A summary can fail while appending turn/start or turn/end and still leave
the root idle with a stable Session sequence. The SDK wait operation then
returned {}, letting the external provider treat the preceding completed
terminal as the result of the entire task. A listener installed only for
the wait would also miss failures between prompt admission and the wait
request.
Retain one latest live failure on each existing SDK Session record, scoped
to the exact owned Agent. Record the Session's next log offset when the
failure occurs. A turn/end from the exact owned Session clears it only
when that terminal was committed at or after that offset. This preserves
failures raised during terminal publication, keeps ordinary represented
turn errors in the durable outcome, and permits later successful activity
to recover. At stable root/descendant completion, session/wait rejects any
remaining failure. Raw session.status and HarnessSession.run behavior are
unchanged; no generic failure history or new notification is introduced.
Add seven owner-local cases for later start/end failures before and during
wait, subsequent successful prompts, represented errors, and publication
ordering including an undefined thrown value. Six failure cases returned
success before the fix. Strengthen listener teardown coverage to assert
all actual subscriptions are disposed after a disposer fails.
Extend the existing recorded subagent-continuable SDK scenario to exercise
session/wait. It still asserts that run() returns DONE at parent turn 1,
then requires child completion and parent turn 2/idle plus its final
summary to be delivered before the wait response. Bypassing the wait made
that ordering assertion fail. No recorded Session or golden output was
invented or refreshed. Update the protocol/server bilingual READMEs and
regenerate the event-consumer matrix for the new error listener.
Validation:
- pnpm exec vitest run packages/sdk/server/tests/wait.spec.ts before the fix:
6 failed, 1 passed (the represented-error case)
- pnpm exec vitest run packages/sdk/server/tests/server.spec.ts packages/sdk/server/tests/wait.spec.ts (40 passed)
- pnpm run test:e2e packages/subagent/subagent-dsh-sdk/tests/nested-delegation.e2e.ts packages/subagent/subagent-dsh-sdk/tests/loader-composition.e2e.ts (8 passed)
- DSH_EXAMPLE_MODE=lib pnpm run test:e2e packages/subagent/subagent-dsh-sdk/tests/nested-delegation.e2e.ts packages/subagent/subagent-dsh-sdk/tests/loader-composition.e2e.ts (8 passed)
- pnpm run test:snapshot snapshots/sdk/sdk.snapshot.ts -t 'replays subagent-continuable through dsh --profile sdk' (1 passed, 24 unselected)
- pnpm run doc-sync: Host compile/bundle, doc-typecheck and 40 other gates
passed; the generated event graph was stale, then regenerated and passed
pnpm run verify-doc-graphs (all 7 graph docs current)
- pnpm run lint:contracts-ready and focused lint of all changed SDK code
- named translation pairing checks and git diff --check
Independent SDK rereview and 7/7 focused tests found no remaining issue.
The parent task owns unchanged Python advanced/recovery validation on the
combined branch; this commit changes no Python or high-level SDK results.
SubagentRun.id previously promised uniqueness only within one parent,
but the unified manager indexes every external activation by that id in
one runtime-wide resident map. Publication also checks the live Agent and
Session registries. Two compliant-looking provider results could therefore
collide even when they belonged to different parents.
Document the existing shared Session id namespace across all parents,
providers, and local Sessions. Update the package reference, bilingual
type-equivalent declaration, and the current upgrade guide so custom
providers know to replace parent-local counters with fresh execution ids.
The shipped ACP, DSH SDK, Codex, and Claude Code providers already mint
UUIDs; no runtime mapping or additional retained identity state is needed.
Add a cross-parent collision test through startActivation. It proves that
publication rejects the duplicate, disposes only the new external handle,
leaves the second parent catalog empty, and preserves the first catalog
entry and execution result through normal cleanup.
Validation: all seven external-lifecycle tests pass, as do scoped bilingual
pairing, verify-upgrade-guides, doc-sync, and full lint. Cordis catalog and
inspection-catalog regeneration produces no tracked artifact changes.
The activation refactor removes tool-subagent configuration keys, changes
the model-visible result from foreground or Job-backed output to an
activation receipt, and removes a published in-process driver package.
Updated package references describe the new behavior but do not tell an
existing deployment or package consumer how to migrate those surfaces.
