tool-bash-persistent overwrote the backend's PS1, so terminal-bash prompt
readiness never matched and every send degraded to the 3.5s silence tier
(idleSilenceMs + handoffGraceMs) under production defaults.
The controlled PROMPT_COMMAND now re-asserts PS1 before every prompt, so an
in-shell override never survives to the next prompt. The tool initializes
with stty -echo alone and detects the no-end-marker fallback through the
seam's stdin_read wait reason instead of matching its own prompt text.
Tool calls drop from 7180/3560/3566 ms to 355/88/91 ms (spawn+init+echo,
echo, pwd; darwin, production defaults). The loader composition suite now
pins the fast path by pushing idleSilenceMs beyond the send bound, and a
real-PTY case proves PS1 self-healing.
Fixes#2585
pi-ai resolves an OAuth provider from a stored OAuth credential alone, and
this adapter builds its Models collection with no credential store and runs
no login flow. `openai-codex` — the one installed provider declaring
`auth.oauth` with no `auth.apiKey` — was therefore offered on the Models page
with the keyless placeholder every pi-ai route carries, and every request on
it failed `Provider is not configured` before going out.
`catalogProviderTakesApiKey()` answers whether pi-ai's installed provider for
a route declares the one method this adapter can supply, and the directory
skips the catalog routes that fail it. Catalog membership is unchanged, so
`declared` still answers what pi-ai ships; the profile half of the union stays
unconditional, so a route a settings document already names keeps its entry
and can be edited or deleted.
Resolution is untouched: a profile naming `apiKeyEnv` on such a route still
builds a working provider.
- Rewrite the 08-04 gutter-reservation note in place: the reservation is Chat's alone and the overlay branch points to the seat-width compensation note; the Testing section now describes the uncompensated control.
- Cross-reference the earlier rejection of the seat inset in the 08-12 note and record the engine-resolved-vs-fixed-8px drift as accepted residual cost instead of asserting Firefox resolves 8px.
- Pair --dsh-scrollbar-width with the mirrored ::-webkit-scrollbar rule and the compensation consumer in the scrollbar-styles gate; document the variable in the ui-theme README.
- Rename the e2e control to compareTabsWithoutCompensation and correct the vacuity-guard comment; rewrap the WorkspaceBrowser doc comment.
The web E2E seed lane for the pwsh terminal card failed on every platform
with `duplicate loader entry id: tool-pwsh`. The overlay inserted a new
tool-pwsh row, but the base bundle has declared that id since the shell
platform layer moved into it, so the overlay's insert delivered a second
row with the same id and the loader rejected the pair at boot.
Enable the existing tool-pwsh row by id instead of inserting it, and
disable pwsh-sandbox so the inserted pwsh-local is the lone executor on
every platform (the base gates pwsh-sandbox on win32, which would
otherwise collide with the inserted executor there).
- stateVersion starts at 1: the package is new, no persisted rows predate it
- pendingCalls pairs by own key so a provider callId naming a prototype
property cannot fold toolMs to NaN on an unmatched crash-recovery result
- StatsLine folds the window fallback only when no sessionStats value is
served, and gates the token group on actual token activity instead of
steps, so failed-only sessions drop the zero-token group
- correct the crash-step counting semantics in the README and Agent Note:
recovery closes interrupted steps with a synthetic step/end on reload
- reword the window-scoped alternative as a plain rejected option and name
isTokenDelta's home beside the StreamChunk type
A turn the provider ends at its per-request output cap previously produced
no visible sign in the Web chat flow: only error-kind turn/end events built
a conversation node, so the truncated answer read as a normal completion.
Add a turn-max-tokens conversation node Definition over the durable
turn/end event, a warning-styled localized notice row distinct from
turn-error, a fixture max-tokens sample turn, and an assembled keyless
snapshot pinning the dot state, title, and hint.
Closes#1522
The step and the Models page both asked one question of a join that
describes every provider: is deepseek-official's credential stored? A user
who configured some other route was taken over on every blank session, and
the DeepSeek setup card opened over them on every visit to Models with a
Cancel that could not close it — while clearing the add card's draft,
because it shared the row-editor close handler.
providerUsable(row) now answers what both surfaces need: the route is
registered and whatever credential its profile names is stored. Readiness
(renamed onboardingReadiness) ends on any usable row, needsSetup takes the
same fact, and each card kind owns its own close handler.
