f5a99d52-3eaa-4ce7-858d-61d4fd77df2a","createdAt":1785218400000,"cwd":"{{cwd}}","delegationDepth":0}
|
||||
{"type":"turn/start","seq":0,"time":1785218400001,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"user/message","seq":1,"time":1785218400002,"data":{"content":[{"type":"text","text":"Call glob exactly once with pattern * and no path. Then reply with exactly GLOB_SAMPLED and nothing else."}],"source":{"kind":"user"},"role":"user","id":"4b397774-ea1a-445a-8116-d25647bf32e6"},"surfaceOp":"append"}
|
||||
{"type":"session/title","seq":2,"time":1785218400003,"data":{"title":"Call glob exactly once with","messageSeqs":[1],"source":{"kind":"fallback"}}}
|
||||
{"type":"step/start","seq":3,"time":1785218400004,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":4,"time":1785218400005,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-pro"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":5,"time":1785218400006,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
|
||||
{"type":"assistant/chunk","seq":6,"time":1785218400007,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"glob-sampling-call","name":"glob","argumentsDelta":"{\"pattern\":\"*\"}"}}}
|
||||
{"type":"assistant/chunk","seq":7,"time":1785218400008,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"glob-sampling-call","name":"glob","arguments":"{\"pattern\":\"*\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":8,"time":1785218400009,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1,"outputTokens":1}}}}
|
||||
{"type":"assistant/chunk","seq":9,"time":1785218400010,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":10,"time":1785218400011,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"glob-sampling-call","name":"glob","arguments":"{\"pattern\":\"*\"}"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-pro"},"id":"d8c174b5-2f08-49b3-80d5-a69aabefbd7a"},"usage":{"inputTokens":1,"outputTokens":1}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":11,"time":1785218400012,"data":{"turn":1,"step":1,"callId":"glob-sampling-call","name":"glob","arguments":"{\"pattern\":\"*\"}"}}
|
||||
{"type":"tool/result","seq":12,"time":1785218400013,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"glob-sampling-call"},"content":[{"type":"tool-result","toolCallId":"glob-sampling-call","content":[{"type":"text","text":"archive/a.ts\nold\\one\nold\\two\nsrc/index.ts\n\n(Showing 4 of 8 paths, sampled across 4 of the 6 top-level entries this pattern matched instead of taken in modification-time order. Narrow path to inspect a specific subtree. The complete result could not be saved; narrow pattern or path to see more.)"}],"isError":false}],"role":"user","id":"e9711775-0ea5-4383-a562-76a6b49a4742"}},"sourceEventSeqs":[11],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":13,"time":1785218400014,"data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","seq":14,"time":1785218400015,"data":{"turn":1,"step":2}}
|
||||
{"type":"assistant/chunk","seq":15,"time":1785218400016,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
|
||||
{"type":"assistant/chunk","seq":16,"time":1785218400017,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"GLOB_SAMPLED"}}}
|
||||
{"type":"assistant/chunk","seq":17,"time":1785218400018,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"GLOB_SAMPLED"}}}}
|
||||
{"type":"assistant/chunk","seq":18,"time":1785218400019,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":1,"outputTokens":1}}}}
|
||||
{"type":"assistant/chunk","seq":19,"time":1785218400020,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":20,"time":1785218400021,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"text","text":"GLOB_SAMPLED"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-pro"},"id":"6f8b4c32-baad-405b-9957-435dc5c855b2"},"usage":{"inputTokens":1,"outputTokens":1}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":21,"time":1785218400022,"data":{"turn":1,"step":2}}
|
||||
{"type":"turn/end","seq":22,"time":1785218400023,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
@@ -0,0 +1,4 @@
|
||||
{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
|
||||
{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"GLOB_SAMPLED"}}}}
|
||||
{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}}
|
||||
@@ -0,0 +1,9 @@
|
||||
You are an AI agent powered by the DeepSeek Harness SDK.
|
||||
|
||||
You are a concise snapshot agent working in {{cwd}}.
|
||||
|
||||
Use the glob tool — not shell find — to discover files by path pattern. A pattern with no "/" matches basenames at any depth, so "*" matches every file in the tree rather than its top level. Results are files only, never directories, and include hidden and ignored files: a result that fits comes back in modification-time order, while a larger one is sampled across top-level entries, so it spans the tree instead of one subtree.
|
||||
|
||||
Use the grep tool — not shell grep or rg — to search file contents. Use read on a matched file when you need surrounding context.
|
||||
|
||||
Check the [exit code: N] marker on every bash result; investigate failures before moving on.
|
||||
@@ -0,0 +1,82 @@
|
||||
{
|
||||
"initial": [
|
||||
{
|
||||
"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> 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. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`.",
|
||||
"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."
|
||||
},
|
||||
"run_in_background": {
|
||||
"type": "boolean",
|
||||
"description": "Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"command",
|
||||
"description"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "glob",
|
||||
"description": "Find files whose paths match a glob pattern. Returns matching file paths — never directories — including hidden and ignored files (VCS metadata directories are excluded). Up to 4 paths come back in modification-time order; a larger result instead returns 4 paths sampled across top-level entries, says so, and reports where the complete sorted list was saved. This tool does not enumerate directory entries.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"pattern": {
|
||||
"type": "string",
|
||||
"description": "Glob pattern to match file paths against (e.g. \"**/*.ts\", \"src/**/*.test.js\"). A pattern with no \"/\" matches the basename at any depth, so \"*\" and \"*.ts\" both search the whole tree; include a separator to anchor the depth."
|
||||
},
|
||||
"path": {
|
||||
"type": "string",
|
||||
"description": "Directory to search in. Defaults to the session workspace; a relative path resolves against it."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"pattern"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "grep",
|
||||
"description": "Search file contents with a ripgrep regular expression. Returns matching lines with line numbers, grouped by file. Returns the first 250 matches inline; a capped result reports where the complete match list was saved. Use read on a matched file for surrounding context.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"pattern": {
|
||||
"type": "string",
|
||||
"description": "Regular expression to search for (ripgrep syntax)."
|
||||
},
|
||||
"path": {
|
||||
"type": "string",
|
||||
"description": "File or directory to search. Defaults to the session workspace; a relative path resolves against it."
|
||||
},
|
||||
"include": {
|
||||
"type": "string",
|
||||
"description": "One glob filter for which files to search (e.g. \"*.ts\", \"*.{js,jsx}\"). Not a list; negation is not supported."
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"pattern"
|
||||
]
|
||||
}
|
||||
}
|
||||
],
|
||||
"changes": []
|
||||
}
|
||||
Reference in New Issue
Block a user