Codex diff review, round 1, two (A) findings:
- The agent/request fallback resolved the RAW seed object — on later
steps the session's cached header fold — so a delegating listener
(await next(), mutate, return) could rewrite the fold in place and
the change would compare as already-baseline: no delta logged, the
persisted log unable to reconstruct the request (the dev invariant
would fire on the divergence, but the log would still lie). One
structuredClone'd, deep-frozen seed now serves both the listener
chain and the fallback — in-place shaping after delegation throws —
and Session.requestHeader() freezes its fold on update, so the leak
class is unrepresentable from either side. Pinned by a loop-level
delegating-mutator test.
- Doc sweep for the old contract: agent README's event row (mutate
GenerateOptions / tool filtering → frozen config seed, replacement
out, logged header), compact-basic's module JSDoc (summarize routed
through agent/request → direct one-shot at llm/stream), and
architecture.md's event-domain line (request mutation → call-config
shaping).
The reconstructability RFC is the principle's home: model-visible ⟺
logged in both forms, the mechanism (boundary derivation + header
fold), the enforcement (write-time round-trip guard, the dev
invariant), the corollaries ranked (prefix-cache stability first), the
MiniCode lineage with the provenance arrow inverted, and the
alternatives it beat — including the stateful transmission client
whose three-design archaeology lives in PR #162.
Placements per the one-home-per-fact taxonomy: a standing-order line in
root AGENTS.md (with displacement trims to stay inside the 1,575-word
ceiling), the principle statement in architecture.md § Session Log and
its Turn Flow lines (condensed to the ratcheted 1,630 ceiling), the
request-envelope section in core-data-structures/core.md with the
LlmCallConfig paste, both review-requested FIXMEs
(FIXME(call-config-shape) beside the type, FIXME(catalog-verbs) at the
catalog's drift-gate note), cookbook rows redirected off agent/request
(tool filtering → system-prompt/assemble, plan-mode prompt → sections/
inject()), and the llm/stream JSDoc stating the frozen-request
contract. RFC index and all generated catalogs regenerated.
Beyond the mechanical conflicts (provider capability lines vs master's new
inheritsParentContext field; generated catalogs regenerated rather than
hand-merged; knip/lockfile), three master-side reworks required semantic
adaptation of this branch:
- The persona rework removed AgentOptions.systemPrompt, which was the
structured-output instruction's channel. The instruction now rides the
SAME final-request enforcement listener that injects the schema'd tool:
appended per request to final.system (per-request wire state, not agent
prompt state). Tests assert the wire request (adapter.requests) instead
of child.options; the bare-direct-dispatch test pins the no-system arm.
- Tool guidance moved out of deployment prompts into per-tool prompt
sections; the examples' workflow paragraph became a tool:<toolName>
section contributed by dsh-tool-workflow (explicit-ask-only policy),
and both example personas resolve to master's minimal identity+behavior
form. tool-workflow gains inject: systemPrompt (+ peer dep, tsconfig
ref); the export-shape guard updated.
- The uniform-RFC-format gate: the dynamic-workflows RFC restructured to
the implemented/ skeleton (bare Status line; Proposal -> Decision;
What-was-rejected -> Alternatives considered; new Consequences), and
the overall-run-timeout deferral is now recorded in the RFC's Deferred
list. The doc-graphs atlas classification gains the workflows seam
(workflow-vm implementation, tool-workflow consumer).
Master's harness-identity section made "empty assembled prompt" states
unreachable through the loop, so the instruction-append is a plain
undefined-ternary and the structured tests assert append-not-replace.
All snapshot goldens (including workflow-run) replay unchanged. Full
local CI-equivalent gate sequence green on the merged tree.
Review round 2 (tianyicui inline comments):
- dsh-system-prompt itself registers the harness:identity (-100) and
deployment:persona (0) sections — they must survive a swapped loop
plugin, so they leave dsh-agent-loop; the persona text is the plugin's
own validated 'persona' config. The model/cwd variables STAY on the
loop: runtime facts of the agents it drives.
- AgentOptions.systemPrompt is deleted with all its forwarding plumbing:
the app configs' systemPrompt keys become 'persona' routed through
dsh-agent-core (schema = z.intersect of the owners'), the ACP bridge
and tool-subagent stop carrying persona configuration, and subagent
children now render the deployment persona like every other agent.
