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.
Master rewrote the headless README around the profile CLI and removed
cli-demo; the replay had resurrected the old body. The branch's claim is
the E2B overlay section alone, now inserted into master's text with the
credential-gated live composition e2e as the runnable instruction (the
config-file demo runner no longer exists).
The linear replay carried old-lineage content over parent-owned files;
this checkpoint restores them and adapts the branch to the parent's
post-rebase seam:
- restore all pty/lsp/subprocess/code-runtime surfaces to the parent's
exact content (this branch claims none of them) and drop the net-zero
code-runtime-e2b/pty-e2b/lsp-e2b residue and its registrations
- widen serializeRemoteEnvironment to the seam's NodeJS.ProcessEnv
tombstone contract: an explicit undefined removes an ambient entry
- migrate the two E2B fixture Agent stubs to the Inbox-model interface
and Session.create
- re-apply the branch's gen-doc-graphs roles, THIRD_PARTY_NOTICES e2b
row, and packages/README group row (trimmed to the doc budget);
regenerate catalogs and re-record bilingual pairings
Master's steering-receipt API (agent.steer returns SteeringReceipt) reached
this branch through the parent sync; the two E2B live-fixture Agent stubs
return the same rejected-outcome receipt the pty test stubs use.
- subprocess-e2b: the 20 ms remote poll cadence becomes a validated pollMs
Config field (each tick is one control-plane request); the README documents
the latency-versus-request-count trade.
- subprocess-e2b: extract src/remote.ts owning asError, signalOpts,
commandOpts, delay, waitTick, and one tolerant signalRemoteGroups shared by
the pgid-keyed process ladder and sid-keyed terminal ladder, so the two
teardown paths keep identical error tolerance.
- subprocess-e2b: service disposal aggregates sibling cleanup failures into
one AggregateError instead of discarding all but the first.
- subprocess-e2b: waitForProcessGroupId refuses published group ids <= 1, so
a same-UID rewrite of the pid file cannot aim termination at kill -- -1;
README documents the same-UID control-state limitation.
- subprocess-e2b: drain-grace expiry now releases an inherited-output E2B
callback blocked on host backpressure before disconnecting, so the SDK
settlement cannot stay pinned behind an unread host stream.
- subprocess-e2b: spawn/spawnTerminal stop validating typed spec fields
(trust-TypeScript rule; pty-local validates its config before specs exist);
resolveExecutable rejects separator-containing relative paths per the seam
contract; terminal setups tracked as a Set of records.
- subprocess-e2b: PTY output push-without-backpressure is a documented
contract (flowing consumer folds bytes; paused consumer buffers).
- fs-e2b: streamText normalizes the pinned SDK's empty-file '' return into an
empty stream instead of throwing on getReader().
- e2b overlays: comment the one-world cwd invariant across e2b.cwd,
workspaceRoot, and bash-local's implicit default workdir.
interrupt_agent(agent_id) passes the calling agent as the ancestor
authority for ctx.subagents.interrupt(); the service verifies live
registry identity and recorded lineage, so a direct child or deeper
descendant stops with the same generic parameter while send_message keeps
its exact-direct-parent authority.
Discovery: list_agents gains an optional scope. descendants walks the new
SubagentService.listDescendants() — one lineage trace flattened in stable
pre-order across ordinary and one-shot intermediates, each entry carrying
its verified parentId and depth — and every status now comes from the
live Agent registry (running/idle/complete).
Refs #1535
Both catalog renderings now tell the model that a directly invoked skill
arrives as an inline <skill_content> block to follow without re-loading it
through the skill tool — the seam rule that keeps the user-explicit path
and the model-autonomous path from double-injecting one skill.
