The transport schema requires both `code` and `description`, but the tool
description and both SDK instruction flavors described the call as passing a
program. `description` was reachable only through the parameter schema, so a
model following the prose emitted `{code}` alone and lost the whole written
program to an INVALID_ARGS rejection.
The length and format guidance stays in RUN_CODE_DESCRIPTION_PARAM_DESCRIPTION
alone, so the schema and the prompt cannot drift.
Fixes#2426
`collapses()` read `defaultMode`, so the collapse only applied when the
DEPLOYMENT was `code`. An agent handed `code` by an agent preset under a
native default announced `[run_code]` on the wire and still executed a
model-direct native call -- the bypass this collapse exists to close,
reopened for exactly the composition `dsh-agent-tool-mode` produces.
`modeFor(scope)` is the same resolution `wireSchemas` and the SDK section
already use, so presentation and execution cannot disagree, and a mode
inherited from a standing preset scope collapses like a declared one.
The per-agent and preset tests asserted only the wire, which is why the
regression passed them. They now assert through the executor: the body
never runs, the call resolves UNKNOWN_TOOL, and the native sibling beside
it still executes.
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.
Regenerated docs, catalogs, graphs, scoped events, re-recorded
translation pairs, and updated test assertions.
Fixes#1815
LegGasai noted that filtering prompt sections by tool:* prefix is a poor
heuristic: it conflates section naming convention with presentation
semantics and would incorrectly drop tool:structured_output. The executor
collapse already enforces the boundary — a model-direct native call is
rejected as UNKNOWN_TOOL regardless of what the prompt says, so filtering
the prompt adds no security and only risks losing useful guidance.
The tool:read/tool:bash/etc sections describe capability usage patterns
that apply to both native and code presentations, and keeping them does
not reopen the native direct-call path because the executor blocks it.
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.
Regenerated docs, catalogs, graphs, scoped events, and re-recorded
translation pairs.
Fixes#1815
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 vendored Cordis rescope (`cordis` -> `@deepseek-ai/cordis`,
`@cordisjs/plugin-*` -> `@deepseek-ai/cordis-plugin-*`) collided with this
branch's two added edges. Resolved by taking master's package names and
keeping this branch's additions: `@deepseek-ai/dsh-agent` and
`@deepseek-ai/dsh-system-prompt` peers, the `scopeChainOf` import, and the
`agent/created` type-only edge.
`docs/event-producer-consumer.*` is generated; regenerated after the merge
rather than hand-resolved.
Moving the agent plane behind presets left two readers on the wrong side of
the host/agent line.
`dsh-token-meter` was disabled on the host and mounted inside each preset's
`compaction` realm, but its three projection units register into the
process-wide `sessionProjections` table. A unit registered from one preset
answers for every session, so whether a `minimal` session showed a context
meter depended on whether some other session had mounted `standard` since
boot, and a process that only ever ran `minimal` showed none. The meter takes
no configuration, keys every fold by Session, and registers no tool or prompt
section, so it returns to the host composition and leaves the presets'
`isolate` map; the realm and `compact-basic` stay, because what a preset
chooses is whether its agent compacts, not whether its tokens are counted.
Nothing named an agent that joined no preset. The join is a scope-parent link,
and without it the tools, prompt-section, and skill views resolve the empty
global layer: the agent publishes, the turn runs, and the model receives
nothing. `AgentPresets` now logs one warning per such agent while a roster is
configured, and the invariant companion fails outright — at
`system-prompt/assemble` rather than at publication, because an unjoined agent
is legal until it addresses a model and `recompose` binds exactly such an
agent. The warning stays advisory: a synchronous `agent/created` throw vetoes
publication, and the ACP bridge, SDK server, and headless bundle all create an
unjoined agent today.
Three limits are recorded rather than fixed: projection key presence is not a
per-session capability signal, a superseded standing generation is never
reclaimed, and a `cordis_mount` temporary plugin belongs to the composition
rather than the session that mounted it.
Fixes#2203
Machine-produced by `pnpm run rescope-vendor --apply` plus the regeneration it
prints: `pnpm install` for the lockfile, `pnpm run gen-third-party-notices`,
`verify-translation-pairing --write` for the touched bilingual pairs,
`gen-doc-graphs`, and one typert snapshot whose ids embed character offsets.
