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

feat: add persistent PTY sessions

Browse Source
This commit is contained in:
NI0317
2026-07-21 16:01:00 +08:00
parent b4750f6333
commit 58cde5103a
71 changed files with 5677 additions and 82 deletions
Download Patch File Download Diff File Expand all files Collapse all files

64
examples/acp-agent/pty-snapshot-backend.mjs Normal file
View File

@@ -0,0 +1,64 @@
/** Deterministic in-memory PTY backend for transcript snapshots. */
class SnapshotSession {
motd = 'dsh> '
statusValue = { kind: 'running' }
scrollback = 'dsh> '
startSend(request) {
const viewport = `${request.text}\nPTY_OK\ndsh> `
this.scrollback += viewport
const result = {
viewport,
waitReason: 'stdin_read',
sessionStatus: this.statusValue,
truncated: false,
}
let consumed = false
return {
done: Promise.resolve(result),
readOutput: () => {
if (consumed) return { delta: '', truncated: false }
consumed = true
return { delta: viewport, truncated: false }
},
cancel: () => false,
}
}
read(request) {
const lines = this.scrollback.split('\n')
const offset = request.offset ?? 0
const count = request.count ?? 500
const end = lines.length - offset
const start = Math.max(0, end - count)
const text = lines.slice(start, end).join('\n')
return { text, totalLines: lines.length, lineBegin: offset, lineEnd: offset + text.split('\n').length, truncated: false }
}
signal() {
return Promise.resolve({ delivered: true, targetPgid: 1 })
}
status() {
return this.statusValue
}
close() {
this.statusValue = { kind: 'exited', exitCode: 0, signal: null }
return Promise.resolve()
}
}
/** Cordis plugin name. */
export const name = 'pty-snapshot-backend'
/** Required PTY service. */
export const inject = ['pty']
/** Register the deterministic snapshot backend. */
export function apply(ctx) {
ctx.pty.registerBackend({
type: 'shell',
spawn: () => Promise.resolve(new SnapshotSession()),
})
}

25
examples/acp-agent/pty.cordis.snapshot.yml Normal file
View File

@@ -0,0 +1,25 @@
# Keyless replay counterpart to pty.cordis.yml.
- id: base
name: '@cordisjs/plugin-include'
config:
path: ./cordis.yml
patches:
- id: llm-deepseek
name: '@deepseek-ai/dsh-llm-deepseek'
disabled: true
- insert:
- id: pty
name: '@deepseek-ai/dsh-pty'
- id: pty-snapshot-backend
name: './pty-snapshot-backend.mjs'
- id: tool-pty
name: '@deepseek-ai/dsh-tool-pty'
- id: llm-replay
name: '@deepseek-ai/dsh-llm-replay'
config:
providers:
- id: deepseek
name: DeepSeek
models:
- id: deepseek-v4-flash
- id: deepseek-v4-pro

20
examples/acp-agent/pty.cordis.yml Normal file
View File

@@ -0,0 +1,20 @@
# Opt-in persistent PTY composition for the PTY snapshot scenario. The base
# deployment already owns the shared sandbox provider and policy.
- id: base
name: '@cordisjs/plugin-include'
config:
path: ./cordis.yml
patches:
- insert:
- id: pty
name: '@deepseek-ai/dsh-pty'
- id: pty-local
name: '@deepseek-ai/dsh-pty-local'
config:
pollIntervalMs: 10
exactProbeAfterMs: 20
idleSilenceMs: 250
timeoutMs: 2000
disposeGraceMs: 500
- id: tool-pty
name: '@deepseek-ai/dsh-tool-pty'