- Example personas drop transport/interface trivia (ACP, CLI) — facts
irrelevant to the model.
- Root CONTEXT.md removed (not idiomatic); its persona definition was
wrong under the new ownership anyway.
- Docs, READMEs, the prompt-variables RFC, and generated catalogs
updated; new loop test pins the assemble-waterfall escape valve
(an emptied assembly sends NO system field).
Reconciliations beyond textual conflicts:
- product rename (DeepSeek Code -> DeepSeek Harness SDK) applied to the
PR-added assertion in system-prompt.spec.ts that master's rename
commit could not reach
- architecture.md: master's rewrite kept; this PR's prompt-assembly
semantics re-added in the new doc's voice (Turn Flow footnote +
service-spine row), within the 1630-word ceiling
- cordis catalog regenerated into master's split events.md/services.md
(events-and-services.md deleted); module graph and doc graphs
regenerated to pick up this PR's new events and dependency edges
A new capability family at packages/workflow/ in the bash seam shape,
modeled on Claude Code's dynamic workflows: the model writes a JavaScript
orchestration script (export const meta = {...} + plain-JS body), a runtime
executes it, and the script — not the conversation — holds the loop, the
branching, and the intermediate results.
- dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary
(WorkflowRun whose result NEVER rejects) + observe-only workflow/* events
carrying data snapshots (id + meta, never the live run), per-listener
contained like subagent/*.
- dsh-workflow-vm: in-process node:vm engine. Meta extraction via a
string/comment-aware scanner (template interpolation rejected; literal
evaluated alone in an empty timed context; statement blanked line-
preservingly so stacks keep script line numbers). Hooks: agent(prompt,
{label, phase, schema, model}) over ctx.subagents, parallel(), pipeline()
(no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline:
hook misuse (unknown/deferred options, bad arguments, unsupported
schemas, tripped caps, seam start failures, cancellation) throws fatal
WorkflowErrors the combinators RE-THROW — never dissolved into the
per-item null reserved for child failures. Realm boundary: inbound values
materialized by descriptor walks that never invoke accessors (defineProperty
copies, __proto__-safe); outbound values rebuilt in-realm via the
context's own JSON.parse. Determinism bans (Date.now/Math.random/argless
new Date) kept so future resume support cannot break scripts. Caps and
timeouts are validated Config. Every hook promise carries a no-op
rejection consumer (app-boot exits on unhandled rejections).
- dsh-tool-workflow: the model-facing workflow tool, synchronous like
dsh-tool-subagent (start → await → try/finally dispose; abort bridged;
non-completed → isError). Generic render card titled by a textual
meta.name sniff. The tool description carries the authoring contract.
Wired into examples/{coding-agent,acp-agent} with explicit-ask-only
guidance. Coverage at every tier: unit (meta scanner, materializer incl.
counting-getter and __proto__ regressions, combinator semantics,
concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon),
integration over the real spawn stack, with-key e2e (real two-phase run +
the tool through the registry pipeline), and a recorded ACP snapshot
scenario (workflow-run, 1 child session). RFC:
docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred
work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's
layout line.
A static harness:identity section at order -100 — the first occupant of
the documented negative band — states that the agent is powered by the
DeepSeek Harness SDK before the deployment's persona renders. Harness
attribution is a harness fact: it lives on the loop plugin, not in each
deployment's persona, so every agent (subagents included) carries it and
no YAML can forget it. A deployment that must drop it can remove the
section in the system-prompt/assemble waterfall.
Order-band docs updated in all five homes (PromptSection JSDoc, the
system-prompt and agent-loop READMEs, architecture.md, the RFC).
The repo's docs are read by people and agents without access to the
company wiki, so external Feishu links are dead weight: the two design-doc
links (MVP requirements, microkernel implementation notes) leave
AGENTS.md's intro and docs/architecture.md (usages + link definitions),
and the microkernel-event-taxonomy RFC drops its plain-text pointer to the
same design doc. The governing principle each reference decorated is
already stated in place; no content moves.
Master split the cordis catalog (d55d4120) while this branch was in review.
Resolution: keep this branch's Service map restructure, adopt master's split
catalog link targets (events.md / services.md), and regenerate the catalog so
the waterfall-semantics anchor fix lands in the split output.