Add the bilingual v0.2.1-alpha.1 upgrade guide and pairing record. Explain
which cordis.yml keys and tool arguments to remove, how to consume parent
completion notices, when host code should await caller-delivery results,
and how publication changes cancellation ownership. Name the existing
Spawn/Fork providers and prepareContinuable API as the driver replacement
without adding a compatibility adapter or promising a foreground mode.
Validation: verify-upgrade-guides, scoped verify-translation-pairing,
verify-md-links, and doc-sync pass. A temporary runtime probe executed the
guide's exact YAML and TypeScript fences and confirmed the caller result,
catalog membership, and absence of a parent notice. The four existing
parent-result tests pass. The probe was removed after execution.
The retained continuation decision still claims a public followup method,
a bare MessageId start result, no activation result/cancellation ownership,
and no human Queue/Steer operations. Those statements contradict the current
startActivation receipt and adjacent-Agent/host message operations already
documented in the same record. The subsystem introduction also says the
activation result can settle before cleanup, despite the manager resolving
that result after teardown and notification.
Correct the current realization in the English/Chinese active documents.
Keep the original single-inbox and residency rationale, distinguish accepted
message identity from the activation receipt, and state the actual result
and disposal timing. Do not change implementation, archived decisions,
provider-level result timing, or runtime APIs.
Validation: doc-sync passed 41 gates on the first run. Its remaining pairing
gate found one Chinese README target using the English locale; correct that
target, re-record the pair, and verify both changed pairs successfully.
Integrate master 78ae4fc2d4d8ecaebb4b674028f781a358b92cc9 after the four
independent review fixes. Keep this base update separate from those fixes
and from subsequent review changes so the integration is independently
reviewable and the observed-master checkpoint remains preserved.
Retain activation-owned execution, caller-independent local discovery,
and unconditional parent final-answer delivery. Preserve master's preset
scoped scheduling tools and all delegated-child schedule deny rules. Move
the new scheduling regression from the removed driver package into the
surviving subagent package and run it through a real Spawn activation.
Preserve master's removal of runtime invariant plugins, dependencies,
exports, and test mounts. Keep context disposal before fixture directory
cleanup. Combine Python workflow ordering with activation/catalog events
without inventing unsupported source-plane import paths.
Keep all frozen Agent Note archives byte-for-byte identical to master;
do not accept Git's automatic edits to renamed archived notes. Retain
current lifecycle and delivery facts in active documentation, repair its
links, and regenerate catalogs/persistence schemas from merged source.
All 62 master persistence roots remain; only subagent/catalog gains the
PR's external membership extension. Keep master's third-party lock graph
and update only workspace dependency changes.
Validation before this checkpoint: 683 focused tests passed, seven
Windows-only cases skipped; 2,772 archived artifacts verified. Generated
catalog and active-pair checks passed. Fresh artifact build and remaining
build-dependent documentation checks continue before publication.
A local child can have send_message available and still finish with a plain
text answer or use the tool only for progress. Selecting completion content
from tool availability drops that captured answer and leaves the parent
with a status-only notice. The recorded spawn case already demonstrates
this: its child returns CHILD_OK without calling the available tool.
Remove the includeClosingText policy and pass every captured final text
through the existing text-only notice renderer. Preserve structured
results, safe diagnostics, external continuation wording, and caller-only
result delivery. No delivery ledger or additional lifecycle state is
needed. A child that sends its final answer explicitly may repeat it in the
completion notice; that cost is preferable to making result delivery
depend on model compliance.
Extend the real-loop parent-result regression with an available-but-unused
messaging tool, restore the unconditional lifecycle expectation, and pin
text alongside structured results and diagnostics. The new regression
fails on the prior implementation because CHILD_RESULT_42 is missing.
Update the owning bilingual descriptions and the exact parent notice
content in headless and TypeScript SDK recordings. Keep replay streams,
released generations, and unrelated recorded clocks unchanged.
Validation: 317 focused lifecycle/workflow tests; full build; 26 focused
headless/SDK replays; Python SDK advanced/recovery smoke (unchanged
fixtures); test:docs (20 gates); doc-sync (42 gates); full lint;
git diff --check.
Caller delivery previously suppressed both settlement messages and local
catalog membership. Workflows therefore stopped publishing the durable
parent-child edge that the parent header and recursive discovery require.
The workflow panel only opens running members, and the ordinary sidebar
hides subagent Sessions, so completed workflow transcripts had no normal
navigation path even though their logs still existed.