9
examples/acp-agent/tests/acp.snapshot.ts
View File

@@ -30,6 +30,7 @@ const BOTH_MODE_CONFIG = fileURLToPath(new URL('../both-mode.cordis.yml', import
const WORKSPACE_CONTEXT_CONFIG = fileURLToPath(new URL('../workspace-context.cordis.yml', import.meta.url))
const ADVANCED_CONFIG = fileURLToPath(new URL('../advanced.cordis.yml', import.meta.url))
const FS_CONFIG = fileURLToPath(new URL('../fs.cordis.yml', import.meta.url))
const PTY_CONFIG = fileURLToPath(new URL('../pty.cordis.yml', import.meta.url))
function snapshotModeFromEnv(value: string | undefined): SnapshotSuiteOptions['mode'] {
switch (value) {
@@ -62,6 +63,14 @@ const SCENARIOS: Scenario[] = [
configPath: FS_CONFIG,
},
{ name: 'bash-spill', hasModelTurn: true, recorded: false, configPath: FS_CONFIG },
{
name: 'pty-tools',
hasModelTurn: true,
recorded: false,
pinsHeader: true,
headerClass: 'pty',
configPath: PTY_CONFIG,
},
{ name: 'fs-terminal-card', hasModelTurn: true, recorded: true },
{ name: 'todo-plan', hasModelTurn: true, recorded: true },
{ name: 'skill-load', hasModelTurn: true, recorded: false, pinsHeader: true, headerClass: 'skill' },

7
examples/acp-agent/tests/snapshots/pty-tools/input.json Normal file
View File

@@ -0,0 +1,7 @@
{
"steps": [
{ "op": "initialize", "terminalOutput": true },
{ "op": "newSession" },
{ "op": "prompt", "text": "Exercise the six PTY tools in order, including one missing-session signal error, then reply DONE." }
]
}

73
examples/acp-agent/tests/snapshots/pty-tools/session.jsonl Normal file
View File

