Merge remote-tracking branch 'origin/master' into codex/pr48-repo-hardening-rfcs
# Conflicts: # docs/adr/README.md # docs/rfc/009-session-persistence-and-resumability.md # docs/rfc/README.md # docs/rfc/implemented/2026-06-11-doc-sync-enforcement.md # docs/rfc/proposed/2026-06-14-acp-agent-client-protocol.md # examples/acp-agent/tests/acp.e2e.ts # packages/acp/README.md # packages/acp/src/index.ts # packages/acp/tests/stream-update.spec.ts # packages/agent-loop/src/loop.ts # packages/tools/src/index.ts
This commit is contained in:
Tianyi Cui
104 files changed
+2586
-590
No files matched your search
@@ -32,6 +32,10 @@ Result text: stdout, then a `[stderr]` section, then status markers — `[timed
|
||||
|
||||
The owning agent is recorded per task id at spawn and kept for the lifetime of the loaded plugin instance (it is **not** cleared on completion). `bash_output`/`bash_kill` reject a task owned by a *different* agent with `task <id> belongs to another session` (a task started with no agent — a non-loop caller — has no owner and is open to anyone; a call with no `exec.agent` cannot access an owned task). Task ids are global and predictable, so under multi-session ACP this ownership check is the fence that stops one session's agent from reading or killing another session's background task. (`TODO(tool-bash-owner-hmr)`: an independent HMR reload of this plugin starts a fresh map, so a task spawned before the reload becomes un-owned — acceptable as HMR is dev-only and the session boundary is one user's cooperative editor; a durable fix attaches ownership to the executor/task lifetime.)
|
||||
|
||||
## UI presentation
|
||||
|
||||
These tools own how their calls render in a UI (an editor's tool-call card) via the `dsh-tools` `presentCall`/`presentResult` seam — a UI never special-cases tool names. For `bash`: the **title** is the exact `command` ("ls -la src") and `kind` is `execute` (terminal/run treatment), matching the reference ACP adapters (claude-agent-acp, codex-acp), which both use the bare command as an execute tool's title. The command is ALSO the **rawInput** for non-terminal UIs that render it (an execute-kind card hides rawInput — Zed shows it only for non-terminal tools — so the command must BE the title to be seen). The model-written `description` rides as a **content** text block shown ABOVE the card. (claude-agent-acp DROPS the description in terminal mode and shows only the card; surfacing it as a content block is a deliberate divergence — we keep the human summary visible alongside the card.) The completed output is wrapped in a fenced ` ```console ` block as the no-terminal-capability fallback — a UI-only affordance, so the model-facing result text stays unfenced. A FOREGROUND `bash` run also flags itself as a **terminal** (the neutral `terminal` field: `presentCall` sets a `cwd` from the model `workdir` when given — absolute as-is, relative for the UI bridge to resolve against the session cwd — else leaves it for the bridge to fill from the session cwd; `presentResult` carries the raw output plus the parsed `exitCode`/`signal`) so a capable client (Zed) renders a terminal card with an exit-status pill instead of the text block — see `packages/acp` ("Terminal card"). A `run_in_background` call is NOT a terminal (it returns a task id immediately and never streams a terminal — poll with `bash_output`), and an `isError` result (spawn failure / abort) carries no exit pill (there is no real process exit); both render as the ordinary execute card / fenced text. `bash_output`/`bash_kill` present a task-scoped title ("Read output from background task bash-3" / "Kill background task bash-3") with the task id as rawInput. These methods are pure/display-only (they also run on `session/load` replay), and a malformed/older logged arg shape falls back to a generic presentation rather than throwing. See `packages/tools` ("Tool-owned UI presentation") and `packages/acp` ("Terminal card" / "Tool-call presentation").