Fixes#2325
Overlaps master on the preset e2e, the web scaffold, and the generated
config-catalog triplet; all merged textually, so the catalog is regenerated and
its pairing hashes re-recorded rather than trusted.
Adding COLLAPSE_SECTION_ORDER and CODE_ONLY_INSTRUCTION shifted every
later line in packages/core/tools/src/index.ts by 14, and three generated
artifacts cite those lines: the subsystems cordis-surface region, the
event producer/consumer matrix, and the Agent Note pair record left
inconsistent by the cherry-pick resolution.
The executor collapse landed without telling the model it exists. Every
tool contributes its own guidance section naming its tool, none of them
qualify how that tool is reached, and they all render before the SDK
(orders 100-199 against SDK_SECTION_ORDER 150), so the prompt said "Use
the read tool" eleven times and never said only run_code is callable.
A real session shows the consequence: the model emitted a native call,
read `unknown tool "read"` for a tool the same prompt declares, and
concluded the deployment was inconsistent rather than routing through
run_code.
The registry now contributes `tools:code-only` at order 99 -- ahead of
the guidance band -- stating the rule, registered wherever `tools:sdk`
is and rendering empty outside an effective `code`. `both` renders it
empty because its native calls do execute, which is also why
both-mode-turn no longer shares code-mode-turn's expected prompt. The
denial itself now names the route back, since a bare UNKNOWN_TOOL for a
declared tool is what misled the model.
wireSchemas() already advertised only run_code under mode: 'code', but the
executor resolved every call through get(), which returns the full visible
map plus the reserved transport. A model could name a native tool directly
and bypass run_code entirely. Route the execution-path lookups through a
new private resolveExecution() that applies the mode collapse at the
operation boundary: model-direct calls under 'code' may only name run_code
(UNKNOWN_TOOL otherwise), while SDK sub-dispatches (parent token set) keep
every visible tool. get()/schemas() public semantics are unchanged.
The denial happens at createExecution, before the extensible policy
pipeline — pre-execute listeners, approval ask, and guards never observe
a call that is deterministically denied. A collapsed call honors the
pre-dispatch cancellation contract, routes aborted results through the
visible tool's finalizeContent, and captures the finalizer before
argument materialization.
Under code mode, a system-prompt/assemble listener filters out tool:*
guidance sections that told the model to call native tools directly.
The tools:sdk section and SDK types remain so programs can still use
all tools through run_code.
Fixes#1815
The service moved its "is a roster composed" reads to the derived root set;
the invariant companion still read `config.roots`. In the shape this change
exists for — an app configures nothing and the roster is the harness home
alone — that made the advisory warning fire while the fail-loud invariant
stayed silent, so an agent could address a model against an empty global
layer unchecked.
Both now read one source: `roots` exposes the resolved set, and the invariant
asks it. That decides the behavior deliberately rather than by omission — a
composition that mounts the roster now fails an unjoined agent whether its
roots were configured or derived, and `includeUserRoot: false` with no
configured roots is how a deployment keeps its agents on the host plane. Both
shapes are pinned; the derived-only case fails against the old predicate.
Three pieces of prose went stale with the first commit: the web-app bundle
comment still called the writable root an assembly fact patched in by
AppCLIEntry (removed in the profile-plugin-bundles refactor — `composeProfile`
owns it now, and only for the shipped root), and the shipped skill and its
Agent Note still called both roots "configuration". The README gains the
resolved-roster reader and the discoverable-but-undeletable preset a second
writable root produces.
`Config.roots` defaulted to `[]`, so a deployment that did not patch both roots
in got a roster with none — `dsh run` once booted exactly that and failed
resolving `standard`. The user root never needed an app: `<dshHome>/.agent-presets`
is the same place in every deployment, resolvable here the way
`dsh-skill-local` resolves `<dshHome>/skills`.
The roster now derives that root itself unless `includeUserRoot` is false, and
`apps/cli` supplies only the SHIPPED root, whose path an installed app alone
can resolve. The derived root is appended after every configured root, so a
shipped id still shadows a home directory claiming it and `writableRoot()`
still prefers an explicitly configured `user` root; the set is resolved once at
construction, because a root set that changed between a `list()` and the
`copy()` acting on its answer would author into a directory the caller never
saw.
Every test that pins an exact roster now says `includeUserRoot: false` — the
machine's real harness home must not decide what a golden or an assertion
counts.