@@ -0,0 +1,73 @@
{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}"}
{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Exercise the six PTY tools in order, including one missing-session signal error, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"}
{"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}}
{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"assistant/chunk","seq":4,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"pty-spawn","name":"pty_spawn","argumentsDelta":"{\"type\":\"shell\",\"name\":\"main\"}"}}}
{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"pty-spawn","name":"pty_spawn","arguments":"{\"type\":\"shell\",\"name\":\"main\"}"}}}}
{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":9,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"pty-spawn","name":"pty_spawn","arguments":"{\"type\":\"shell\",\"name\":\"main\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}
{"type":"tool/call","seq":10,"time":0,"data":{"turn":1,"step":1,"callId":"pty-spawn","name":"pty_spawn","arguments":"{\"type\":\"shell\",\"name\":\"main\"}"}}
{"type":"tool/result","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"pty-spawn","content":[{"type":"text","text":"started PTY session pty-1 (main) [type: shell]\ndsh> "}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"}
{"type":"step/end","seq":12,"time":0,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":13,"time":0,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":14,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"pty-send","name":"pty_send","argumentsDelta":"{\"sessionId\":\"pty-1\",\"text\":\"printf 'PTY_OK\\\\n'\"}"}}}
{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"pty-send","name":"pty_send","arguments":"{\"sessionId\":\"pty-1\",\"text\":\"printf 'PTY_OK\\\\n'\"}"}}}}
{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
{"type":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":19,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"pty-send","name":"pty_send","arguments":"{\"sessionId\":\"pty-1\",\"text\":\"printf 'PTY_OK\\\\n'\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[14,15,16,17,18],"surfaceOp":"append"}
{"type":"tool/call","seq":20,"time":0,"data":{"turn":1,"step":2,"callId":"pty-send","name":"pty_send","arguments":"{\"sessionId\":\"pty-1\",\"text\":\"printf 'PTY_OK\\\\n'\"}"}}
{"type":"tool/result","seq":21,"time":0,"data":{"turn":1,"step":2,"callId":"pty-send","content":[{"type":"text","text":"printf 'PTY_OK\\n'\nPTY_OK\ndsh> \n[wait: stdin_read]\n[session: running]"}],"isError":false,"meta":{"viewport":"printf 'PTY_OK\\n'\nPTY_OK\ndsh> ","waitReason":"stdin_read","sessionStatus":{"kind":"running"},"truncated":false}},"sourceEventSeqs":[20],"surfaceOp":"append"}
{"type":"step/end","seq":22,"time":0,"data":{"turn":1,"step":2}}
{"type":"step/start","seq":23,"time":0,"data":{"turn":1,"step":3}}
{"type":"assistant/chunk","seq":24,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":25,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"tool-call-delta","index":0,"id":"pty-read","name":"pty_read","argumentsDelta":"{\"sessionId\":\"pty-1\",\"offset\":0,\"count\":20}"}}}
{"type":"assistant/chunk","seq":26,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"pty-read","name":"pty_read","arguments":"{\"sessionId\":\"pty-1\",\"offset\":0,\"count\":20}"}}}}
{"type":"assistant/chunk","seq":27,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
{"type":"assistant/chunk","seq":28,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":29,"time":0,"data":{"turn":1,"step":3,"content":[{"type":"tool-call","id":"pty-read","name":"pty_read","arguments":"{\"sessionId\":\"pty-1\",\"offset\":0,\"count\":20}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[24,25,26,27,28],"surfaceOp":"append"}
{"type":"tool/call","seq":30,"time":0,"data":{"turn":1,"step":3,"callId":"pty-read","name":"pty_read","arguments":"{\"sessionId\":\"pty-1\",\"offset\":0,\"count\":20}"}}
{"type":"tool/result","seq":31,"time":0,"data":{"turn":1,"step":3,"callId":"pty-read","content":[{"type":"text","text":"dsh> printf 'PTY_OK\\n'\nPTY_OK\ndsh> \n[lines: 0-3 of 3]"}],"isError":false},"sourceEventSeqs":[30],"surfaceOp":"append"}
{"type":"step/end","seq":32,"time":0,"data":{"turn":1,"step":3}}
{"type":"step/start","seq":33,"time":0,"data":{"turn":1,"step":4}}
{"type":"assistant/chunk","seq":34,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":35,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"tool-call-delta","index":0,"id":"pty-signal","name":"pty_signal","argumentsDelta":"{\"sessionId\":\"pty-missing\",\"signal\":\"SIGINT\"}"}}}
