The snapshot tier was built single-session: dsh-llm-replay served calls from
one global positional cursor, and the harness harvested one session log. A
subagent runs as a second agent with its own session, so a parent→child
scenario could neither replay deterministically nor harvest the child's log.
This resolves the TODO(subagent-snapshots) deferral from the subagent RFC.
- Stamp the calling session id onto the model request: GenerateOptions.sessionId
(typed Branded<'SessionId'> to avoid the dsh-llm↔dsh-session cycle), set by the
agent loop from agent.session.id. Adapters ignore it; an llm/stream listener
routes by it.
- Key replay per session: dsh-llm-replay loads the parent log plus one per child
(childFiles / $DSH_SNAPSHOT_CHILD_FILES), derives a script per recorded session,
and binds each live (freshly-random) session to a recorded script by first-call
order — parent first (earliest createdAt, first to stream). Keys by WHO calls,
so it survives a future concurrent/backgrounded subagent; a global cursor would
not. An unrecorded extra session fails loud.
- Harvest every log: the harness collects all .jsonl across cwd buckets, ordered
primary-first (top-level, then children by createdAt), and RunResult exposes the
plural sessionLogs. The spec writes each back on record (session.jsonl +
session.<n>.jsonl) and diffs each against its fixture on replay.
- Wire the subagent seam + spawn + fork + tool into the acp-agent example (both
cordis configs) and add two nested scenarios recorded against the real API:
subagent-spawn (parent + 1 child) and subagent-multi (parent + 2 children, 3
sessions). Both replay keyless in the default gate.
A new RFC documents the design (docs/rfc/implemented/testing/). Single-session
replay is unchanged (a call with no sessionId is one anonymous primary session).
TODO follow-up: a dedicated branded-ids package could own the SessionId brand and
dissolve the cross-package cycle note; out of scope for this testing PR.
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
Codex review of the PR1 diff surfaced docs/cleanup drift:
- LlmService class JSDoc still advertised "streaming / non-streaming call
surfaces, both interceptable via waterfall events" — corrected to the single
streaming surface; regenerated the cordis catalog so its mirror updates.
- Removed GenerateResult from gen-cordis-catalog.ts LINK_MAP (the type is gone).
- The adapter-change RFC's acceptance criterion named the retired
verify-event-taxonomy gate; updated to verify-cordis-catalog.
- Dropped the now-tautological "streaming and one-shot assembly agree" property
test (the streaming/one-shot distinction lived in the removed flush API;
usage/finish remain covered by assembler.spec.ts and the finish property).
The LLM service exposed three call surfaces (stream/streamBlocks/generate) but
the only production consumer — the agent loop — uses stream() exclusively,
feeding raw chunks through its own BlockAssembler for replay fidelity. Drop the
speculative convenience surfaces and the registry-change event that no listener
consumed, leaving stream() as the single model-call contract for both
production and tests.
- Remove LlmService.streamBlocks() and generate(), the llm/generate waterfall,
and GenerateResult.
- Remove the llm/adapter-change event (declaration + emits) and the
listener-throw rollback ordering that existed only to protect it; keep the
HMR rollback disposer.
- Remove BlockAssembler.flushReady()/flushRemaining()/result() and the flushed
cursor — the streaming-flush slice existed only for streamBlocks().
- Adapter tests drive a stream()+BlockAssembler helper (tests/assemble.ts)
instead of generate(), exercising the same path production uses.
- Land the AGENTS.md "RFCs are proposals, not golden truth" principle and move
both RFCs proposed -> implemented.
Implements:
- docs/rfc/implemented/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md
- docs/rfc/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.md
Add a README to each group dir (core/llm/bash/session-persistence/ui/
support) stating its role and product-vs-support classification, and
rewrite packages/README.md around the hierarchy (group table, grouped
"what goes where", removed the package-hierarchy FIXME).
Move the package-hierarchy RFC to implemented/architecture/ and rewrite
it to describe what shipped (placement rationale, the paths-wildcard and
publint dedup, the two new guardrail gates). Fold the remaining
tsconfig.build.json references dedup into the discover-package-inventory
proposal and fix its cross-link.
