The previous pass over-corrected: presenting both roots as unknowable made the
guidance vaguer without making it truer. Every `dsh` launcher puts authored
presets under `$DSH_HOME/.agent-presets`, so the skill and persona state that
as the answer to "where do my presets live" and reserve the read-back for the
path an agent actually opens or edits, which `copy()` already reports.
Neither root is a property of the preset layer. `Config.roots` defaults to `[]`;
the two the shipped agent sees are patched in by the dsh CLI, whose user root is
`dshHomePath('.agent-presets')` and whose system root ships beside the install.
`writableRoot()` then takes the first `user` root from whatever configuration
supplied it.
The skill and the persona stated `${DSH_HOME:-$HOME/.dsh}/.agent-presets/<id>/`
as where authored presets live, which is only the default install's answer, and
no call reports either root: `authorable` says whether a writable one exists,
and `list()` cannot reveal a user root that is still empty. Both now keep that
path as what to tell a user asking where to look, and direct every path an agent
acts on to `list()` or `resolve()` — which is also what `copy()` already relies
on, since it chooses the writable root itself and reports the file it created.
Review found two errors in the first pass.
The skill quoted `service "<name>" has been registered at <Owner>` as the
rejection for a service published into the root realm. That message only
appears when the loose name collides with one the host already supplies. A
preset publishing its OWN new service name reaches the root realm successfully
and is rejected by the mount audit instead, with `row(s) published
process-global service(s) [...]` — which is the shape a forgotten realm
actually takes. Both messages are now listed, verified by mounting one preset
of each kind.
The Agent Note claimed every harness package publishes exactly three file
patterns. 139 do; 28 also publish `lib/client.js`, 22 publish
`lib/types/**/*.js`, and `dsh-message-feedback` publishes `src`. The note now
states only the fact it needs: no package's `files` includes its README.
Also from review: the copy step no longer repeats the display name it already
set, the id rule spells out `[a-z0-9][a-z0-9-]*`, and the sandbox step says
reads need no escalation.
These e2e boot a real harness and read Host services, so they type-check in the
Host aggregate; importing a Client package there pulls its whole project — and
everything it references — into the Host build phase, where a Client project
waiting on generated artifacts cannot compile. The welcome-notice constants are
mirrored in the scaffold instead, which lets apps/cli drop the Client project
references that only served as their owner map.
A fast one-shot can request exit through ctx.appExit while the launcher
still awaits its watcher setup; the failure guard now also swallows the
resulting rejections when the tree is no longer live, not only on
signal shutdown. Sync the app-boot README and headless bundle comment
with unconditional patch watching, and bring the two Agent Notes still
asserting the --dev row append and the headlessIo slot current.
The client-hmr row joins the web bundle as an ordinary always-on roster
row: without a rebuild watcher rewriting client bundles it polls
unchanged files and stays idle. This deletes the --dev flag, the web
runtime's mode config, the mode-forked prompt contract, the DSH_WEB_MODE
bash variable, and the post-settlement row-creation machinery the
conditional row required. dsh web + pnpm run dev:web remains the
development loop.
The web runtime creates its dev-mode client-hmr row in the root tree
after Loader settlement with plain loader.create, deleting the vendored
Entry.enableRuntime state machine and dsh-cmdline's enableRow export.
Include declares the existing EntryGroup.key tree-carrier marker instead
of the EntryConfigResolver protocol (its own path stays literal; nothing
used a dynamic path). The launcher recognizes no app row: SIGTERM exits
0 on every surface, every boot watches its user patch layers, and the
headless runner exits through ctx.appExit, deleting ctx.headlessIo. Also
restores the vendor README rescope entry to the position the
rescope-vendor exact-edit anchor requires, fixing the master hygiene
regression.
The `cordis` preset's `editing-cordis-compositions` skill is the only guidance
an agent has when it authors a preset, and four of its statements were false.
`tool-bash` was named as the worked example of a row that hides a service; it
provides nothing and injects `bashEnv` from the host's own `bash-env` row, so
following that advice strands the row behind its realm and the preset fails to
mount. The `isolate` example composed `tasks-local` with `tool-tasks`, which
the shipped compositions' own comments say breaks `run_in_background`. A string
realm label was described as pooling one instance; labels join realms and
`provide()` still throws on the second registration. Rows were to be checked
against a package README, which no harness package publishes.
Verification is now the agent's own: `standingKeyFor(id)` runs the same mount a
session start performs and rejects an unresolvable package, an invalid config, a
service in the root realm, and a row that never activated. The skill states that
`list()`'s `broken` field is a shape check that every one of those passes, ships
the `cordis_mount` plugin that reaches the roster service, and names `copy()` as
the authoring write. The prohibition on touching the shipped install is promoted
to its own section and extended to the host composition.
Fixes#2266
Only `docs/module-graph.*` conflicted, from master's new
`@deepseek-ai/dsh-message-feedback` package; generated, so taken from master
and regenerated.
Hook bypassed as before: the staged-pairing check hands an archived note path
to `verify-translation-pairing`. The full-corpus gate passes.
Generated docs (`module-graph`, `event-producer-consumer`) taken from master
and regenerated. The `cordis-inspect-jsdoc` golden likewise: master's copy is
the base, and this branch's `presentAs` per-scope rewording is re-applied on
top, since `cordis_inspect` renders that JSDoc into model-visible output.
Hook bypassed as before: the staged-pairing check hands an archived note path
to `verify-translation-pairing`. The full-corpus gate passes.
Master moved peerDependencies to `workspace:^`; this branch's two added peers
(`dsh-agent`, `dsh-system-prompt`) take the same form. `docs/module-graph.*`
is generated; regenerated after the merge.