{"type":"assistant/chunk","seq":36,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"pty-signal","name":"pty_signal","arguments":"{\"sessionId\":\"pty-missing\",\"signal\":\"SIGINT\"}"}}}}
{"type":"assistant/chunk","seq":37,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
{"type":"assistant/chunk","seq":38,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":39,"time":0,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"pty-signal","name":"pty_signal","arguments":"{\"sessionId\":\"pty-missing\",\"signal\":\"SIGINT\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[34,35,36,37,38],"surfaceOp":"append"}
{"type":"tool/call","seq":40,"time":0,"data":{"turn":1,"step":4,"callId":"pty-signal","name":"pty_signal","arguments":"{\"sessionId\":\"pty-missing\",\"signal\":\"SIGINT\"}"}}
{"type":"tool/result","seq":41,"time":0,"data":{"turn":1,"step":4,"callId":"pty-signal","content":[{"type":"text","text":"Error: unknown PTY session pty-missing"}],"isError":true},"sourceEventSeqs":[40],"surfaceOp":"append"}
{"type":"step/end","seq":42,"time":0,"data":{"turn":1,"step":4}}
{"type":"step/start","seq":43,"time":0,"data":{"turn":1,"step":5}}
{"type":"assistant/chunk","seq":44,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":45,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"tool-call-delta","index":0,"id":"pty-kill","name":"pty_kill","argumentsDelta":"{\"sessionId\":\"pty-1\"}"}}}
{"type":"assistant/chunk","seq":46,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"pty-kill","name":"pty_kill","arguments":"{\"sessionId\":\"pty-1\"}"}}}}
{"type":"assistant/chunk","seq":47,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
{"type":"assistant/chunk","seq":48,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":49,"time":0,"data":{"turn":1,"step":5,"content":[{"type":"tool-call","id":"pty-kill","name":"pty_kill","arguments":"{\"sessionId\":\"pty-1\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[44,45,46,47,48],"surfaceOp":"append"}
{"type":"tool/call","seq":50,"time":0,"data":{"turn":1,"step":5,"callId":"pty-kill","name":"pty_kill","arguments":"{\"sessionId\":\"pty-1\"}"}}
{"type":"tool/result","seq":51,"time":0,"data":{"turn":1,"step":5,"callId":"pty-kill","content":[{"type":"text","text":"killed PTY session pty-1"}],"isError":false},"sourceEventSeqs":[50],"surfaceOp":"append"}
{"type":"step/end","seq":52,"time":0,"data":{"turn":1,"step":5}}
{"type":"step/start","seq":53,"time":0,"data":{"turn":1,"step":6}}
{"type":"assistant/chunk","seq":54,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":55,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"tool-call-delta","index":0,"id":"pty-list","name":"pty_list","argumentsDelta":"{}"}}}
{"type":"assistant/chunk","seq":56,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"pty-list","name":"pty_list","arguments":"{}"}}}}
{"type":"assistant/chunk","seq":57,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
{"type":"assistant/chunk","seq":58,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":59,"time":0,"data":{"turn":1,"step":6,"content":[{"type":"tool-call","id":"pty-list","name":"pty_list","arguments":"{}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[54,55,56,57,58],"surfaceOp":"append"}
{"type":"tool/call","seq":60,"time":0,"data":{"turn":1,"step":6,"callId":"pty-list","name":"pty_list","arguments":"{}"}}
{"type":"tool/result","seq":61,"time":0,"data":{"turn":1,"step":6,"callId":"pty-list","content":[{"type":"text","text":"(no PTY sessions)"}],"isError":false},"sourceEventSeqs":[60],"surfaceOp":"append"}
{"type":"step/end","seq":62,"time":0,"data":{"turn":1,"step":6}}
{"type":"step/start","seq":63,"time":0,"data":{"turn":1,"step":7}}
{"type":"assistant/chunk","seq":64,"time":0,"data":{"turn":1,"step":7,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":65,"time":0,"data":{"turn":1,"step":7,"chunk":{"type":"text-delta","index":0,"text":"DONE"}}}
{"type":"assistant/chunk","seq":66,"time":0,"data":{"turn":1,"step":7,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}}}
{"type":"assistant/chunk","seq":67,"time":0,"data":{"turn":1,"step":7,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":3}}}}
{"type":"assistant/chunk","seq":68,"time":0,"data":{"turn":1,"step":7,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":69,"time":0,"data":{"turn":1,"step":7,"content":[{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":3}},"sourceEventSeqs":[64,65,66,67,68],"surfaceOp":"append"}
{"type":"step/end","seq":70,"time":0,"data":{"turn":1,"step":7}}
{"type":"turn/end","seq":71,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}