|
||||
|
||||
## Background completion notices
|
||||
|
||||
When a background task finishes, a short notice is injected into the owning agent's session (`agent.inject()`, source `{kind: 'plugin', plugin: 'tool-bash'}`). Injection is **durable context for the next model request, not a wake-up** — an idle agent stays idle until something sends a message. That's why the tool descriptions tell the model to poll with `bash_output`.
|
||||
|
||||
@@ -39,6 +39,7 @@
|
||||
import type { Context } from 'cordis'
|
||||
import { isAbsolute, resolve as resolvePath } from 'node:path'
|
||||
import { defineTool } from '@deepseek-ai/dsh-tools'
|
||||
import type { ToolCallPresentation, ToolResult, ToolResultPresentation } from '@deepseek-ai/dsh-tools'
|
||||
import type { Agent } from '@deepseek-ai/dsh-agent'
|
||||
import type { BashRunResult, BashTask, CollectedOutput } from '@deepseek-ai/dsh-bash'
|
||||
|
||||
@@ -47,10 +48,11 @@ export const inject = ['tools', 'bash']
|
||||
|
||||
/**
|
||||
* Validate the constraints the SchemaSpec can't express. `defineTool` now
|
||||
* validates parsed args against the SchemaSpec before `execute` runs (RFC 005
|
||||
* → ADR 0011), so type/required/enum checks are already done and `args` is
|
||||
* the validated `InferArgs` shape here. What remains are value constraints the
|
||||
* DSL has no vocabulary for: non-empty strings and a positive, finite timeout.
|
||||
* validates parsed args against the SchemaSpec before `execute` runs (the
|
||||
* arg-validation RFC), so type/required/enum checks are already done and `args`
|
||||
* is the validated `InferArgs` shape here. What remains are value constraints
|
||||
* the DSL has no vocabulary for: non-empty strings and a positive, finite
|
||||
* timeout.
|
||||
*/
|
||||
function validateBashArgs(args: {
|
||||
command: string
|
||||
@@ -72,7 +74,7 @@ function validateBashArgs(args: {
|
||||
|
||||
/**
|
||||
* Reject an empty `task_id`. Type and presence are guaranteed by the
|
||||
* SchemaSpec validation (ADR 0011); only the non-empty constraint, which the
|
||||
* SchemaSpec validation (the arg-validation RFC); only the non-empty constraint, which the
|
||||
* DSL can't express, is left to check here.
|
||||
*/
|
||||
function validateTaskId(value: string): string {
|
||||
@@ -123,6 +125,119 @@ export function renderResult(result: BashRunResult): string {
|
||||
return body + markers.join('\n')
|
||||
}
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// UI presentation (tool-owned). These shape how a UI (e.g. the ACP bridge)
|
||||
// renders a bash call's pending and completed states. They are display-only and
|
||||
// pure — a UI may call them during live streaming AND a session-log replay.
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
/**
|
||||
* Pending-state presentation for a `bash` call. The TITLE is the exact `command`
|
||||
* — a `kind: 'execute'` card is rendered as a terminal whose header label IS the
|
||||
* title, and an execute-kind card HIDES `rawInput` (Zed: `should_show_raw_input
|
||||
* = !is_terminal_tool`), so the command must BE the title to be seen. This
|
||||
* mirrors the reference ACP adapters (claude-agent-acp, codex-acp), which both
|
||||
* use the bare command as an execute tool's title. The model-written
|
||||
* `description` (a readable summary) rides as a `content` text block shown ABOVE
|
||||
* the card. (Note: claude-agent-acp DROPS the description in terminal mode and
|
||||
* shows only the card; surfacing it as a content block is a deliberate
|
||||
* divergence here — we keep the human summary visible alongside the card.)
|
||||
* `rawInput` still carries the bare command for non-execute UIs that DO render it.
