Tool and prompt-section visibility is inherited along dsh-scope's parent
chain, and an agent's scope key is minted with no parent. Per-session agent
presets moved every model-facing row onto the agent plane and made
AgentPresets.mount() the one thing that binds that link, from the api-proxy's
session create, resume, and fork paths. The two in-process subagent drivers
installed only the per-child persona and tool filter, so a child's scope chain
had length one and its registry view resolved the global layer alone — which
is empty wherever a preset roster is composed. One-shot children reached the
model with no tools, continuable ones with only the host-plane `report`, and
neither carried its parent's persona, workspace context, or skill catalog.
AgentPresets.composeFrom() joins one agent to the standing composition another
already runs on. It is a bind, not a mount: the child gets its parent's exact
generation, so a composition edited since the parent started cannot fork it
onto another one, and it is synchronous, which is what lets a child creation
window use it. applyChildComposition() now takes the parent and performs the
join first, making a child composed without it unrepresentable at the call
sites. childSessionMeta() records the joined id so a cold read rebuilds the
composition the child actually ran under.
The audit that followed found two api-proxy readers on the wrong authority:
presenterScopeFor() and the live-agent branch of assertPresetUnchanged() both
read header.agentPreset, which goes stale the moment a blank session switches
preset. A switched session's cold transcript resolved presenters in the older
composition's layer and silently degraded to generic cards, and the gateway
refused to adopt a live session under the preset it actually runs while
accepting the one it left. Both now resolve through resolveSessionPreset(),
matching the resume branch fifteen lines above. The owning architecture Agent
Note carried the stale claim that the header records what a session runs; it
is corrected to name the header/log pair and its three readers.
Fixes#2165
The skills capability moves back to the host plane as one singleton, layered
with the ScopedLayers infrastructure the tools registry established: a
registration files into its calling context's layer (repository plugins and
host rows land global, a preset's skill-local lands in that preset's layer),
and a read merges the global layer with the viewing scope's chain, the
nearest layer winning duplicate names outright while rank keeps deciding
duplicates within one layer.
The web-app bundle re-enables the base skill registry row (skill-local and
tool-skill stay preset-owned), the standard preset drops its isolate skills
realm for bare rows over the host registry, tool-skill passes the calling
agent as the view scope, and the gateway's skills domain reads the host
registry in the presenter scope — a cold session now resolves its recorded
preset's standing key instead of failing.
The merge-forward took the parent's module-graph verbatim; the merged
tree adds the sandbox-windows-acl package and dsh-session edges.
verify-module-graph is a ci-static gate, not in local doc-sync.
Move the triplet to implemented/architecture/, rewrite Proposal into a
present-tense Decision, fold Acceptance criteria and Risks into
Consequences (recording what pins the result), retitle the migration
section to what the move actually touched, and repoint the seven
inbound FIXME/README links.
- restore the parent's AGENTS.md body around this branch's e2b row (the
replay had resurrected the pre-profile-CLI layout, deleting the api/,
bundle/, settings/, and credentials/ groups); the fs/lsp row
condensations stay for the word budget
- aggregate the composite rollback failure, not the original error, when
private state cleanup also fails — a surviving remote group is no
longer hidden by a later cleanup error (triple-failure regression)
- own the state directory before the makeDir RPC, matching the terminal
transaction, so a cancellation racing a committed creation still
enters cleanup
- drop the hidden pollMs parameter defaults; the schemastery default is
the one home, and tests pass the cadence explicitly
- restore spawn/spawnTerminal graceMs validation to the seam's
documented bound (the earlier removal cited subprocess-local as not
validating; it does), with rejection regressions
Master turned THIRD_PARTY_NOTICES.md into generator output (the branch's
hand-added e2b row carried a stale dotenv entry), and the cascade's
ours-side resolution flattened the module graph to the parent's content;
both regenerate from the current tree.
Restores master's vitest config and packages-README pairing record (the
replay had carried old-lineage copies; this branch claims neither), and
regenerates the doc graphs, catalogs, and architecture pairing the
replay's ours-side resolutions had flattened to master's content.
Yichen Jiang
Turtle
creatixchu
Huanqi Cao
imccyu
Tianyi Cui