Hook bypassed for the same reason as the previous merge: the staged-pairing
check hands an archived note path to `verify-translation-pairing`. The
full-corpus gate passes.
Review found two defects in the previous commit's ordering fix.
@pku-xht: `historyStateFor` copied the attached session's events, the handler
then awaited `presenterScopeFor`, and only then read the projection baseline
off the still-live Session. An append during that await served events cut at N
beside a baseline folded to N+1 — one response describing two moments. The
same restructure had also moved the baseline read outside the `try`, so a
failing snapshot escaped the structured `internal` error.
Both awaits now happen before the cut: `historySourceFor` resolves which
session serves the read, `presenterScopeFor` ensures the recorded composition,
and `historyCutOf` then reads events and baseline adjacently with nothing
between them. The whole sequence is back inside the try.
The invariant judged any scoped assembly with a chain of one as an unjoined
agent, which rejects a legitimate assembly in a standing preset key (that key
has no parent of its own). It now gates on `context.agent` — a scope-only read
is not an agent and is out of range by construction rather than by a premise
about who else calls `assemble` — and asks the roster's own
`composedPreset()` instead of introspecting chain length. The advisory warning
uses the same relation.
Also from review: the `2026-08-05-per-agent-tool-presentation` note still
described `presentAs` as per-agent, which standing mounts made false and this
branch's own rewording contradicts; the duplicated "process-wide unit table"
argument collapses to the Agent Note with pointers from the five copies; a
dead `.sort()` before `arrayContaining`; and change-history narration in the
tool-cordis README.
The root manifest carries the dsh family version. bump writes it with the
members, because the workspace constraint requires them to match, and that
constraint now accepts a prerelease segment: without both, release:dsh 0.0.2
left the root behind and 0.0.1-rc.1 could satisfy neither check.
The Landlock workflow no longer passes --access public, which overrode the
restricted publishConfig this repository just adopted for those packages.
Vendored change detection reads build inputs when a package publishes build
output, and vendor/cordis publishes the src its export map already pointed at:
its lib/ is untracked, so a real source edit read as 'nothing changed' and the
next publish would fail on a version whose bytes moved. The next version also
takes the last published version as its baseline, so a re-sync that restores a
lower upstream version cannot recompute a version already on the registry, and
bump confirms the registry carries what the newest tag names.
Tag prefixes are constructed rather than recovered from a full tag, which a
hyphenated version defeated. Pack runs group per ref so concurrent pull requests
stop displacing each other, the publish job carries the global group, and the
unused id-token permission is gone.
Every release script sits behind an entry guard, which is what lets the pure
judgements carry tests: tag naming, publish order and cycle reporting, version
arithmetic, payload policy, and the change judgement.
The Agent Note moves to implemented and states what shipped: one probe command,
the registry confirmation that now exists, and byte reproducibility recorded as
assumed rather than measured.
The pre-commit staged-pairing hook was bypassed for this merge: master's
`docs(notes): archive superseded dsh run decision` (7ee9e16001) arrives as a
rename into `.agents/notes/archived/`, and the hook hands that path to
`verify-translation-pairing`, which correctly refuses an archived note as
out-of-corpus. The full-corpus gate passes (851 pairs).
1504 hand-written ranges pointing at workspace members become workspace:^, so
pnpm pack substitutes each member's real version at publication: sibling
peerDependencies follow the family version instead of being pinned at ^0.0.1,
and a reference to a vendored package follows that package's own line. Without
this, publishing 0.0.2 ships peer ranges naming a version that does not exist,
and 0.0.1-rc.1 does not satisfy ^0.0.1 either.
It also retires ranges that had gone stale against the workspace: ^4.0.0-rc.6
for a 4.0.0-rc.7 checkout, ^3.17.0 for schemastery 3.18.0.
workspace:* stays where an exact published version is the point, which is how
the Landlock entry pins its platform packages.
A workspace constraint now requires the protocol, so a new package cannot
reintroduce a hand-written range. The same constraint caught packages/boot/cmdline
arriving on master without the publishable trio, which this change completes.
Every package under packages/, apps/, and vendor/ drops "private": true and
declares publishConfig.access "restricted": the repository now states which
packages it publishes instead of deciding it at publish time. Each one also
declares its repository and directory, which is how a consumer of a private
package reaches its source.
The Landlock packages move to restricted with them. They have never been
published, so nothing anonymous depends on them today, and the whole
@deepseek-ai scope stays private.
The workspace constraint that required every package to be private now applies
to non-members only, and asserts the publishable trio on each release member.
`minimal` was rewritten upstream into a fixed-prompt PTY surface that now
carries its own compaction group, so this branch's token-meter move applies to
it too: the row leaves the group and `tokenMeter` leaves the realm, exactly as
in the other three presets. Master's header prose is kept whole — the note this
branch had added there described a composition that no longer exists.
`docs/event-producer-consumer.*` is generated; regenerated after the merge.
Launcher flags come first and end at the first token dsh does not
recognize; everything after reaches the booted app verbatim, so
dsh --profile tui --resume <id> works with no launcher change and
dsh --profile web --help prints the web app's help. A bare dsh -h, which
has no app to hand the flag to, still prints the launcher's own.
src/web.ts is deleted: the Web flag family, its LAN-trust sampling, and the
one-shot task positional now live in their bundles, and runProfile no
longer knows any row id. What the startup row decides comes back as a
launcher-owned patch layer above every layer a user can edit, so a live
config edit recomposes the tree without resetting a served port.
dsh web and dsh --profile web finally boot through one path, which also
gives --profile web the harness-source prompt section that only the alias
used to add.
Yichen Jiang
Tianyi Cui
imccyu
Turtle
creatixchu