|
||||
*
|
||||
* `terminal` marks the call so a capable UI renders a TERMINAL card — but ONLY a
|
||||
* FOREGROUND run is a terminal: a `run_in_background` call returns a task id
|
||||
* immediately (it never streams a terminal; its output is polled via
|
||||
* `bash_output`), so it is NOT marked terminal and renders as an ordinary
|
||||
* execute card. For a foreground run the `terminal.cwd` (header) is the model
|
||||
* `workdir` when given — ABSOLUTE as-is, RELATIVE for the UI bridge to resolve
|
||||
* against the session cwd; when omitted the bridge fills the session workspace
|
||||
* cwd (this PURE presenter, args only, can't see it).
|
||||
*/
|
||||
type BashCallArgs = { command: string; description: string; workdir?: string; run_in_background?: boolean }
|
||||
|
||||
function presentBashCall(args: BashCallArgs): ToolCallPresentation {
|
||||
const base = {
|
||||
title: args.command,
|
||||
kind: 'execute' as const,
|
||||
rawInput: args.command,
|
||||
content: [{ type: 'text' as const, text: args.description }],
|
||||
}
|
||||
// A background start is not an interactive terminal — no terminal card.
|
||||
if (args.run_in_background === true) return base
|
||||
return { ...base, terminal: args.workdir !== undefined ? { cwd: args.workdir } : {} }
|
||||
}
|
||||
|
||||
/**
|
||||
* Completed-state presentation for a `bash` call. Two parallel renderings of the
|
||||
* same output: `terminal.output` for a UI that shows a terminal card (the run's
|
||||
* stdout/stderr + status markers, exactly as the model sees them — the RAW text,
|
||||
* newlines preserved, since a terminal renderer relies on exact bytes), and a
|
||||
* fenced ```console `content` block as the fallback for a UI without terminal
|
||||
* support (the fences are a UI-only affordance, so they live here, not in the
|
||||
* model-facing result; the fenced body is trimmed of trailing blank lines for a
|
||||
* tidy block). A capable UI also gets an exit-status pill from `terminal.exitCode`
|
||||
* / `terminal.signal`, parsed from the status markers `renderResult` appended.
|
||||
*
|
||||
* Terminal output/exit is suppressed for results that are NOT a finished
|
||||
* foreground run: a `run_in_background` start (`isBackground` — the text is a
|
||||
* task-id ack, not a streamed run) and an `isError` result (a spawn failure or
|
||||
* abort — there is no real process exit to pill, and the body is an error
|
||||
* message, not `renderResult` output, so parsing it would be meaningless). Those
|
||||
* fall back to the fenced `content` block with no terminal metadata. The bridge's
|
||||
* orphan guard also drops a result terminal when the call wasn't terminal, so a
|
||||
* background call (not marked terminal in `presentBashCall`) is doubly safe.
|
||||
* A non-text result (unexpected for bash) falls through to `undefined`.
|
||||
*/
|
||||
function presentBashResult(args: unknown, result: ToolResult): ToolResultPresentation | undefined {
|
||||
const block = result.content.length === 1 ? result.content[0] : undefined
|
||||
if (block === undefined || block.type !== 'text') return undefined
|
||||
const raw = block.text
|
||||
const fenced = raw.replace(/\n+$/, '')
|
||||
const content = [{ type: 'text' as const, text: `\`\`\`console\n${fenced}\n\`\`\`` }]
|
||||
const isBackground = typeof args === 'object' && args !== null && (args as { run_in_background?: unknown }).run_in_background === true
|
||||
// No exit pill / terminal output for a background ack or an errored run.
|
||||
if (isBackground || result.isError) return { content }
|
||||
return { content, terminal: { output: raw, ...parseExitStatus(raw) } }
|
||||
}
|
||||
|
||||
/**
|
||||
* Recover the structured exit status from a rendered `renderResult` string — the
|
||||
* inverse of the status markers it appends. A `[killed by signal: SIG]` marker
|
||||
* yields `{signal}`; otherwise an `[exit code: N]` marker yields `{exitCode:N}`;
|
||||
* absent both we report `{exitCode:0}` (a clean run appends no marker — and a
|
||||
* trapped-timeout run that exits 0 also has none and is accurately exit 0).