Record every successfully admitted local child in its parent's catalog,
independently of the result recipient. Membership answers which local
Sessions belong to the parent; delivery answers who consumes this activation's
result. Keeping those decisions separate restores completed-child and
descendant discovery without duplicating workflow completion messages or
adding return guidance to caller-owned work. Publication failures retain
the existing rollback transaction for both delivery modes.
These local children intentionally retain the unified continuable mode:
list_agents includes them, the parent catalog opens their transcripts after
reload, and the existing direct-parent controls can cold-resume them. No
one-shot execution path or additional lifecycle state is introduced.
Caller-owned external executions still use their consumer's membership
records because they have no local Session to open.
Update the existing bilingual service/workflow documentation and decision
records, refresh the owning workflow/Ralph/advanced Session recordings and
Python SDK event expectations, and preserve unrelated recorded stream times.
Validation:
- Full repository build passed.
- 443 subagent, workflow-host, and Ralph tests; 14 list_agents tests passed.
- Four focused headless workflow/advanced snapshot refreshes and replays passed.
- Three shipped-Web workflow tests passed, including completed-child catalog
navigation after reload and the continuable composer.
- Python SDK advanced and scheduler-recovery snapshots refreshed and replayed
through the built dsh CLI with Python 3.12.
- Three discovery regressions fail with the original catalog exclusion and
pass after restoring this fix.
- test:docs (20 gates), doc-sync (42 gates), lint:contracts-ready, Host and
Client TypeScript builds, and git diff --check passed.
A content-deduplicated shared file has no visible change record. If its
metadata became unavailable while the harness-home winner changed or vanished,
the reconciler skipped the failed candidate and still published the winner's
replacement or removal. Guidance that remained in the shared file disappeared
from the model's effective instructions. Content-read failures had the same
partial-group behavior even when metadata probing succeeded.
Rollback the probed candidate group whenever any metadata probe is unavailable
or its bounded content read cannot complete. Include candidates without a
visible predecessor and candidates previously removed as duplicates. Reuse
one rollback operation for proposed messages, deferred version updates,
metadata mutations, and retained digest bookkeeping, so a later successful pass
can reconstruct the complete group independent of cache warmth.
A filesystem path can also appear as a project instruction when the Harness
home is the project root. Releasing observed paths on rollback let that later
alias publish the very content withheld by the failed global group. A transient
failure of the first member also left failed and unvisited paths unreserved.
Factor the existing scope-to-file path calculation and reserve every eligible
member's absolute path for the rest of that pass when its group rolls back.
Project aliases therefore cannot bypass group preservation, without additional
filesystem operations. The shared resolver keeps probing and rollback path
calculations identical. Add metadata, content-read, and one-shot first-member
failure regressions for this supported same-file layout and its recovery.
Keep cancellation propagating to the caller. Keep explicit baseline-budget
exclusions outside observation rollback, because their removals are deliberate
policy decisions. No new session fields, baseline identities, polling, retries,
or process-global state are needed. Clarify the metadata/content and hidden
candidate guarantee in the bilingual README.
Add four real-plugin outage/recovery tests for metadata or content failure while
the retained home file is edited or deleted, plus a cold-cache reconciliation
regression. Add an authored headless session scenario with instance-local
provider failure injection: request two keeps baseline A while shared metadata
is unavailable; request three receives the home B replacement and shared A
addition together after recovery. The fixture restores the provider method on
disposal and asserts the real home/shared files before restoring observation.
Declare its test-only filesystem dependency without changing runtime packages.
Regenerate the persistence catalog's source anchors after the shared path
helper import shifts AgentInstructionSource by one line. Its persisted fields
and SHA-256 type fingerprint remain unchanged; no type acknowledgement or
Session migration is required for a source-location-only update.
Validation:
- All five new regressions failed with the intended partial-group emissions
before the source fix.
- pnpm exec vitest run packages/context/agent-instructions/tests/agent-instructions.spec.ts -t 'hidden duplicate has|cold global group|unavailable active candidate|unavailable scope': 8 passed.
- pnpm exec vitest run packages/context/agent-instructions: 174 passed.
- The focused authored headless snapshot refresh and replay passed.
- Restoring the early skip for an unavailable hidden candidate makes the
headless snapshot fail with the premature harness-home replacement.
- README translations were updated together and their pairing rerecorded.