Update AGENTS.md: regrouped repo-layout map, depth-2 globs, the new
verify-package-paths gate in the doc-sync listing, and a note that we
lean toward stricter lint in the agentic-coding era (machine-caught
errors and a consistent foundation outweigh the one-time cost).
Merge brought in the RFC-classification reorg and two new doc gates;
rewrite every drifted packages/<name> cross-link (Markdown link targets,
moved-README relative depths, and .ts comment paths) to the grouped paths.
Add two doc-sync/hygiene gates so the manual checks this restructure
needed become automated:
- verify-package-paths.ts: flags a packages/<path> reference (in Markdown
or a .ts comment/string) that does not resolve AND names a real package
in a segment — i.e. a stale path to a MOVED package. A path naming a
non-existent package (a forward-looking proposal) is left alone, so it
applies uniformly across proposed/implemented/rejected.
- check-workspace-constraints: assert the packages/<group>/<pkg> depth-2
shape (group dirs carry no package.json; no flat or over-nested
packages). Group names stay open; only the shape is fixed.
Move the 18 flat packages/<name> packages into role-grouped dirs:
core/, llm/, bash/, session-persistence/, ui/, support/. Group dirs are
pure containers; each package keeps its @deepseek-ai/dsh-* name.
Collapse the per-package tsconfig paths maps (base + typecheck) into one
@deepseek-ai/dsh-* wildcard with a candidate per group, and derive the
publint list from the hierarchy. Update all depth-coupled globs/configs
(workspace, tsdown, vitest, eslint, knip, tsconfig includes/refs,
per-package tsconfigs, generators, doc-script scopes, type-equiv manifest)
and the cross-package/script relative imports in tests.
Fix doc-typecheck's workspacePaths() to parse tsconfig JSONC via the
TypeScript API instead of a regex comment-strip, which corrupted the
new wildcard `/*/` path candidates.
WIP: doc cross-links and package/RFC docs still to update.
Add a second axis to every RFC — its class (feature, bug-fix,
simplification, architecture, process, testing) — encoded in the path
as docs/rfc/{lifecycle}/{class}/file.md. The folder is the label, so
the closed set is enforced by structure rather than a parsed field.
Two new doc-sync gates back it:
- verify-rfc-classification: every RFC sits in a valid class folder and
the README index lists it under the matching lifecycle→class heading.
- verify-doc-refs: every docs/*.md path cited in a packages|examples TS
comment resolves — closes a drift class verify-md-links can't see, and
catches the four comment refs this reorg moved.
The README gains a Classification section explaining the taxonomy and
per-class index sub-sections. A self-referential process RFC records why
the scheme is path-encoded and gated.
Annotate all 24 harness events across the 5 event-declaring packages with
an explicit `@mode emit|waterfall|parallel` tag and self-contained JSDoc, so
the generated cordis catalog can render each entry's mode and prose from
source alone.
Collapse docs/adr/ and docs/rfc/ into a single docs/rfc/ with proposed/,
implemented/, and rejected/ subfolders. Every file is renamed to
yyyy-mm-dd-topic-title.md, where the date is when the topic was first
proposed (from git history). ADRs and RFCs that covered exactly the same
topic are merged (property-based testing, session persistence); the
umbrella RFC 005 stays split across its three implemented decisions, and
RFC 006's deferred part-3 (API extractor reports) splits into its own
proposed RFC. All cross-references become machine-checkable relative
links instead of bare "ADR NNNN" / "RFC NNN" prose.
Add a verify-md-links doc-sync gate (scripts/verify-md-links.ts) that
checks every relative Markdown cross-link resolves, wired into doc-sync
alongside verify-md-wrap. This makes the reorganization self-verifying:
the same change that rewrote ~forty inter-doc links adds the check that
proves none dangle. Document the cross-link convention in a new
docs/AGENTS.md and record the gate as an implemented RFC.
doc-sync, typecheck, lint, and the full test suite (667) all pass.
llm.registerAdapter, agents.register, sessions.create, systemPrompt.section,
systemPrompt.tools, and tools.register each mutated state, emitted a change
event, then returned the disposer. In Cordis a synchronous throw before the
effect returns its disposer leaves nothing for the fiber to collect, so a
throwing change-listener leaked the registry entry permanently — HMR/dispose
could not clean it, and the duplicate-name/already-exists check stayed wedged
until restart.