`pnpm run rescope-vendor --check` verifies the result.
Renames nine vendored packages (cordis, cosmokit, schemastery and the six
@cordisjs plugins) and every reference that resolves them: manifest names and
dependency keys, module specifiers including declare-module merges, cordis.yml
plugin names, tsconfig paths, every Markdown fence, and `docs/` prose.
Directory names, upstream versions, and dependency ranges are unchanged, so
vendor/README.md still reads as an upstream snapshot; its manifest table gains
an upstream-name column so THIRD_PARTY_NOTICES keeps MIT attribution pointed
at each fork's origin.
The tutorial tier follows the rename end to end: its yaml fences named plugins
the Loader can no longer resolve, its `ts ignore-check` fences disagreed with
the compiled fences beside them, and its prose quoted both. The contracts that
told readers to keep upstream names — the root convention and the vendoring
cookbook's tree comment and manifest invariant — now say to rescope instead.
Two rules read `@deepseek-ai/` as "another workspace plugin": the client bundle
purity gate now names the vendored libraries a browser bundle inlines, and the
files where a bare `cordis` is an agent-preset id keep that product data.
A restriction was compiled against the global tool layer alone: only
global-layer tools were tested against `admits()`, and every chain-layer
tool was overlaid unfiltered afterward. That read the exempt set as "the
global layer" when what it means is "what this scope registers itself" —
two descriptions of the same set only while every model-facing tool sat in
the host composition.
Moving those rows onto the agent plane separated them. A preset's tools are
an ANCESTOR contribution to a joined agent, so a subagent's `toolFilter`
stopped constraining anything it was given; and with the global layer empty
`restrict()` rejected every name it received as unknown, failing the child
outright. With the same tools in the global layer the filter still admits
and applies normally, which is what makes this a regression of the move
rather than a standing limitation.
`view()` now filters everything a scope inherits — the global layer and
every ancestor layer on its chain — and exempts only the layer the scope
owns. That exemption is load-bearing rather than incidental: the delegation
runtime registers a child's `report` and structured-output tools into the
child's own layer, and a filter naming the capabilities the child may use
must not strip the machinery it answers through. Tool order, and with it
prefix-cache reuse, is unchanged: inherited names keep their global-then-
ancestor position and own-layer names still come last.
The diagnostic said "unknown global tool" while listing what is really the
inherited surface; it now names the surface it checks and says why an
own-layer name is not restrictable.
Fixes#2185
Purge the residual task/phase ordinals review caught ((T2), (queue cut 1)
×3, T6, P-I, 'this cut' ×6 including battery-expansion finds in two
untouched notes and a workflow JSDoc); drop the 'externally logged as
Decision 21' parenthetical and rename the remaining bare decision-21
mentions; mark the gui-layering IPC bridge row as a hypothetical example;
restore the GATE_NOTICE doc-typecheck clause and the py-types 'measured'
provenance; say subprocess-backed in filesystem.md; add the picker note
path. Amend the citations note: merged-PR evidence anchors in Agent Notes
are sanctioned, and the candidate gate patterns gain the four shapes the
sweep missed. All nine touched pairs re-recorded.
Delete design-session citations (decision/audit/plan ordinals, stack
positions), change narration, review choreography, and reviewer-addressed
justification from comments, JSDoc, docs, READMEs, Agent Notes, tests, and
generator templates; restate every affected fact as current-state contract
prose. Fix generated docs at their sources and regenerate the catalogs and
cordis-surface regions; re-paste type-equiv blocks; update every bilingual
counterpart and re-record the pairs. Record the citation rule in the
committed-artifact-citations Agent Note.