|
||||
*
|
||||
* Why parse rendered text at all: `presentResult` is replay-safe and on a
|
||||
* `session/load` the ONLY thing persisted is this content text — the structured
|
||||
* `BashRunResult` is long gone — so unless the exit were added to the persisted
|
||||
* event schema (deliberately NOT done; see the terminal-rendering RFC), parsing
|
||||
* is the only channel. The match is anchored to a LEADING newline + end-of-string
|
||||
* because `renderResult` always inserts a `\n` before the marker (line ~124) onto
|
||||
* a non-empty body: a real marker is therefore always its own final line. That
|
||||
* defeats the common spoof (program output that simply ENDS in `[exit code: 5]`
|
||||
* with no trailing newline — a clean exit 0 — no longer reads as a failure).
|
||||
*
|
||||
* KNOWN RESIDUAL (inherent to the replay-only-sees-text design): a clean exit 0
|
||||
* whose body's FINAL line is itself exactly the marker text — `[exit code: N]`
|
||||
* or `[killed by signal: SIG]`, printed by the program with nothing after — is
|
||||
* still indistinguishable from a real marker and would show a wrong pill. This is
|
||||
* display-only (execution and the model-facing text are unaffected) and narrow;
|
||||
* the complete fix is to persist a structured exit on the result event, which the
|
||||
* RFC names as the escape hatch.
|
||||
*/
|
||||
function parseExitStatus(text: string): { exitCode: number } | { signal: string } {
|
||||
const signal = /\n\[killed by signal: ([^\]\n]+)\]$/.exec(text)
|
||||
if (signal?.[1] !== undefined) return { signal: signal[1] }
|
||||
const exit = /\n\[exit code: (\d+)\]$/.exec(text)
|
||||
if (exit?.[1] !== undefined) return { exitCode: Number(exit[1]) }
|
||||
return { exitCode: 0 }
|
||||
}
|
||||
|
||||
/** Pending-state presentation for `bash_output`/`bash_kill` (background-task tools). */
|
||||
function presentTaskCall(verb: string, args: { task_id: string }): ToolCallPresentation {
|
||||
return { title: `${verb} background task ${args.task_id}`, kind: 'execute', rawInput: args.task_id }
|
||||
}
|
||||
|
||||
/**
|
||||
* Resolve the working directory for a bash call. Precedence: an explicit model
|
||||
* `workdir` wins; otherwise default to the calling agent's session cwd
|
||||
@@ -241,6 +356,8 @@ export function apply(ctx: Context): void {
|
||||
if (result.aborted) throw new Error('command aborted')
|
||||
return [{ type: 'text', text: renderResult(result) }]
|
||||
},
|
||||
presentCall: presentBashCall,
|
||||
presentResult: presentBashResult,
|
||||
}))
|
||||
|
||||
ctx.tools.register(defineTool({
|
||||
@@ -265,6 +382,7 @@ export function apply(ctx: Context): void {
|
||||
text += `\n${statusLine(read.task)}`
|
||||
return Promise.resolve([{ type: 'text', text }])
|
||||
},
|
||||
presentCall: args => presentTaskCall('Read output from', args),
|
||||
}))
|
||||
|
||||
ctx.tools.register(defineTool({
|
||||
@@ -282,5 +400,6 @@ export function apply(ctx: Context): void {
|
||||
text: killed ? `killed background task ${id}` : `task ${id} had already finished`,
|
||||
}])
|
||||
},
|
||||
presentCall: args => presentTaskCall('Kill', args),
|
||||
}))
|
||||
}
|
||||
@@ -119,7 +119,7 @@ describe('bash tool', () => {
|
||||
})
|
||||
|
||||
// Type and required-key violations are now rejected by the harness
|
||||
// (defineTool validates against the SchemaSpec — ADR 0011) before execute.