Convert each to the generator-effect pattern already proven in
AgentLoop.create: mutate state, `yield` the disposer that undoes it (collected
before the next step runs, so it is torn down if a later step throws), THEN
emit the change event. The existing duplicate-name throws are unchanged — they
fire before any mutation, so they correctly leak nothing. No public API change:
generator effects are still synchronous SyncEffects and register() keeps
returning its fire-and-forget disposer wrapper.
Tests: a listener-throw rollback test for all six methods — register with a
change-listener that throws, assert the call throws AND the registry is clean
(entry absent; a subsequent listener-free register of the same name succeeds
and contributes exactly once). For systemPrompt (no duplicate-name check) the
two tests assert assembly is clean. Verified each fails against the pre-fix
emit-before-return-disposer form.
Introduce HarnessError in dsh-llm (the leaf package): a stable machine-routable
code distinct from the message, cause chaining, name from the subclass, plus
isHarnessError. LlmError, ToolArgsError, and InvariantError now extend it.
Tool failures carry the structure end-to-end: ToolExecutionResult gains
error: { name, code } (populated from a thrown HarnessError), and the loop
forwards it onto the tool/result session event (which gained the same optional
field) for retry/sandbox plugins and replay. The loop's toError wraps non-Error
throws in a HarnessError(code: UNKNOWN, cause) instead of a bare Error.
Landed last and in isolation so it's a pure upgrade over the plain Error+code
the earlier PRs used — independently revertible. Graduates RFC 005 pt 2 ->
ADR 0015; RFC 005 now fully implemented.
- llm: generator now emits finish chunks (the finish-defaults property was
vacuously green); add a property asserting streaming and one-shot assembly
agree on usage and finish
- agent-loop: assert the synchronous burst batches into exactly one turn; add
a mixed-schedule property (send/settle interleavings); recordStatus returns
its disposer; per-run timeouts so a hang loses no seed
- session: randomize the noise/message interleaving (was a fixed alternation)
- tools: exclude non-finite doubles from generated numeric args (JSON-real)
Adds fast-check + one tests/properties.spec.ts per protocol-shaped package
(llm/BlockAssembler, session, tools/schema DSL, agent-loop scheduling). The
tools suite includes the RFC 001<->005 composition property (generated args
satisfying a spec pass validateArgs), closing the validator/InferArgs drift
risk from ADR 0011. Loop properties are deterministic (settle on agent/status,
no sleeps).
The BlockAssembler suite found a real bug on first run: a duplicate block-end
at the same index overwrote an already-flushed block, so the streamed prefix
disagreed with final blocks(). Fixed (first close wins, matching the existing
straggler rule) + regression test. Graduates RFC 001 -> ADR 0013.
- AGENTS.md Commands: fix typecheck/build descriptions; add lint, lint:fix,
test:coverage, knip, publint, hygiene (were undocumented).
- Drop the bare `yarn demo` for explicit `demo:echo` + `demo:coding`; update
README, examples READMEs (and document coding-agent in examples/README).
- New cookbook guide: adding-a-vendored-package.md (the missing "add" half of
vendor/README's update-only procedure).
- architecture.md: add a table-of-contents and extract the Extension cookbook
to docs/cookbook/extension-cookbook.md (link-preserving); drop the completed
"restructure this document" TODO.
- ADR 0009 (capability seams) + 0010 (twin LLM adapters), and a "when to write
an ADR" standard in adr/README.
- Add a committed dsh-code-review skill under .agents/skills, exposed to Claude
Code via a tracked .claude/skills symlink (gitignore carve-out).
Hard line breaks mid-paragraph make docs harder to edit and diff — a
one-word change reflows and re-diffs the whole paragraph. Reflow all
tracked non-vendor Markdown (plus vendor/AGENTS.md) so each prose
paragraph is a single line; soft-wrapping is the editor's job. Fenced
code, tables, and list structure are preserved (wrapped list items fold
to one line per bullet). Documents the convention in AGENTS.md.