The folder is becoming the home of one-doc-per-subsystem pages (intro +
data structures + cordis services/events), so the name must describe the
whole contract, not just the type-vocabulary third of it. Mechanical
rename rebuilt on current master: every inbound Markdown link, generator
constant, website route, type-equiv manifest path, and spec expectation
moves together; the zh sides of the notes whose prose names the folder
are aligned (子系统) in the same change; touched bilingual pairs
re-recorded; translation-prompt snapshot re-recorded (its example embeds
development.md). Historical Agent Note slugs keep their dated
filenames.
modeFor read only the exact scope's layer, so a `code`-preset session
advertised the native catalog: the mode is declared on the preset's STANDING
scope, and the agent only parents to it. Nearest scope wins along the chain —
the mode decides what the model SEES, which is the class of fact the chain
inherits. Caught live (the model politely computed with bash and said
run_code was not in its list); the chain test pins it.
The client half of the label fix: the create echo and the session-added
frame's agentPreset now reach the session list (newest wins in the upsert —
every producer of the field reports the CURRENT composition), and a confirmed
blank-session switch publishes through the new ISessions.noteAgentPreset, so
the header label moves with the composition instead of waiting for a reload.
Authoring meets standing mounts: write() and remove() drop the standing
pointer so the NEXT session composes the edited roster, while every session
already joined keeps the generation it runs on — a superseded generation is
never disposed while the process lives. The settings-dialog golden re-records
with this layer's Agent Preset nav entry, which the incoming layer-3 record
had overwritten.
A preset is now ONE composition per process, not one per session. The roster
mounts it once under a synthetic standing scope; each agent joins by having
its scope key parented to the mount's. Two mechanisms in dsh-scope carry the
whole change: registration views walk the parent chain (global → preset →
agent, nearest shadowing farthest — ScopedLayers.chainLayers), and scoped
event dispatch admits a listener tagged with an ancestor of the carrier key,
which is what lets a standing composition's plan/compaction/token listeners
observe each agent composed under it while a sibling preset's stay deaf.
The preset plugins already key their state by Session/Agent — they predate
presets and were written for the shared world — so sharing one instance is a
return to their design, not a rewrite. Preset ymls are unchanged: one mount
per preset means one Entry per preset, whose entry-local realms keep two
presets' services apart exactly as they kept two sessions' apart before.
The standing scope hangs off the service's UNTRACED context (selfCtx): a
method invoked through the traceable proxy sees this.ctx rebound to the
caller and carrying its shadow, and a subtree minted from that resolves every
service through the shadow's fiber instead of each entry's own inject store —
preset rows then fail on the very services they declare.
A standing mount survives its agents deliberately. The composition a running
session joined must outlive the file changing or disappearing underneath it;
reclamation happens at whole-tree teardown, and file edits reach only future
generations (the authoring layer swaps the pointer, never disposes a joined
generation).
Code Mode was a deployment-wide field on the host `tools` row: a
deployment ran every session that way or none. The obvious product
shape — 代码模式 beside 标准/极简/创造 in the preset picker — had
nothing to hang on.
The registry itself cannot move into a preset; the agent loop's
scheduler, the api-proxy's presenters, and every tool plugin are its
consumers. So split the registry from its projection: `presentAs(mode)`
writes one cell on the calling agent's scope layer, exactly as
`restrict()` does, and the three reads that decided presentation take
that scope's mode instead of the service's. The config `mode` becomes
the default agents shadow rather than a process-wide fact.
Two consequences are load-bearing. `run_code` now enters a view only
for scopes whose own mode presents it — a native agent must not find it
dispatchable because another agent in the process does — and the
reserved name holds whatever the configured mode, since any agent may
select a code mode later.
`dsh-agent-tool-mode` is the row a preset carries to declare this. A
code mode waits for the host's `codeRuntime` rather than assuming it,
so a runtime-less deployment fails the preset at mount, naming the
row, instead of at the session's first request.
The shipped `code` preset is `standard` plus that row, ordered second.
The docstring names ZWNJ/ZWJ as a skew instance but nothing checked the
predicate's tail-position accept branch; this is its first test, and it
also covers camelCase's Tool-prefix branch for a head that is
XID_Continue but not XID_Start.
The equivalence sentence pinned its evidence to Node 22.23.1 against
CPython 3.9.6 without saying the samples sit inside those two versions'
shared tables, next to five named characters where that same pair
diverges.
