Merge remote-tracking branch 'origin/master' into worktree/pr1018-todo-retarget-20260731

# Conflicts:
#	apps/cli/README.i18n.yaml
#	packages/ui/tui/README.i18n.yaml

apps/cli/tests/fixtures/composition-echo-llm.ts

@@ -0,0 +1,51 @@
+import type { Context } from 'cordis'
+import type {
+  GenerateOptions,
+  LlmModelInfo,
+  LlmResolvedModelInfo,
+  StreamChunk,
+} from '@deepseek-ai/dsh-llm'
+import { LlmAdapter } from '@deepseek-ai/dsh-llm'
+
+/** Terminal marker the preset smoke waits for before it asks the TUI to exit. */
+export const COMPOSITION_REPLY_TEXT = 'Shipped composition acknowledged.'
+
+// Provider id and model the keyless tail routes `main` to; that overlay is the
+// only caller, so the pair lives here as plain constants.
+const COMPOSITION_PROVIDER = 'composition-keyless'
+const COMPOSITION_MODEL = 'composition-keyless-model'
+
+/**
+ * Network-free adapter for the shipped-composition smoke. It answers every
+ * request — tool-ful agent turns and the tool-less auxiliary calls alike — with
+ * one fixed text and never calls a tool, because the assertion under test is the
+ * assembled tool catalog the loop logs, not any tool's behavior.
+ */
+class CompositionEchoAdapter extends LlmAdapter {
+  override listModels(provider: string): Promise<readonly LlmModelInfo[]> {
+    return Promise.resolve([{ provider, id: COMPOSITION_MODEL, name: 'Preset Keyless' }])
+  }
+
+  override resolveModel(provider: string, model: string): Promise<LlmResolvedModelInfo> {
+    return Promise.resolve({ provider, id: model, name: 'Preset Keyless', context: { contextWindow: 128_000 } })
+  }
+
+  override async * stream(_options: GenerateOptions): AsyncIterable<StreamChunk> {
+    yield { type: 'block-start', index: 0, blockType: 'text' }
+    for (const char of COMPOSITION_REPLY_TEXT) yield { type: 'text-delta', index: 0, text: char }
+    yield { type: 'block-end', index: 0, block: { type: 'text', text: COMPOSITION_REPLY_TEXT } }
+    yield { type: 'usage', usage: { inputTokens: 20, outputTokens: COMPOSITION_REPLY_TEXT.length } }
+    yield { type: 'finish', reason: { kind: 'stop' } }
+  }
+}
+
+export const name = 'composition-echo-llm'
+export const inject = ['llm']
+
+/**
+ * Register the network-free adapter the shipped-composition smoke routes through.
+ * @param ctx - the loader-mounted plugin context.
+ */
+export function apply(ctx: Context): void {
+  ctx.llm.registerAdapter([COMPOSITION_PROVIDER], new CompositionEchoAdapter())
+}

apps/cli/tests/fixtures/composition-keyless-tail.cordis.yml

@@ -0,0 +1,52 @@
+# Keyless tail for the shipped-composition smoke, applied as `--config` so the
+# launcher boots `base.cordis.yml` + `tui.cordis.yml` and then this file.
+#
+# Everything below is test isolation, never composition under test: the model is
+# replaced so no request leaves the process, the settle marker gates the smoke's
+# first prompt, and the session artifacts move into the smoke's temporary
+# workspace so the log inspection can read them.
+
+# A patch's `name` is an assertion rather than a replacement, so the base
+# adapter row is disabled and the scripted one inserted. Relative specifiers
+# resolve against the INCLUDED file's directory (apps/cli/config), not this
+# file's, because the include moves baseUrl there.
+- id: llm-deepseek
+  disabled: true
+
+- insert:
+    - id: composition-echo-llm
+      name: '../tests/fixtures/composition-echo-llm.ts'
+    - id: composition-settled
+      name: '../tests/fixtures/composition-settled.ts'
+
+- id: agent-loop
+  config:
+    agents:
+      - id: main
+        provider: composition-keyless
+        model: composition-keyless-model
+        cwd: !!js process.cwd()
+
+- id: session-persistence-jsonl
+  config:
+    root: './.sessions'
+    compression: none
+
+- id: session-query-sqlite
+  config:
+    path: './.sessions/session-query.db'
+
+# The title call is a second, tool-less request that would race the log
+# inspection for no coverage: the catalog under test rides the agent turn.
+- id: session-title-llm
+  disabled: true
+
+- id: tui
+  config:
+    sessionId: !!js configuredAgentIdentities?.main?.id ?? 'main'
+    welcome: 'composition smoke ready.'
+    showReasoning: true
+
+# HMR watches the repository; a PTY subprocess test must not start a watcher.
+- id: hmr
+  disabled: true