|
||||
// (defineTool validates against the SchemaSpec — the arg-validation RFC) before execute.
|
||||
it.each([
|
||||
[{}, /missing required property "command"/],
|
||||
[{ command: 42, description: 'd' }, /"command" must be a string/],
|
||||
@@ -562,3 +562,152 @@ describe('status lines', () => {
|
||||
expect(text(read)).toContain('[status: completed, exit code: 0]')
|
||||
})
|
||||
})
|
||||
|
||||
describe('tool-owned UI presentation (presentCall / presentResult)', () => {
|
||||
it('bash presentCall: title is the command, description as a content block, marks a terminal; workdir → cwd (absolute or relative, bridge resolves)', async () => {
|
||||
const ctx = await setup()
|
||||
// No explicit workdir → the call still flags a terminal, but with no cwd (the
|
||||
// UI bridge fills the session cwd it owns; the pure presenter can't see it).
|
||||
// The command is the title (an execute card hides rawInput); the description
|
||||
// rides as a content text block (shown above the terminal card).
|
||||
expect(ctx.tools.get('bash')?.presentCall?.({ command: 'ls -la src', description: 'List files in src' }))
|
||||
.toEqual({ title: 'ls -la src', kind: 'execute', rawInput: 'ls -la src', content: [{ type: 'text', text: 'List files in src' }], terminal: {} })
|
||||
// An ABSOLUTE workdir is surfaced verbatim as the terminal cwd header.
|
||||
expect(ctx.tools.get('bash')?.presentCall?.({ command: 'pwd', description: 'Print dir', workdir: '/tmp/x' }))
|
||||
.toEqual({ title: 'pwd', kind: 'execute', rawInput: 'pwd', content: [{ type: 'text', text: 'Print dir' }], terminal: { cwd: '/tmp/x' } })
|
||||
// A RELATIVE workdir is passed through AS-IS (the bridge resolves it against
|
||||
// the session cwd, matching where execution runs) — not dropped.
|
||||
expect(ctx.tools.get('bash')?.presentCall?.({ command: 'pwd', description: 'Print dir', workdir: 'sub' }))
|
||||
.toEqual({ title: 'pwd', kind: 'execute', rawInput: 'pwd', content: [{ type: 'text', text: 'Print dir' }], terminal: { cwd: 'sub' } })
|
||||
})
|
||||
|
||||
it('bash presentResult: console-block content AND terminal.output (RAW newlines) + parsed exit code', async () => {
|
||||
const ctx = await setup()
|
||||
const present = ctx.tools.get('bash')!.presentResult!(
|
||||
{ command: 'echo hi', description: 'echo' },
|
||||
{ content: [{ type: 'text', text: 'hi\n[exit code: 0]\n\n' }], isError: false },
|
||||
)
|
||||
// The fenced ```console content trims trailing blank lines for a tidy block;
|
||||
// terminal.output keeps the RAW bytes (newlines intact) a terminal renderer
|
||||
// needs; exitCode is parsed back from the [exit code: N] marker.
|
||||
expect(present).toEqual({
|
||||
content: [{ type: 'text', text: '```console\nhi\n[exit code: 0]\n```' }],
|
||||
terminal: { output: 'hi\n[exit code: 0]\n\n', exitCode: 0 },
|
||||
})
|
||||
})
|
||||
|
||||
it('bash presentResult: a non-zero exit and a signal kill parse into exitCode / signal', async () => {
|
||||
const ctx = await setup()
|
||||
const args = { command: 'x', description: 'x' }
|
||||
const nonzero = ctx.tools.get('bash')!.presentResult!(args, { content: [{ type: 'text', text: 'oops\n[exit code: 3]' }], isError: false })
|
||||
expect(nonzero?.terminal).toEqual({ output: 'oops\n[exit code: 3]', exitCode: 3 })
|
||||
const killed = ctx.tools.get('bash')!.presentResult!(args, { content: [{ type: 'text', text: 'gone\n[killed by signal: SIGKILL]' }], isError: false })
|
||||
expect(killed?.terminal).toEqual({ output: 'gone\n[killed by signal: SIGKILL]', signal: 'SIGKILL' })
|
||||
})
|
||||
|
||||
it('bash presentResult exit parse is the inverse of renderResult markers (round-trip)', async () => {
|
||||
const ctx = await setup()
|
||||
const present = ctx.tools.get('bash')!