The first real LlmAdapter implementations, shipped as a deliberate pair:
same models and wire protocol, completely different internals, so the
StreamChunk protocol is verified across independent implementations.
- dsh-llm-deepseek: hand-rolled fetch + SSE parser + chunk-translation
state machine against the official chat-completions format (thinking
mode via top-level thinking/reasoning_effort; the empty-string
reasoning_content first chunk; usage attached to the finish chunk or
trailing; reasoning_content passback on tool-call turns; disjoint
cache-token accounting).
- dsh-llm-pi-ai: the same endpoint through @earendil-works/pi-ai,
mapping its event vocabulary (parsed tool arguments, in-stream error
events, folded reasoning tokens) onto the same chunks.
The agent loop now honors the in-band error path: an adapter that ends
its stream with finish {kind:error|aborted} (the only option for
adapters that can't throw mid-stream, like pi-ai) is translated into a
step error, so the turn ends error/aborted with a logged error event
instead of a normal completed assistant message. This makes the
StreamChunk error contract real for both adapters; docs/architecture.md
and the StreamChunk doc are updated accordingly.
New yarn test:e2e (vitest.e2e.config.ts, *.e2e.ts) runs key-gated
real-API matrices for both adapters across V4 Flash/Pro and all
thinking/effort levels; it self-skips without DEEPSEEK_API_KEY. Unit
suites run against local node:http mock SSE servers at 100% per-file
coverage.
assertNever (dsh-llm) marks unreachable defaults on CLOSED unions:
adding a StreamChunk variant now breaks compilation at
BlockAssembler.push, and a value escaping its type at runtime throws
with diagnostics. The module doc and a new AGENTS.md convention spell
out the dividing line: merge-extensible unions (SessionEventMap,
ContentBlockMap, …) must NOT use assertNever — plugin-added variants
are valid unknown values there; handle known cases and fall through
with a comment.
Nominal string types via a unique-symbol brand (zero runtime cost):
an AgentId can no longer be passed where a CallId is expected. Each
core package brands the IDs it owns — CallId in dsh-llm (tool-call
correlation across blocks, chunks, session events, and execution
results), SessionId in dsh-session, AgentId in dsh-agent. Construction
goes through same-named factory functions; public string-in APIs
(sessions.create, agentLoop.create) keep accepting plain strings and
brand internally. Policy note in the brand module: brand IDs that
cross package boundaries, not every string.
Flat config with two layers. Correctness (type-checked): the headline
rules for this codebase are no-floating-promises / no-misused-promises
(a lost promise in the agent loop is our primary bug class),
switch-exhaustiveness-check (we switch over merge-extensible unions
everywhere), no-unnecessary-condition, require-await, and
no-explicit-any. Style (@stylistic): 2-space, no semicolons, single
quotes, trailing commas, max-len 140 — the existing house style, now
enforced instead of drifting between agents. vendor/ is excluded
(vendored source keeps upstream style); tests relax the rules that
fight test ergonomics (non-null assertions after expects, async mock
signatures, non-Error throws).
Code adjusted to pass: registry disposers wrap ctx.effect's
promise-returning disposer behind a sync () => void (our public API),
BlockAssembler gains an invariant-checking mustGet instead of non-null
assertions, lastTurnNumber uses findLast, waterfall tails return
Promise.resolve instead of async-without-await arrows, and the two
deliberate suppressions (non-exhaustive derivation switch, unbound
execute pass-through) carry justification comments.
yarn lint / yarn lint:fix added.
tsconfig.base.json adds noUncheckedIndexedAccess,
exactOptionalPropertyTypes, noImplicitOverride,
noFallthroughCasesInSwitch, noUnusedLocals, and noUnusedParameters on
top of strict. Vendored packages opt out of the new flags locally
(their tsconfigs are ours to regenerate; their source is not), keeping
upstream-sync friendliness.
Our code fixed accordingly: index accesses acknowledge undefined
(assembler flush cursors, lastTurnNumber); optional properties are
omitted instead of set-to-undefined (GenerateResult.usage,
ToolDefinition.strict, GenerateOptions.system/tools, error payloads
via an errorData helper); Session.onAppend is explicitly
`(…) => void | undefined`; tests and examples updated for unused
parameters and indexed access.
