The native adapter's route was named deepseek, colliding with pi-ai's
catalog provider of the same name, so the two DeepSeek paths could never
be mounted side by side. The web settings page needs both configurable at
once. Compositions, fixtures, goldens, scaffolding defaults, and docs all
move together (pre-release, no shim); TUI/session-query-spill/
missing-credential goldens re-recorded through their keyless refresh
modes because provider-name length shifts box padding and spill
truncation points.
An empty or omitted providers dict is now the valid dormant posture: the
adapter mounts with zero routes and no catalog entries, registers routes
the moment the llm-pi-ai settings section supplies profiles, and drops
them when it empties. The TUI demo mounts the adapter bare, so adding an
openai/anthropic provider is purely a settings.yaml (or, next PR, web
form) operation with per-request apiKeyEnv credential resolution.
openai + anthropic routes register keyless beside the direct deepseek
adapter — the catalog stays browsable and requests fail actionably until a
key arrives — with per-request apiKeyEnv resolution, so a user's settings
section (proxy baseURL, extra routes) and .env keys are the only steps to
turn them on.
Vendored @cordisjs/plugin-hmr uses decorators — non-erasable syntax the
--experimental-transform-types demo:tui launch refuses — so its row made the
shipped TUI composition unbootable from source while the tsx-launched
snapshot harness masked it. The stale !!js head comment goes with it;
restoring dev HMR is tracked separately.
New credentials data-structure page (type-equiv manifested), group README,
rewritten llm-deepseek/llm-pi-ai READMEs (dynamic configuration, dict
profiles, credential chain), capability-seams/service-role registration,
Agent Note (bilingual), demo compositions mounting settings-local +
credentials-local with no inline key plumbing, installSettingsSection
consumer helper on the settings seam (deduplicating both adapters' wiring),
jscpd symmetry markers for the provider twins, runtime-closure additions for
python/sdk-runtime, and doc-budget ceilings AGENTS.md 1750→1755 /
packages/README.md 850→865 for the structural one-line group rows.
The TUI keyless smoke exposed the wrong idle signal: /plan submitted while
the driver is between turns still saw status running (checkpointing), so
the selection queued and the immediate copy never appeared. The commit
gate is now the log's own open-turn fold — plan/mode commits at once
whenever no turn is open, and queues only inside one. Specs drive the
distinction through explicit turn/start / turn/end events instead of a
fake status; the keyless smoke pins the new idle copy on both /plan and
/plan off; regenerated cordis/service catalogs ride along.
The idle /plan and /plan off command paths pin the immediate-commit copy;
the chip's dead leaving/locked guard is deleted (both states disable the
button, so no click reaches the handler); the multi-turn TUI golden is
re-recorded keyless over the idle-commit wording and the standalone
plan/mode narration ordering.
Two CI-only test failures on the personal TUI/skills stack:
- packages/ui/tui/tests/tui.spec.ts anchored the dark-palette test at
process.cwd(), which is not guaranteed under $HOME; on CI runners the
prompt rendered an absolute path instead of the `~/` abbreviation. Anchor
cwd under homedir() so the assertion is deterministic.
- examples/tui-agent/tests/tui-keyless-smoke.e2e.ts asserted stale
dsh-customize / dsh-upgrade skill descriptions. Sync the expectations to
the bundled SKILL.md frontmatter.
Consolidates the personal dsh-tui customizations (module split into
components/session/extension, prompt template + running-glyph indicator,
copyable transcript, tool-card headers, timing placement, XML tool output,
status/footer rework) and ports upstream's model reasoning-effort selector
(Shift+Tab effort cycling, effort-aware /model, footer, and /status) onto
the personal module layout.
Implements the execa Agent Note's four sub-changes:
- execa (root devDep + loader-smoke dep) replaces the hand-rolled
spawn-collect-timeout choreography in loader-smoke, apps/cli and
cli-demo/acp-demo built-bin e2e, lsp-local and code-runtime-worker
built-lib e2e, the tui pty-harness outer collector, the jsonrpc
keyless smoke, and crash-recovery's child spawn. Genuinely custom
parts stay custom: cli-demo's interrupt-on-marker, jsonrpc's
line-predicate protocol driving, crash-recovery's SIGKILL-at-failpoint.
The two loader-smoke /* v8 ignore */ OS-error branches are gone.
- llm-mock-server CLI tokenizes via node:util parseArgs; numeric
coercion/bounds/cross-option constraints stay manual; pinned
error-message tests updated to the parseArgs texts.
- both loadRootEnv copies in apps/web/tests are deleted: the owning
vitest configs (web unconditionally, snapshot in record mode)
already load the repo-root .env before these files run.
- the four poll loops (acp-snapshot harness waits + crash-recovery
waitForFile) ride vi.waitFor with explicit {interval, timeout}.
Conflict resolution: scripts/type-equiv.manifest.json takes master's new
paired-derivative format (one primary entry per pair) and re-adds this
stack's CodeDispatchLog entry in that format. zh README pairs brought
along for the dispatch-log arm (spill-policy behavior/limitations bullets,
tools limitation bullet now pointing at the shipped bounding).
Responding to ds-review-bot round 2 on #661:
- logWork is bounded: past maxParallelSubCalls pending shaped-append tasks
the ordered commit lane holds (Promise.race drains one), so a slow spill
backend backpressures the run instead of accumulating unbounded pending
I/O and retained results. Tasks self-remove on settlement; run
settlement still drains every task inside the open turn. New spill test
drives three oversized reads against a hung backend at cap 1 and proves
the third dispatch cannot start until a save drains.
- shapeDispatchLog's catch uses errorMessage() (total), so a thrown value
with a throwing toString cannot escape the containment and lose the
settle event.
- CodeDispatchLog.content documented as the RENDERED result projection
(native tool/result vocabulary), not what the program received — the
program gets the structured value; doc pair + type-equiv re-synced.
- New RECORDED tui-agent snapshot scenario code-mode-dispatch-spill: the
real Loader-visible composition (worker runtime + spill-local + policy)
drives an oversized bash sub-call end-to-end; replay proves the durable
dispatch copy is bounded to preview + locator while the program value
stays whole (the outer result carries just the line count).
Agent Note updated (both languages).
Yichen Jiang
imccyu
Tianyi Cui
_Kerman
NI0317
Turtle