One principle: every fact in the assembled prompt has exactly one owner.
- dsh-system-prompt: merge-extensible AssembleContext on assemble();
a variable(name, provider) registry; {{name}} interpolation in
renderPrompt, strict (unknown/valueless/malformed references throw);
duplicate section and variable names rejected; assembly carries
resolved section text + variables through the assemble waterfall.
- dsh-agent declares AssembleContext.agent; dsh-agent-loop registers
the agent:persona section (order 0 - identity renders before tool
guidance) and the model/cwd variables, and drops its string join:
renderPrompt(assembly) IS the full prompt.
- Tool guidance moves to its owners: descriptions carry per-tool
semantics; sections only cross-call habits (tool:bash exit-code
habit at order 105; read's not-shell nudge). todo/subagent need no
section - their descriptions already carry the contract.
- SubagentProvider.inheritsParentContext (spawn/acp false, fork true);
dsh-tool-subagent derives truthful per-provider wording and resolves
the provider at load (backend must be listed first).
- Example personas shrink to identity + behavior with {{model}} (and
{{cwd}} in the ACP tree); the welcome banner stops enumerating tools.
RFC: docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md
The Layering ASCII diagram was cluttered, lumped THE concrete loop plugin
undifferentiated into a grab-bag plugins box, omitted dsh-agent-core and the
app packages, and restated the dependency rule that packages/README.md
already owns — while being the first thing a reader linked from README hits.
- Drop the Layering section; the tier story becomes one intro sentence and
the dependency rule a one-line Service map footer linking
packages/README.md#dependencies.
- Split the Service map into the spine (packages/core/) vs the swappable
capability seams; annotate ctx.agentLoop as THE concrete loop plugin.
- Promote Cordis waterfall semantics to a top-level section placed before
first waterfall use; drop '(important)' from the heading (anchor swept:
AGENTS.md, gen-cordis-catalog.ts + regenerated catalog).
- Promote Event taxonomy to a top-level section (anchor unchanged).
- Retitle 'The vocabulary (dsh-llm)' to 'Content blocks and streaming
(dsh-llm)' so the heading names its content (citation swept:
llm-streaming.md).
Net -29 words (1851 -> 1822); the 1890 ceiling stands, keeping the
manifest's working margin.
gen-cordis-catalog.ts now emits docs/cordis-catalog/events.md and
docs/cordis-catalog/services.md instead of the combined
events-and-services.md: a reader is either finding what to listen to or
what to call, and each axis now scans and deep-links as its own page.
Headings promote one level (scopes and ctx.<key> entries become H2), the
dispatch-mode legend lives on the events page, and the inherited tier
splits accordingly. --check verifies both files and names whichever is
stale.
Every reference updated in the same change (no compat redirects,
pre-release stance): architecture.md, AGENTS.md, docs/AGENTS.md tier row,
filesystem/subagent core-data-structures pages (the ctx.fs anchor
survives — slugs are heading-level-independent), fs README, four RFCs,
the tool-catalog and persistence-catalog generator intros (both
regenerated), and the bilingual development.md pair (re-recorded).
ImageBlock had no production producer and every consumer dropped it:
the deepseek serializer skipped it, the pi-ai converter skipped it as
unrepresentable, the ACP bridge neither advertises image prompt
capability nor forwards image blocks, and compact-basic charged a flat
85-token estimate and rendered an [image] placeholder. A block
constructed today would silently vanish from the wire — the vocabulary
advertised a capability no path honors, the silent-data-loss shape the
defensive patterns warn against. The only constructors were tests
pinning the skip/estimate branches.
Remove ImageBlock and its ContentBlockMap entry (its cache?: CacheHint
field leaves with it; CacheHint itself and the other two cache? fields
are out of scope). compact-basic loses its explicit image estimate and
placeholder arms (the merge-extensible default arms absorb the case);
the deepseek serializer, pi-ai converter, and ACP codec already handled
image in their default arms, so only their image-naming comments
change. The codec's inbound rejection of ACP-protocol image prompt
content stays — that guards wire content a client can send regardless
of our vocabulary.