apps/cli/tests/fixtures/composition-settled.ts

@@ -0,0 +1,24 @@
+import type { Context } from 'cordis'
+
+/**
+ * Marker the shipped-composition smoke gates its first prompt on. The TUI renders as soon as
+ * its own fiber starts, so a prompt typed at the banner can reach the loop while
+ * later rows — tool plugins, persistence — are still activating, and would
+ * assemble a partial catalog. Waiting for this line makes the turn observe the
+ * settled tree.
+ */
+export const COMPOSITION_SETTLED_MARKER = 'COMPOSITION_TREE_SETTLED'
+
+export const name = 'composition-settled'
+
+/**
+ * Announce settled Loader activation on the terminal byte stream, after every
+ * entry in the booted tree has started. The write is detached: awaiting the
+ * Loader from inside an entry would wait on this entry's own activation.
+ * @param ctx - the loader-mounted plugin context.
+ */
+export function apply(ctx: Context): void {
+  void ctx.loader.await().then(() => {
+    process.stdout.write(`\n${COMPOSITION_SETTLED_MARKER}\n`)
+  })
+}

apps/cli/tests/shipped-composition.e2e.ts

@@ -0,0 +1,124 @@
+import { readdir, readFile } from 'node:fs/promises'
+import { fileURLToPath } from 'node:url'
+import { join } from 'node:path'
+import { describe, expect, it } from 'vitest'
+import { LOADER_SMOKE_TEST_TIMEOUT_MS } from '@deepseek-ai/dsh-loader-smoke'
+import type { SessionEvent } from '@deepseek-ai/dsh-session'
+import { COMPOSITION_REPLY_TEXT } from './fixtures/composition-echo-llm.ts'
+import { COMPOSITION_SETTLED_MARKER } from './fixtures/composition-settled.ts'
+import { runTuiPtySmoke } from './pty-harness.ts'
+
+const dshBinScript = fileURLToPath(new URL('../src/bin.ts', import.meta.url))
+const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
+// An overlay over the shipped tree, so the catalog under test is the one
+// `base.cordis.yml` + `tui.cordis.yml` assemble; the tail only swaps the model
+// and redirects session artifacts.
+const keylessTail = fileURLToPath(new URL('./fixtures/composition-keyless-tail.cordis.yml', import.meta.url))
+
+/**
+ * The catalog the shipped `dsh` TUI puts in front of the model, as the loop
+ * logged it, minus the ripgrep-dependent pair below.
+ * The absences are the composition's security decisions, not incidental gaps:
+ * the `cordis_*` toolset executes model-written JavaScript that no sandbox row
+ * confines, `web_fetch` chooses its own request target, and `mcp_*` servers
+ * spawn outside `ctx.bash`. The composition Agent Note owns the rationale and
+ * its sources.
+ */
+const EXPECTED_TUI_TOOLS = [
+  'ask_user_question',
+  'bash',
+  'create_goal',
+  'edit',
+  'exit_plan_mode',
+  'get_goal',
+  'ralph',
+  'read',
+  'session_event_read',
+  'session_event_search',
+  'session_event_trace',
+  'session_search',
+  'session_trace',
+  'skill',
+  'str_replace_editor',
+  'subagent',
+  'subagent_fork',
+  'task_kill',
+  'task_list',
+  'task_output',
+  'todo_write',
+  'update_goal',
+  'web_search',
+  'workflow',
+  'write',
+]
+
+/**
+ * `glob` and `grep` come from `dsh-tool-fs-search`, which probes `command -v rg`
+ * through the mounted bash executor at load and registers neither tool when
+ * ripgrep is absent. That is a host dependency, not a composition decision, so the
+ * pair is asserted separately — present together or absent together.
+ */
+const RIPGREP_TOOLS = ['glob', 'grep']
+
+/** The assembled request header the smoke asserts on. */
+interface LoggedHeader {
+  /** Assembled tool names, sorted. */
+  names: string[]
+  /** `bash`'s assembled parameter properties; the escalation pair is present only under a confining executor. */
+  bashArguments: Record<string, unknown>
+}
+
+/**
+ * Read the request header the loop assembled for its first request from the
+ * session log the smoke's workspace persisted — the model-visible composition
+ * itself, not a registry projection taken beside it.
+ * @param cwd - the smoke's temporary workspace.
+ * @returns the assembled catalog, system prompt, and `bash` argument shape.
+ */
+async function loggedHeader(cwd: string): Promise<LoggedHeader> {
+  const sessionsDir = join(cwd, '.sessions')
+  const entries = await readdir(sessionsDir, { recursive: true })
+  // A single keyless run writes one session log.
+  const logRelPath = entries.find(name => name.endsWith('.jsonl'))
+  if (logRelPath === undefined) throw new Error(`no session log written under ${sessionsDir}`)
+  const lines = (await readFile(join(sessionsDir, logRelPath), 'utf8')).split('\n').filter(Boolean)
+  for (const line of lines) {
+    const event = JSON.parse(line) as SessionEvent
+    if (event.type !== 'request/header') continue
+    const tools = event.data.header.tools ?? []
+    const bash = tools.find(schema => schema.name === 'bash')
+    return {
+      names: tools.map(schema => schema.name).sort(),
+      bashArguments: (bash?.parameters as { properties?: Record<string, unknown> } | undefined)?.properties ?? {},
+    }
+  }
+  throw new Error(`session log ${logRelPath} has no request/header event`)
+}
+
+describe('shipped dsh composition (real Loader tree in a PTY)', () => {
+  it('assembles exactly the shipped TUI catalog', async () => {
+    let observed: LoggedHeader | undefined
+    const output = await runTuiPtySmoke({
+      label: 'dsh shipped composition',
+      tempDirPrefix: 'dsh-shipped-tui-',
+      binScript: dshBinScript,
+      tsconfigPath,
+      configPath: keylessTail,
+      env: { DEEPSEEK_API_KEY: 'keyless-composition-no-call', DSH_TELEMETRY_DISABLED: '1' },
+      // Artifact CI builds and smokes concurrently on a contended runner.
+      ...(process.env.DSH_EXAMPLE_MODE === 'lib' ? { timeoutMs: 60_000 } : {}),
+      actions: [
+        { waitFor: COMPOSITION_SETTLED_MARKER, send: 'Describe the shipped composition.\r' },
+        { waitFor: COMPOSITION_REPLY_TEXT, send: '/exit\r' },
+      ],
+      inspect: async (cwd) => { observed = await loggedHeader(cwd) },
+    })
+    expect(output).toContain(COMPOSITION_REPLY_TEXT)
+    expect(observed?.names.filter(name => !RIPGREP_TOOLS.includes(name))).toEqual(EXPECTED_TUI_TOOLS)
+    expect([[], RIPGREP_TOOLS]).toContainEqual(observed?.names.filter(name => RIPGREP_TOOLS.includes(name)))
+    // The TUI mounts the unrestricted local executors, so `tool-bash` emits no
+    // escalation pair. Pinning its absence keeps a later sandbox change from
+    // arriving here unannounced.
+    expect(Object.keys(observed?.bashArguments ?? {})).not.toContain('sandbox_permissions')
+  }, LOADER_SMOKE_TEST_TIMEOUT_MS)
+})