- Three project-alias regressions failed on the initial group rollback fix,
then passed after reserving failed and unvisited candidate paths.
- pnpm exec vitest run packages/context/agent-instructions/tests/agent-instructions.spec.ts -t 'frozen across a project alias|hidden duplicate has|cold global group|caches a removed duplicate': 12 passed.
The user-global instruction scope now reads two roots: $DSH_HOME/AGENTS.md
first, then the shared agents root that other agent tools use
($DSH_AGENTS_HOME, else ~/.agents). Both resolve from the process environment
through @deepseek-ai/dsh-home-paths; no config field is added, because the
stack base (PR #5718) removed the per-row home override.
The two files are candidates of one candidate group: identical trimmed content
renders once from the harness home, an unobservable candidate preserves the
group's last-good state, and reconciliation probes both roots so external
edits, removals, and new files become visible change notices. A candidate
dropped as a duplicate keeps being reconciled, so deleting or changing the
retained candidate promotes it. The harness-home file keeps its recorded
`user-global` scope key; the shared file carries `agents-global`.
A user-global delta states `These user-global instructions apply to all work.`
instead of naming its reconciliation scope, and a project path whose first
component would collide with a user-global scope directory renders with a
leading `.` so it keeps its own scope.
Review follow-ups:
- The guide claimed the removed field was the last per-row home override;
other providers (skill-filesystem, shell-env, credentials-local,
subagent-dsh-sdk, attachment-local) keep their own fields, so it now states
that the removal covers the instruction loader, and step 1 also names the
home-level `$DSH_HOME/cordis.patch.yml` layer.
- `DiscoverOptions` regains an already-resolved `dshHome` that `apply()` passes
from its mount-time `resolveConfig()`, so baseline discovery and
reconciliation share one resolution point instead of reading the environment
separately.
- The package README says the loader reads the process home rather than "the
same home as sessions, skills, and storage", and the resolver Agent Note
states what the skill provider's fields actually select.
- `discoverBaselineInstructionFiles` JSDoc no longer lists a removed option.
The agent-instructions row accepted `dshHome`, letting one consumer read a
different harness home than sessions, skills, and storage. Home is process
policy: the plugin now resolves `$DSH_HOME`, else `~/.dsh`, through
`resolveDshHome()` from `@deepseek-ai/dsh-home-paths`, and the config field and
the library's explicit-home option are gone.
Tests and both snapshot fixtures pin the home with `vi.stubEnv('DSH_HOME', ...)`
and the harness's existing `DSH_HOME` export instead of row configuration.
`dsh-skill-filesystem` keeps its own `dshHome`/`agentsHome` fields.
The removed cordis.yml key gets an upgrade guide.
- Make the record commit an ES private method, so appendPluginRecord()
is its only runtime entry.
- Document PluginRecordType and PluginRecord on the session subsystem
page, and state in the README and JSDoc that the V3-to-V4 edge renames
unknown ignorable V3 events into the plugin: namespace and that plugins
outside this repository must not call the writer.
- The caller gate parses only files that contain the name or a \u
escape, documents that wildcard re-exports are not reported, and its
spec reads a temporary repository instead of this checkout.
- Cover Session.fromRestore in the record test and name SessionEventMap
in the catalog generator's diagnostic.
Add appendPluginRecord(), which appends one ignorable event whose type is
`plugin:` followed by lowercase slash-separated segments, and
pluginRecordOf(), which reads such an event back. Records are not
SessionEventMap members, so the persistence catalog is unchanged; a build
that does not recognize one retains and skips it, and records never enter
the model-visible surface. Resume and fork carry them with the log, and a
format migration keeps them on a best-effort basis.
Only production source under packages/experimental/ may call the writer.
The verify-plugin-record-callers hygiene gate checks every reference in
repository sources, and the persistence catalog generator rejects a
SessionEventMap member in the plugin: namespace.
Session.append() and the record writer share one commit path, so a record
follows the same reentrancy, detach, and observer-containment rules. The
ignorable-events decision, the session README, the format-version
cookbook, and the plugin-author practices describe the records.
- Disposal cancels detached runs before the engine waits for timer callbacks,
so a callback parked in a $ call ends instead of blocking unload.
- A forgotten band wakes and ends its watch streams; a refresh asked for
during a pass joins one more pass that settles after it; the Web band drops
an ended stream so the next subscriber opens a fresh one.