Tests that constructed harness image blocks to pin the removed branches
are dropped (the 85-token estimate pin) or retargeted onto plugin-added
block types / other non-text blocks, which the surviving default arms
own. Docs, the type-equiv pastes, and the content-block vocabulary
RFC's block list and multimodal-home consequence are updated in the
same change; the RFC moves to implemented/ and the index is
regenerated. A real multimodal feature reintroduces image via
declaration merging together with the adapter mapping, ACP
advertisement, and compaction pricing that honor it.
agent/steering was the last transient mirror of a durable session event:
drainSteering appended the durable steering/message {turn, content, source}
and emitted the identical fact one line later. Zero production listeners
existed — every steering consumer (hook bridges, goldens, deriveMessages)
reads the durable event — and the one regression test subscriber asserted
a fact the log already records.
Remove the declaration (dsh-agent types + JSDoc list + README row), the
emit in drainSteering (its ctx parameter goes too), and the emit line in
the loop-pseudocode blocks (loop.ts module doc, architecture.md); the
cordis catalog is regenerated. The regression test now pins source
preservation on the durable steering/message event. Live-notification
needs keep their surviving homes: agent/queued at enqueue time,
session/event at drain time.
RFC: docs/rfc/implemented/simplification/2026-07-04-remove-agent-steering-mirror.md
(moved from proposed/, amended to shipped reality). The three implemented
RFCs that stated the retention — the boundary-mirror removal, the
stream-chunk removal, and event-domain-semantics — are amended to point
at that RFC as the record of the removal, per implemented/AGENTS.md.
The rejected retire-mid-turn-steering RFC keeps its frozen text (it
records the declined proposal); the steering capability itself —
steer(), the durable event, continuation forcing — is untouched.
architecture.md is the behavior map: layering, service map, seam
pattern, and the loop — everything else defers to its owning tier.
- Seam narrations compress to two-to-four sentences plus links to the
RFC and type-catalog homes that carry the detail (turn-end variant
semantics -> session.md, derivation mapping -> session.md, StreamChunk
conventions -> llm-streaming.md + source).
- The MVP feature-to-mechanism checklist moves de-statused into the
extension cookbook as 'The feature -> mechanism map' — mechanisms
only, no implementation-status bolding to rot; the microkernel RFC's
proof-obligation pointer follows it.
- The layering diagram describes layers by family instead of
enumerating packages (the stale 'future plugins: hooks, compaction'
row is gone); the dependency rule defers to packages/README.md.
- The loop pseudocode, the three externally-cited anchors (the
vocabulary, event taxonomy, waterfall semantics), and the filename
are unchanged.
- Budget ratchet: docs/architecture.md 3897 -> 1800 (now 1,797 words);
the doc-tiers RFC's deferred list prunes the item this ships.
Use the new filesystem seam for skill file reads and system skill writes when ctx.fs is available, and include the skill tool in the generated tool catalog.
The loop recorded every model token delta as a durable `assistant/chunk`
session event AND emitted an identical live `agent/stream-chunk` Cordis event
one line later. Same StreamChunk, same turn/step; the emit added only the live
Agent handle, which the sole consumer discarded. This is the boundary-mirror
duplication the event-domain work removed for turn/step boundaries, applied to
the token stream — a follow-up the boundary RFC explicitly deferred.
The premise is settled: chunk persistence is authoritative (the proposal to
stop persisting chunks was rejected — replay/snapshots depend on it), so
`assistant/chunk` on `session/event` is the load-bearing token stream and
`agent/stream-chunk` is pure redundancy.
- Remove the `agent/stream-chunk` declaration + emit; drop the now-unused
StreamChunk import from dsh-agent's types.
- Migrate `dsh-ui-stdio` (the only live consumer; ACP already reads
assistant/chunk off session/event) to render assistant/chunk in its existing
session/event listener. Consolidating to one listener also makes the
inReasoning dim-SGR flag deterministic across chunk/boundary events (they no
longer race across two listeners).
- Repoint the agent-loop tests (cancel/loop) and ui-stdio tests to the
session/event assistant/chunk feed.
- New RFC (implemented/simplification/2026-07-02-remove-stream-chunk-mirror);
amend the boundary RFC's retained-list entry to cross-link; update
architecture, cookbook, event-domain-semantics, the ACP proposal, and the
regenerated cordis catalog.
Snapshot goldens unchanged (ACP never used the mirror), confirming no
editor-facing transcript change.
