The three-entry cordis.yml (dsh-sandbox-local + dsh-bash-sandbox at a
read-only default + dsh-approval) served over ACP: the first live approval
composition. Recorded snapshot scenarios pin the wire end to end —
config-options advertisement, the mode-switching arc as the suite pinned
header (both switches, the prompt-section delta, one changed-by-the-user
notice per knob, a confined write landing under the switched mode), and
both escalation branches over scripted permissionAnswers (a grant runs
confined under workspace-write; a rejection executes nothing and pins the
fail-closed text). The with-key escalation e2e drives a real model +
real runner + the real bridge answerer, world-verified; ci.yml snapshot
lane and e2e.yml install bubblewrap so the confined replays actually
execute.
Both RFCs move to implemented/ (Decision/Consequences form, deferred
phases tracked in their own sections), with every cross-reference flipped.
ctx.sandbox (dsh-sandbox): confine(argv, policy) returns the argv to spawn
instead — wrapped so the process and its children run confined — plus the
enforcement completeness and the backend denial/runner-failure dialects;
no usable backend throws the fail-closed SANDBOX_UNAVAILABLE. Policy rides
per call. dsh-sandbox-local selects by platform and caches the verdict:
multi-candidate chains probe FUNCTIONALLY in preference order (Linux:
bwrap → the registry-installed node-addon-landlock-run launcher), a sole
candidate is selected unprobed (darwin: sandbox-exec/Seatbelt) and fails
closed at execution via runnerFailureSignatures; win32 is a reserved empty
chain. Profile parity is honest per backend (documented temp-area and ABI
differences; enforcement full|partial is a structured result fact).
CI: the sandbox-e2e matrix proves real-kernel confinement per rung (bwrap,
Landlock per architecture through the registry-installed launcher,
Seatbelt), failing on a silent all-skip; the packed-install rehearsal
installs the launcher family from the registry and asserts the binary
executable apart from kernel enforcement.
Everything outside the package and example that a new top-level group and a
new demo touch: GROUP_ORDER in gen-module-graph and gen-doc-graphs (plus the
tools-service consumers list, the APP_EXAMPLES entry, and the graph-atlas
label/mode rows), the knip e2e entries, the packages/README group row, the
AGENTS.md layout and demo lines, and the regenerated module-graph /
config-catalog / graph-atlas / capability-seams / composition artifacts.
AGENTS.md and examples/AGENTS.md word-budget ceilings rise to current+5%
(1802 / 653): the new group and demo rows are genuine additions to both docs,
not condensable restatements.
The master merge added a code-runtime/ package row while this branch adds
the timeout/ row; together they push packages/README.md over its 605-word
ceiling. Condense the timeout/ row to the terse sibling style and raise the
ceiling 605->610 for the genuinely-new package group, mirroring how the
code-runtime work raised architecture.md's ceiling in the same spirit.
New group packages/code-runtime/ with the interface package
@deepseek-ai/dsh-code-runtime, per the Code Mode RFC: abstract CodeRuntime
service (run() resolves program failures as an error field, rejects only
for seam misuse), the CodeRunRequest/CodeBindingNamespace/CodeRunResult/
CodeLogEntry/CodeRunFailure vocabulary, and readonly language/isolation
backend descriptors. Registered in the tsconfig maps, packages/README,
architecture service map, and the doc-graph service-role classification;
catalogs regenerated.
The RFC's one forward path token to the worker package becomes an npm-name
mention until PR3 creates that directory (verify-package-paths is
drift-scoped: the now-existing group made the token checkable).
docs/architecture.md ceiling 1630 -> 1640: the doc gained a genuinely new
capability-service row; the row itself is already minimal.
Exact-size ceilings turned every two-word wording fix into a gate
event. The policy amends to: a ceiling sits at least 5% above the
doc's current size (pre-rewrite) and keeps that margin when ratcheted
to target — routine edits pass, real growth still trips the gate.
Amended together in all four policy homes (docs/AGENTS.md § Budgets,
the doc-tiers RFC, the gate script's module comment, the skill's
ratchet rule) plus the manifest values, so prose and mechanics stay
consistent.
The gate joined the doc-sync chain in this PR; the root file's two
enumerations of that chain must name it in the same change. The frozen
ceiling re-records the exact new count (8134).
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.
- The manifest now freezes each budgeted doc at its exact current wc -w
count, matching the documented policy (a ceiling starts at the doc's
current size); the headroom that contradicted the freeze claim is
gone. Post-rewrite ratchets may still land at new-size-plus-headroom,
per the skill's ratchet rule — that is a different moment than the
initial freeze.
- --list now renders MISS/BAD rows for missing files and malformed
ceilings instead of silently dropping them (gate mode already failed
correctly; the report mode no longer under-reports).
Applies the documentation standard to its biggest offender. Every rule
survives as one to three lines plus a link to its durable home; the
stories, duplicate statements, and re-narrations go:
- Situational clusters evict to new homes: docs/testing.md (tiers,
with-key policy, real-over-mock, world-verification, real-entry-path
guards), docs/defensive-patterns.md (the bug-class rules), and
docs/cookbook/responding-to-pr-review-on-a-stack.md (the stacked-PR
review procedure).
- Doc-authoring rules consolidate into docs/AGENTS.md § Writing rules
(current-state-never-history, md-wrap, ts-block compilation, @mode,
catalog same-change, pair same-change).
- packages/README.md drops to the group table + the extension-vs-bundle
dependency rule; the hand ASCII graph yields to the generated
module-graph.md; group READMEs are the canonical per-package map.
- packages/AGENTS.md keeps only its packages-specific rules (export
shape, ctx.get, real-Loader coverage); examples/AGENTS.md repoints
its with-key-policy link; rfc/README.md loses a narrated-history
aside; dsh-code-review / dsh-find-simplifications / verify-md-wrap
references follow the moved content.
- Budget manifest ratchets: AGENTS.md 8200 -> 1500 (now 1,495 words),
packages/README.md 1900 -> 600, packages/AGENTS.md 600 -> 450; the
two new eviction docs join the budget set (testing 800, defensive
550); docs/AGENTS.md raises 1000 -> 1250 for the absorbed writing
rules (the one justified increase). The doc-tiers RFC's deferred list
prunes the two items this change ships.
Standing docs accrete a paragraph per PR with nothing pushing back; the
root AGENTS.md reached 8,130 words in 50 commits with the same rule
stated two and three times. This encodes the counter-pressure:
- docs/AGENTS.md becomes the documentation standard: the tier taxonomy
(one home per fact), target word budgets, and the slop checklist.
- verify-doc-budgets joins doc-sync: word ceilings for the six
accretion-prone standing docs, manifest-driven, frozen at current
sizes and ratcheted down as each doc is brought to target.
- .agents/skills/dsh-doc-standards: the thin placement/audit/red-gate
workflow over the standard, mirroring the dsh-translate-docs split.
- RFC (implemented/process) records the decision, alternatives, and
the first audit cycle's deferred work list.
The gate's first catch was the standard itself (1,057 > 1,000); it
ships condensed to 984 words rather than with a raised ceiling.