- $ has Claude Code's namespaces: an unserved member rejects with
'no implementation for <namespace>.<member>' instead of a TypeError.
- A .catch handler's next makes the rewrite check; a tool rename is refused
like an argument rewrite; a null op answer is reported as no answer;
defineMod returns its disposer from apply; the live turn record is copied
before the chain freezes it; prompt.submit is raised only for batches with
a human message and names the submitting mod as origin.
- $.http.fetch bounds the body while streaming; bandColumns/bandRows are
Config; the client package drops its stale gateway edges; the source
overlay lives in the package and anchors its entries to the file, and the
dsh installation no longer depends on the experimental packages.
docs/subsystems/claude-code-mods.md lists every way a mod behaves
differently through the bridge than under Claude Code 2.1.287 — packaging,
events, the chain, $ members, drawing, testing, and the example mods,
including the four official mods assessed by reading. The bridge README
describes defineMod, the band, and the test kit; the band package gets its
README; the group index, release families, config and client catalogs,
module and seam graphs, and the Cordis API catalog are regenerated.
A mod is now a plugin built with defineMod() around its register(on,
options); the bridge is the ClaudeCodeMods service (ctx.claudeCodeMods)
that keeps the loaded mods and raises their events. The plugin.json /
hooks.json loader, pluginDirs, and dynamic imports are gone.
prompt.submit context becomes text blocks appended to the human's own
prompt message and $.prompt.submit queues a user-sourced message, so the
bridge adds no message source kind: the persistence record and the
regenerated schema are removed and the artifacts match master again.
Engine correctness from the review round: next() is memoized and every
started run beneath is awaited before a hook's answer settles; a rewritten
tool argument skips the hook with a report pointing at the pre-tool input
rewrite proposal; timers belong to the session whose event started them;
$.tool.call injects a tool's deferred contexts; $.clock.sleep honors the
event signal; a built-in tool answered with { result } is validated against
its output schema before it becomes an error-shaped result; hooks on events
this host never raises are reported at load.
Examples: the three mods from the Claude Code blog post under examples/,
Token Weather and its test unchanged, Blast Radius and Replay Theater
completed from the published fragments, run by their own tests through a
claude-code/testing alias over the new test kit ($.ui.mount/find/press).
- prompt.submit sees and rewrites only the human's own messages, gains the
rewritten text on an image-only prompt, and keeps only typed result fields
- a mod's $.tool.call reaches only the mods loaded before it, attributed to
the caller, instead of re-entering every mod through the pipeline
- a .catch handler shares the failed hook's beneath state so nothing beneath
runs twice; a late next from an abandoned handler is ignored
- hook results are validated before use; detached runs report rejections
- session.end keeps $.state readable until its hooks settle; agent creation
cancellation abandons a waiting session.start hook; agents is read lazily
- a success a hook marks isError becomes a failure; replacement entries clear
on tools/result; per-agent registrations drop with the agent
- $.store writes are serialized per plugin and bounded in UTF-8 bytes;
$.http.fetch bodies are bounded; timers refuse rescheduling after unload
and unload awaits running callbacks; regex matchers reset lastIndex
Root build scripts, the desktop bundle and the dev:web watcher pass the
native loader so tsdown never selects the undeclared unrun fallback. A spec
covers the build.ts rejection path.
Without process.features.typescript, tsdown falls back to the undeclared
unrun loader, which fails to import and, once installed, resolves
import.meta.url in packages/client/tsdown.client.ts to the entry config.
Refs #5622
Add @deepseek-ai/dsh-experimental-claude-code-mods, an alpha bridge that
loads Claude Code mods (plugin directories whose hooks/hooks.json names a
hooks module), runs register(on, options) unchanged, and raises the mod
events from harness extension points: session.start on agent/created,
prompt.submit and turn.start on agent/pre-step, tool.call around
tools/execute, turn.complete on turn/end, session.end on agent/disposed,
and command.run from registered commands. The $ mods API is served over
composed services (commands, tools, user-questions, fs, subprocess,
storage domain, projections); unserved members fail by name.
Includes a middleware chain with Claude Code's failure rules and budget
clock, a claude-code/testing-style test kit, fixtures from the mods
tutorial, full-loop and Loader composition tests, the attribution-only
claude-code-mods message source with its persistence record, and the
regenerated catalogs.
Tianyi Cui