Self-review findings, all prose/metadata (no behavior change): the
package description still claimed hard (execution) enforcement; the RFC
Problem framing still defined plan mode as a read-only tool policy;
integration/mode/snapshot-suite comments still referenced the removed
sandbox clamp and cap; the header-fallback explanation said
'front-of-list insertion' where the actual mechanism is a non-tail
insertion the append-only tools delta cannot express (exit_plan_mode
sits mid-list alphabetically); AGENTS.md's layout line and the RFC's
'policy state/listener' phrasing move to collaboration-state wording.
Review follow-up (tianyicui): plan mode and the sandbox are orthogonal
AXES, not just orthogonal state — entering plan must not change what the
sandbox enforces, matching Codex's separation of Plan/Default
collaboration presets from sandbox and approval settings.
ModeDefinition.access, the bash/resolve-mode clamp, and both cap-derived
guards are removed; a ModeDefinition is exactly { section }, and a mode
now carries only its guidance section plus the exit_plan_mode review.
The bash seam's resolveMode + waterfall go with their only listener:
dsh-bash and dsh-tool-bash revert to master byte-for-byte, and the
dsh-mode → dsh-bash dependency edge is gone. A deployment that wants
kernel-enforced read-only planning pairs the mode picker with the
independent sandbox-mode option, in either order.
The RFC archives this as the second removed enforcement shape (after
the interim allowlist) with the same restart trigger — effects
self-declaration; the orthogonality FAQ now answers with the two-axis
rule. The plan example demonstrates the axes side by side, and the
re-recorded fixtures pin the guidance-only section.
toolPairingBalancedAfter previously answered by resolving a cached
positional successor and reading its before-balance, with a null-successor
depth fallback. Both queries are the same prefix property sampled at
adjacent cuts, so the cache now holds one per-cut balance sequence
(N nodes -> N+1 cuts) plus a seq->position index; before/after differ
only by a cut offset. The successor map, the duplicate rebuild/extend
fold loops, and the non-null assertion are gone, and the running counter
is named inProgressToolCalls. Docs describing the successor mechanism
are updated in place.
Semantic resolutions beyond line merges:
- The bash seam keeps resolveMode + the bash/resolve-mode waterfall on
master's task-free BashExecutor (run/start/resolve only; BashProcess
handles); tool-bash consults it at its stamping site and escalation
baseline on master's render/background split, with a waterfall test on
the recording executor.
- dsh-mode's BASH_FAMILY narrows to ['bash']: bash_output/bash_kill are
replaced by the kind-generic task_output/task_kill, which span every
task kind and only observe or stop work, so the access cap withholds
only the starter it can reason about.
- The plan-mode snapshot suite adopts master's pin grammar (tool-schema
sidecars; the expectedHeaderSnapshots extension is gone — the exit
transition deltas, and entering-before-turn-1 needs no second
snapshot); modes-advertise joins the plan header class (no-model, so
membership is vacuous). Fixtures re-recorded on the acp-demo bin;
the replay overlay gains the passthrough sandbox runner.
- examples/plan-acp-agent rewires to @deepseek-ai/dsh-acp-demo and drops
its tool-bash entry (the spine bundle now composes it); dsh-stdio (the
renamed stdio-chat home) keeps its /mode command and gains the dsh-mode
peer edge; the acp bridge keeps the modes surface beside master's
permission presets.
- mode README gains the Model Experience / Known Limitations sections the
new README gates require; AGENTS.md ceiling 1370 → 1440 for the kept
mode/ layout line and Agent efficiency section.
The background-task change repeated its lifecycle design across implemented RFCs, package READMEs, JSDoc, test commentary, and model-visible schemas. That repetition obscured the contracts that maintainers must preserve and added avoidable prompt tokens.
Rewrite the implemented RFCs around the current design, keep authorization, exact-owner cleanup, wait/abort ordering, producer quiescence, and teardown-failure guarantees at their owning surfaces, and remove peer surveys, review history, control-flow narration, and emphatic restatement.
Shorten the task and subagent schema wording, synchronize the bilingual tool cookbook, and regenerate the config, service, RFC, tool, and replay snapshot derivatives. Runtime behavior is unchanged; test edits update prose-only assertions and descriptions.
Repair cross-group README links whose targets changed groups
(ui/jsonrpc, ui/app-boot -> examples; examples/* -> ui seams),
re-record the bilingual-pair consistency hashes for the docs the
rename touched on both language sides, and condense the AGENTS.md and
packages/README.md group entries. The packages/README ceiling rises
710 -> 760 for the mandated new examples/ hierarchy row (5% headroom).
Move the agent-spine bundle and the stdio/ACP/JSON-RPC app packages out of
core/ and ui/ into a new packages/examples/ group, renamed with a -demo
suffix so the npm name marks them as non-product surface:
core/agent-core -> examples/agent-spine-demo (dsh-agent-spine-demo)
ui/stdio-agent -> examples/stdio-demo (dsh-stdio-demo)
ui/acp-agent -> examples/acp-demo (dsh-acp-demo)
ui/jsonrpc-agent -> examples/jsonrpc-demo (dsh-jsonrpc-demo)
Update every code/config/test reference and reference-only doc mentions, and
regenerate module-graph, config-catalog, and doc-graphs. The jsonrpc bin
(dsh-jsonrpc-agent) and single-file exe (dsh-jsonrpc-agent-pkg) keep their
names; the SDK runtime-startup surface is reconciled separately.
Bring PR #219 onto current master before re-evaluating review findings so fixes are tested against the code that would actually land.
Resolve generated catalogs by regeneration, preserve the new ACP tool-schema sidecar format while refreshing affected snapshots keylessly, and update the newly paired Chinese adding-a-tool document to match the background-task guidance. This keeps generated and bilingual artifacts authoritative instead of choosing one conflict side blindly.