The 'adding a language is two table entries plus its renderer' checklist
predates the `CodeSdkLanguage` union and now contradicts the mechanism
sentence beside it: following it literally leaves the union untouched, which
is exactly the excess-property error that sentence promises. It is three
parallel edits, in the note's Decision and Consequences and in the
`SDK_RENDERERS` JSDoc.
Two guard descriptions still claimed work the compiler took over. The
Decision's 'the drift this guards against' now names the `satisfies` pins and
leaves the guards their reachable case, a mounted runtime reporting a language
neither table knows; `resolveFlavor`'s JSDoc drops 'keeps the table coupled to
SDK_RENDERERS' for the same reason. The Consequences said a half-added
language 'cannot arise' for the runtime guards — it can, one PR later at the
consumer's integration point, and never on this base; the claim is now about
timing rather than impossibility.
`SDK_RENDERERS` and `RUN_CODE_FLAVORS` had to stay in step by review alone:
the `Object.hasOwn` guards catch drift only once a runtime reporting the
half-added language exists, which is the one case that cannot arise. Both
tables are now `satisfies`-checked against a shared `CodeSdkLanguage` union,
so a missing or extra entry fails `typecheck`. The declared `Record<string, …>`
type stays, since `CodeRuntime.language` is an unconstrained `string`.
The code-runtime seam's own README row and `CodeRuntime.language` JSDoc still
named `'typescript'` as the sole well-known value; both now name `'python'`
too and say only `'typescript'` has a published backend.
The previous commit's `UNPRINTABLE` sentence said the raw-reach point for all
three characters is `pyScalar`'s `JSON.stringify`, and the test comment said
that route is the only one. Both are exclusive claims and both are false: the
subscript tool-name comment calls `JSON.stringify` itself, and a tool name
carrying NEL, LS, or PS always lands there, none of the three being
`XID_Continue`. `pyScalar`'s own docstring already recorded that inheritance,
so the file contradicted itself. Both sentences now name the two call sites.
The note's evaluation axis was introduced as "the `typing` names the block
spells", which excludes one of its own members (`A | B` is operator syntax)
and omitted PEP 585 builtin generics — `dict[str, Any]` and `list[…]` appear
in nearly every render and need 3.9. The axis is now "the names and syntax the
block would evaluate at definition time", enumerated 3.8 through 3.11.
The test title covered two of the three characters it asserts; NEL is NEXT
LINE, neither a line nor a paragraph separator.
Four non-blocking review suggestions, all prose plus one assertion.
`UNPRINTABLE`'s new sentence named three characters but only two raw-reach
points, leaving "and NEL?" open; it now says all three reach text through
`pyScalar`, and how the description path handles each. `pyScalar`'s
raw-pass-through list already covered NEL under "the C1 controls", and the
test now pins it alongside LS and PS, so the docstring's claim has a
mechanical check for every character it names.
The test title said "paragraph separators" for a pair whose first member is
LINE SEPARATOR. Two docstring paragraphs are reflowed to the file's ~80
columns after the earlier inserts left short lines.
The note's CPython-floor obligation gains a second axis: the `typing` names
the block spells (`TypedDict` 3.8, `NotRequired` 3.11, `A | B` annotations
3.10) are definition-time evaluation floors, not parse floors, so the floor PR
does not read "parseable on the supported range" as "executable on it".
Review read `JSON.stringify`'s raw pass-through of U+0085/U+2028/U+2029 as a
parse hazard: an LS in a `Literal[...]` value or in a `# tools["..."]` comment
would end the physical line and take the SDK block down. Measured on CPython
3.9.6 (Unicode 13.0) and 3.12.13 (15.0): all three are accepted in both a
string literal and a `#` comment, value round-tripping, and only LF and CR
terminate either. The set is the tokenizer's, not `str.splitlines()`'.
Both existing claims were accurate, so nothing changes behaviorally. Name the
distinction where it was assumed: `UNPRINTABLE`'s terminator sentence now says
which set it means, and `pyScalar`'s raw-pass-through list, previously "DEL and
the C1 controls", now also names LS/PS, which are neither. A test pins the raw
form for `const` and `enum` so escaping them later cannot land as a silent
divergence from the TypeScript flavor.
Yichen Jiang
Tianyi Cui
Chinesezjc
Turtle
imccyu