apps/cli/tests/tui.snapshot.ts

@@ -362,7 +362,8 @@ interface ScenarioResult {
 }
 
 async function runScenario(scenario: Scenario): Promise<ScenarioResult> {
-  const clock = vi.spyOn(Date, 'now').mockReturnValue(new Date(2026, 6, 21, 12, 0, 0).getTime())
+  const snapshotTime = new Date(2026, 6, 21, 12, 0, 0).getTime()
+  const clock = vi.spyOn(Date, 'now').mockReturnValue(snapshotTime)
   const fixtureFile = join(fixtureDir(scenario), 'session.jsonl')
   const childFiles = childFixturePaths(scenario)
   const prompts = userPrompts(await readFile(fixtureFile, 'utf8'))
@@ -543,6 +544,13 @@ async function runScenario(scenario: Scenario): Promise<ScenarioResult> {
         `manual summary did not start; status=${agent.status}; tail=${
           agent.session.events.slice(-8).map(event => event.type).join(',')
         }`)
+      clock.mockReturnValue(snapshotTime + 1_000)
+      await settleTerminal(terminal)
+      await expect.poll(() => terminal.snapshot()).toContain('dsh ⊙')
+      await expect.poll(() => terminal.snapshot()).toContain('Context being compacted 1.0s')
+      const liveCompaction = await terminal.snapshot()
+      expect(liveCompaction.indexOf('Context being compacted 1.0s')).toBeLessThan(liveCompaction.indexOf('dsh ⊙'))
+      clock.mockReturnValue(snapshotTime)
 
       // Real keystrokes: the prompt keeps its ordinary queue identity while
       // admission is reserved, and an injection appends immediately.