|
||||
// For each renderResult outcome, the rendered text fed back through
|
||||
// presentResult recovers the matching structured exit — the parse and the
|
||||
// marker emission co-evolve in one file, so this pins the pair.
|
||||
const base = {
|
||||
aborted: false,
|
||||
timeoutMs: 1000,
|
||||
stdout: { text: 'out', truncated: false },
|
||||
stderr: { text: '', truncated: false },
|
||||
}
|
||||
const cases = [
|
||||
{ result: { ...base, exitCode: 0, signal: null, timedOut: false }, expect: { exitCode: 0 } },
|
||||
{ result: { ...base, exitCode: 7, signal: null, timedOut: false }, expect: { exitCode: 7 } },
|
||||
{ result: { ...base, exitCode: null, signal: 'SIGTERM' as const, timedOut: false }, expect: { signal: 'SIGTERM' } },
|
||||
// A trapped-timeout run that exits 0 has no signal/exit marker → reads as exit 0 (it did exit 0).
|
||||
{ result: { ...base, exitCode: 0, signal: null, timedOut: true }, expect: { exitCode: 0 } },
|
||||
]
|
||||
for (const c of cases) {
|
||||
const rendered = renderResult(c.result)
|
||||
const out = present.presentResult!({ command: 'x', description: 'x' }, { content: [{ type: 'text', text: rendered }], isError: false })
|
||||
const { output: _o, ...exit } = out?.terminal ?? {}
|
||||
expect(exit).toEqual(c.expect)
|
||||
}
|
||||
})
|
||||
|
||||
it('bash presentResult: a clean exit-0 whose output ENDS in marker-like text is NOT read as a failure', async () => {
|
||||
const ctx = await setup()
|
||||
const args = { command: 'printf "[exit code: 5]"', description: 'print' }
|
||||
// A successful command can print text that looks like a marker. renderResult
|
||||
// for a clean exit 0 appends NOTHING (and no trailing newline), so the body's
|
||||
// own tail is `[exit code: 5]`. The parse requires a LEADING newline before
|
||||
// the marker (renderResult always inserts one before a REAL marker), so this
|
||||
// no-trailing-newline body is NOT mistaken for a failure → exitCode 0.
|
||||
const out = ctx.tools.get('bash')!.presentResult!(args, { content: [{ type: 'text', text: '[exit code: 5]' }], isError: false })
|
||||
expect(out?.terminal).toEqual({ output: '[exit code: 5]', exitCode: 0 })
|
||||
// Same for a fake signal marker with no leading newline.
|
||||
const sig = ctx.tools.get('bash')!.presentResult!(args, { content: [{ type: 'text', text: '[killed by signal: SIGKILL]' }], isError: false })
|
||||
expect(sig?.terminal).toEqual({ output: '[killed by signal: SIGKILL]', exitCode: 0 })
|
||||
})
|
||||
|
||||
it('bash presentCall/presentResult: a run_in_background call is NOT a terminal and its ack carries no exit pill', async () => {
|
||||
const ctx = await setup()
|
||||
// The background start returns a task-id ack, not a streamed run — no terminal.
|
||||
const call = ctx.tools.get('bash')!.presentCall!({ command: 'sleep 100', description: 'wait', run_in_background: true })
|
||||
expect(call).toEqual({ title: 'sleep 100', kind: 'execute', rawInput: 'sleep 100', content: [{ type: 'text', text: 'wait' }] })
|
||||
expect((call as { terminal?: unknown }).terminal).toBeUndefined()
|
||||
// The ack result is fenced text only — no terminal output / exit pill.