16
examples/acp-agent/tests/snapshots/pty-tools/stdout.expected.jsonl Normal file
View File

@@ -0,0 +1,16 @@
{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"pty-spawn","title":"Start PTY main","kind":"execute","status":"in_progress"}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"pty-spawn","status":"completed","content":[{"type":"content","content":{"type":"text","text":"started PTY session pty-1 (main) [type: shell]\ndsh> "}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"pty-send","title":"printf 'PTY_OK\\n'","kind":"execute","status":"in_progress","rawInput":"printf 'PTY_OK\\n'","content":[{"type":"content","content":{"type":"text","text":"PTY pty-1"}},{"type":"terminal","terminalId":"pty-send"}],"_meta":{"terminal_info":{"terminal_id":"pty-send","cwd":"{{cwd}}"}}}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"pty-send","status":"completed","_meta":{"terminal_output":{"terminal_id":"pty-send","data":"printf 'PTY_OK\\n'\nPTY_OK\ndsh> \n[wait: stdin_read]\n[session: running]"}}}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"pty-read","title":"Read PTY pty-1","kind":"read","status":"in_progress","rawInput":{"sessionId":"pty-1","offset":0,"count":20}}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"pty-read","status":"completed","content":[{"type":"content","content":{"type":"text","text":"dsh> printf 'PTY_OK\\n'\nPTY_OK\ndsh> \n[lines: 0-3 of 3]"}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"pty-signal","title":"Signal PTY pty-missing","kind":"execute","status":"in_progress","rawInput":{"sessionId":"pty-missing","signal":"SIGINT"}}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"pty-signal","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown PTY session pty-missing"}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"pty-kill","title":"Kill PTY pty-1","kind":"delete","status":"in_progress"}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"pty-kill","status":"completed","content":[{"type":"content","content":{"type":"text","text":"killed PTY session pty-1"}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"pty-list","title":"List PTY sessions","kind":"read","status":"in_progress"}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"pty-list","status":"completed","content":[{"type":"content","content":{"type":"text","text":"(no PTY sessions)"}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"DONE"}}}}
{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}}