Docs: per-folder README.md for packages/ (family overview + one per
package: service, events, API, extension points, TODOs), examples/,
and examples/echo-agent/; folder-level AGENTS.md (+ CLAUDE.md
symlinks) for packages/ and vendor/; module-level doc comments in
every packages/*/src file; richer JSDoc on all exported API
(event side effects, disposal contracts, error behavior). Root
AGENTS.md gains a "Type Safety and Documentation" policy section:
the codebase aims to be very type-safe and well documented; type
gymnastics are acceptable in core packages when they improve
plugin-author DX; verbose docs are fine as long as they stay strictly
in sync with the code.
Type safety: removed the upstream-inherited "noImplicitAny": false
from tsconfig.base.json — packages/* now compile under full strict
mode; vendor/loader and vendor/include set it locally (vendor/cordis
already did). Eliminated every `: any` / `as any` from packages and
examples (catch clauses use unknown + a CodedError narrowing type;
event data access uses discriminated-union narrowing).
Typed tool schemas: new @deepseek-ai/dsh-tools schema DSL —
SchemaSpec with per-property `required: true` booleans, type-level
InferArgs<S>, a runtime SchemaSpec → JSON Schema converter, and
defineTool() so first-party tools get typed execute(args) with zero
casts (raw JSON Schema still accepted for MCP interop; chosen over
schemastery because it targets JSON Schema generation directly).
echo-tool and all test tools migrated; +7 tests.
High (loop pipeline): agent/step-result now runs before the
assistant/message append so the session log records what tool dispatch
actually uses; abort is honored between tool calls, not just
mid-stream; steering drains at step start, pending steering overrides
a negative turn-continuation decision (/goal pattern), and leftover
steering is re-enqueued as queued messages so it is never stranded;
exceptions from turn-continuation listeners and session/flush are
contained to the turn (error event + agent/error) instead of killing
the driver loop.
Medium: disposal emits agent/status('disposed') and mid-turn disposal
records reason 'disposed'; duplicate LLM adapter registration throws
(all-or-nothing); SessionEvent is a real discriminated union (casts
removed); model-less agents fail with a clear actionable error unless
agent/request supplies a model.
Low: agent/queued and agent/steering carry the resolved MessageSource;
streamBlocks() yields strictly in stream order and flushes delta-only
blocks (matches generate()); BlockAssembler freezes blocks on
block-end and ignores stragglers from malformed streams; turn
numbering is a counter seeded from the log (fork-safe); LoopAgent's
stop disposer is infallible (a throwing status listener cannot skip
registry cleanup); AgentLoop.create uses a generator effect so stop
and unregister are independent disposables; SessionStore wires
onAppend inside its effect.
21 regression tests added (review-fixes.spec.ts), organized by
finding. Docs updated: loop pseudocode (status emissions, ordering,
error containment, steering guarantees) and waterfall composition
caveat in docs/architecture.md; AGENTS.md notes that excessive tests
are welcome.
@deepseek-ai/dsh-llm: provider-neutral content-block vocabulary
(merge-extensible maps), raw StreamChunk protocol, ToolSchema,
abstract LlmAdapter, LlmService adapter registry, BlockAssembler.
@deepseek-ai/dsh-session: event-sourced Session (append-only log,
deriveMessages; context/steering render as tagged envelopes),
SessionStore, session/event + awaited session/flush durability seam.
@deepseek-ai/dsh-system-prompt: ordered sections + tool-schema
providers; assemble() through the system-prompt/assemble waterfall.
Tool schemas are part of the assembly by design.
@deepseek-ai/dsh-tools: tool registry feeding schemas into the
assembly; execute() through the tools/execute waterfall (the single
sandbox/permission/hook seam).
@deepseek-ai/dsh-agent: Agent interface (send/steer/inject/abort,
spawn/fork TODO seams), AgentRegistry, and the full agent/* event
taxonomy so plugins never depend on the concrete loop.
Tianyi Cui
imccyu