|
||||
const result = ctx.tools.get('bash')!.presentResult!(
|
||||
{ command: 'sleep 100', description: 'wait', run_in_background: true },
|
||||
{ content: [{ type: 'text', text: 'started background task bash-1' }], isError: false },
|
||||
)
|
||||
expect(result?.terminal).toBeUndefined()
|
||||
expect(result?.content).toEqual([{ type: 'text', text: '```console\nstarted background task bash-1\n```' }])
|
||||
})
|
||||
|
||||
it('bash presentResult: an isError result carries no exit pill (no real process exit to report)', async () => {
|
||||
const ctx = await setup()
|
||||
// A spawn failure / abort has no process exit — the body is an error message,
|
||||
// not renderResult output, so no terminal output/exit is emitted.
|
||||
const out = ctx.tools.get('bash')!.presentResult!(
|
||||
{ command: 'x', description: 'x' },
|
||||
{ content: [{ type: 'text', text: 'command aborted' }], isError: true },
|
||||
)
|
||||
expect(out?.terminal).toBeUndefined()
|
||||
expect(out?.content).toEqual([{ type: 'text', text: '```console\ncommand aborted\n```' }])
|
||||
})
|
||||
|
||||
it('bash presentResult: leaves a non-text (unexpected) result untouched → undefined (UI keeps raw content)', async () => {
|
||||
const ctx = await setup()
|
||||
const present = ctx.tools.get('bash')!.presentResult!(
|
||||
{ command: 'x', description: 'x' },
|
||||
{ content: [{ type: 'image', url: 'https://x/y.png' }], isError: false },
|
||||
)
|
||||
expect(present).toBeUndefined()
|
||||
})
|
||||
|
||||
it('bash presentResult: a result that is not exactly one block → undefined (no single text to fence)', async () => {
|
||||
const ctx = await setup()
|
||||
const args = { command: 'x', description: 'x' }
|
||||
// Empty content (no block) and multi-block content both fall through.
|
||||
expect(ctx.tools.get('bash')!.presentResult!(args, { content: [], isError: false })).toBeUndefined()
|
||||
expect(ctx.tools.get('bash')!.presentResult!(args, {
|
||||
content: [{ type: 'text', text: 'a' }, { type: 'text', text: 'b' }],
|
||||
isError: false,
|
||||
})).toBeUndefined()
|
||||
})
|
||||
|
||||
it('bash_output / bash_kill presentCall: a readable task-scoped title, task id as rawInput', async () => {
|
||||
const ctx = await setup()
|
||||
expect(ctx.tools.get('bash_output')!.presentCall!({ task_id: 'bash-3' }))
|
||||
.toEqual({ title: 'Read output from background task bash-3', kind: 'execute', rawInput: 'bash-3' })
|
||||
expect(ctx.tools.get('bash_kill')!.presentCall!({ task_id: 'bash-3' }))
|
||||
.toEqual({ title: 'Kill background task bash-3', kind: 'execute', rawInput: 'bash-3' })
|
||||
})
|
||||
|
||||
it('presentCall validates softly: malformed args (missing required description) return undefined, never throw', async () => {
|
||||
const ctx = await setup()
|
||||
// defineTool wraps presentCall to soft-validate against the schema and fall
|
||||
// back to undefined (a generic UI presentation) rather than throwing on the
|
||||
// display path — it may run on replay of arbitrary logged args. The
|
||||
// ToolDefinition.presentCall takes `unknown`, so a malformed shape needs no cast.
|
||||
expect(ctx.tools.get('bash')?.presentCall?.({ command: 'ls' })).toBeUndefined()
|
||||
})
|
||||
})
|
||||
Reference in New Issue
Block a user