23
examples/acp-agent/tests/snapshots/pty-tools/system-prompt.expected.md Normal file
View File

@@ -0,0 +1,23 @@
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.
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 PTY only when work needs persistent terminal state or interactive stdin; prefer bash/read/write/edit for bounded one-shot operations. Track every PTY session id and kill sessions that no longer matter. An inferred_idle or timeout result does not prove the foreground command exited.
Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.
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 -->
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.

505
examples/acp-agent/tests/snapshots/pty-tools/tool-schemas.expected.json Normal file
View File

@@ -0,0 +1,505 @@
{
"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`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
"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."
},
"sandbox_permissions": {
"type": "string",
"description": "The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.",
"enum": [
"workspace-write",
"danger-full-access"
]
},
"justification": {
"type": "string",
"description": "Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."
}
},
"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."
},
"sandbox_permissions": {
"type": "string",
"description": "The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.",
"enum": [
"workspace-write",
"danger-full-access"
]
},
"justification": {
"type": "string",
"description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access."
}
},
"required": [
"file_path",
"old_string",
"new_string"
]
}
},
{
"name": "pty_kill",
"description": "Close one persistent PTY and wait until its captured owned process tree is gone.",
"parameters": {
"type": "object",
"properties": {
"sessionId": {
"type": "string",
"description": "PTY session id."
}
},
"required": [
"sessionId"
]
}
},
{
"name": "pty_list",
"description": "List persistent PTY sessions owned by the current agent.",
"parameters": {
"type": "object",
"properties": {}
}
},
{
"name": "pty_read",
"description": "Read a bounded page of retained output from a persistent PTY without sending input.",
"parameters": {
"type": "object",
"properties": {
"sessionId": {
"type": "string",
"description": "PTY session id."
},
"offset": {
"type": "number",
"description": "Newest-relative line offset (default 0)."
},
"count": {
"type": "number",
"description": "Requested line count (default 500; backend caps apply)."
}
},
"required": [
"sessionId"
]
}
},
{
"name": "pty_send",
"description": "Send text to a persistent PTY. By default Enter is submitted and the call waits for a prompt, stdin wait, output silence, timeout, or session exit. Background mode returns a task id for task_output/task_kill.",
"parameters": {
"type": "object",
"properties": {
"sessionId": {
"type": "string",
"description": "PTY session id returned by pty_spawn or pty_list."
},
"text": {
"type": "string",
"description": "UTF-8 text to write to the terminal."
},
"submit": {
"type": "boolean",
"description": "Submit Enter after text (default true). Set false for control characters or incomplete REPL input."
},
"run_in_background": {
"type": "boolean",
"description": "Return a task id immediately; collect with task_output or stop with task_kill."
}
},
"required": [
"sessionId",
"text"
]
}
},
{
"name": "pty_signal",
"description": "Send an allowed signal to the current foreground process group of a persistent PTY.",
"parameters": {
"type": "object",
"properties": {
"sessionId": {
"type": "string",
"description": "PTY session id."
},
"signal": {
"type": "string",
"description": "Signal to deliver. Shell-targeted SIGKILL is rejected; use pty_kill.",
"enum": [
"SIGINT",
"SIGTERM",
"SIGKILL",
"SIGTSTP",
"SIGHUP"
]
}
},
"required": [
"sessionId",
"signal"
]
}
},
{
"name": "pty_spawn",
"description": "Create a persistent, owner-isolated PTY session from a registered backend type. Use this for shell or REPL state that must survive across tool calls.",
"parameters": {
"type": "object",
"properties": {
"type": {
"type": "string",
"description": "Registered PTY backend type, usually \"shell\"."
},
"name": {
"type": "string",
"description": "Optional owner-local display name such as \"main\" or \"gdb\"."
},
"cwd": {
"type": "string",
"description": "Initial working directory. Defaults to the deployment workspace root."
}
},
"required": [
"type"
]
}
},
{
"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": "skill",
"description": "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.",
"parameters": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "The exact skill name from the available skills list."
}
},
"required": [
"name"
]
}
},
{
"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. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.",
"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."
},
"run_in_background": {
"type": "boolean",
"description": "Run as a background task and return its id; collect with task_output or stop with task_kill."
}
},
"required": [
"description",
"prompt"
]
}
},
{
"name": "subagent_fork",
"description": "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. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.",
"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 task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."
},
"run_in_background": {
"type": "boolean",
"description": "Run as a background task and return its id; collect with task_output or stop with task_kill."
}
},
"required": [
"description",
"prompt"
]
}
},
{
"name": "task_kill",
"description": "Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.",
"parameters": {
"type": "object",
"properties": {
"task_id": {
"type": "string",
"description": "Task id returned by the tool that started the background work."
},
"reason": {
"type": "string",
"description": "Optional short reason, recorded in the log and forwarded to the task."
}
},
"required": [
"task_id"
]
}
},
{
"name": "task_list",
"description": "List your background tasks (running and finished) with their ids, kinds, and statuses.",
"parameters": {
"type": "object",
"properties": {}
}
},
{
"name": "task_output",
"description": "Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.",
"parameters": {
"type": "object",
"properties": {
"task_id": {
"type": "string",
"description": "Task id returned by the tool that started the background work."
},
"wait": {
"type": "boolean",
"description": "Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive."
},
"timeout_ms": {
"type": "number",
"description": "Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum."
}
},
"required": [
"task_id"
]
}
},
{
"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",
"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": "workflow",
"description": "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.\n\nThe 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?, provider?, 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.\n\nScript-body hooks:\n- `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), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `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.\n- `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`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: 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.",
"parameters": {
"type": "object",
"properties": {
"script": {
"type": "string",
"description": "The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."
},
"meta": {
"type": "object",
"description": "The workflow identity block (plain JSON — never code).",
"properties": {
"name": {
"type": "string",
"description": "Short kebab-case workflow name."
},
"description": {
"type": "string",
"description": "One-line description of what the workflow does."
},
"whenToUse": {
"type": "string",
"description": "Optional guidance on when this workflow applies."
},
"phases": {
"type": "array",
"description": "Optional phase declarations matched by phase() calls.",
"items": {
"type": "object",
"properties": {
"title": {
"type": "string",
"description": "The phase title phase() calls match by exact string."
},
"detail": {
"type": "string",
"description": "Optional one-line description of the phase."
},
"provider": {
"type": "string",
"description": "Optional provider override this phase is expected to use."
},
"model": {
"type": "string",
"description": "Optional model override this phase is expected to use."
}
},
"required": [
"title"
]
}
}
},
"required": [
"name",
"description"
]
},
"args": {
"type": "object",
"description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."
}
},
"required": [
"script",
"meta"
]
}
},
{
"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."
},
"sandbox_permissions": {
"type": "string",
"description": "The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.",
"enum": [
"workspace-write",
"danger-full-access"
]
},
"justification": {
"type": "string",
"description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access."
}
},
"required": [
"file_path",
"content"
]
}
}
],
"changes": []
}