Owner queue

blocking · spec:hq.context#question.clientMaterial

How is client material handled, project by project: what is screened, and where?

holds spec:hq.context, spec:decisions.client-material-deferred

non-blocking · spec:cc-agents.adapter-contract#question.capKeyMeaning

CONTRACT.md says the cap key names the account a turn spends, while the code keys Codex by one machine-wide bucket named codex and OpenCode by opencode:<provider>, which does not identify distinct accounts.

Provisional: The key is whatever capFor returns; nothing establishes credential identity.

holds no Specs

non-blocking · spec:cc-agents.codex-adapter#question.fakeAppServer

These behaviours are exercised against a fake app-server that speaks Codex's protocol; a real Codex is exercised only by the live suite under tests/live, which runs outside the graph and outside the gate.

Provisional: The unit evidence stands for the protocol; the live suite remains the check against a real Codex.

holds no Specs

non-blocking · spec:cc-agents.codex-adapter#question.perAccount

The README calls the Codex cap per account, while the adapter keeps a single machine-wide bucket named codex whose default is the machine's share.

Provisional: Described here as a machine-wide bucket; no account identity is established.

holds no Specs

non-blocking · spec:cc-agents.coordination#question.bridge

Should messages that cross an operating system boundary by a route outside the host's own messaging be recorded and joined to a chain, and how does a lead on another operating system reach its parent's tree?

Provisional: This release's tree covers records on the local machine only, and an external parent is shown as an unresolved boundary. Cross-operating-system delivery remains outside this release. The existing cross-machine route stays until a separate bounded measurement shows how a join and a report cross it. No distributed service is built.

holds no Specs

non-blocking · spec:cc-agents.coordination.record#question.clientText

Should the record hold the full text of messages in a project whose material is confidential?

Provisional: Yes, because attribution needs the text. The record stays on the machine where the session ran, and recordText set to metadata for a project replaces the text with its length and hash.

holds no Specs

non-blocking · spec:cc-agents.coordination.record#question.auditGrade

Does the owner need crash-proof durability, an audit-grade log?

Provisional: No. The record is observational with stated coverage limits, and a stronger write path waits until someone requires it.

holds no Specs

non-blocking · spec:cc-agents.installation#question.invisibleToTheGraph

The marketplace, the manifest and the install script are JSON and shell, so no anchor binds them and the graph derives neither implemented nor has-verifier here; the install test run is npm run test:install.

Provisional: The Spec stays at defined until a node test asserts the manifest and options, which would carry a test anchor and the documented realization.

holds no Specs

non-blocking · spec:cc-agents.installation#question.linuxClaim

The README says Linux was not tried live, while a smoke run proved basic execution there; the sentence is broader than the evidence.

Provisional: Basic execution on Linux is evidenced, and the pane and the machine guard under load there are not.

holds no Specs

non-blocking · spec:cc-agents.mod-layer#question.stepLabel

The steps hand over through an internal progress tool call, so a step shows its progress only when it ends, every 20 seconds by default, never token by token.

Provisional: Kept as built; Claude Code buffers output until a step ends.

holds no Specs

non-blocking · spec:cc-agents.model-templates#question.refusesNothing

The README says the templates refuse nothing, while two quality templates still say never to use Opus on search; the correction waits with the source the templates are generated from.

Provisional: The templates are described as data copied from their source; the prohibition is that source's to remove.

holds no Specs

non-blocking · spec:cc-agents.opencode-adapter#question.pollingCost

Reading the transcript once a second means text arrives a paragraph at a time and each read is a process; a streaming transport that needs a stored pairing credential was not adopted.

Provisional: Polling stays, and the adapter holds no credential.

holds no Specs

non-blocking · spec:cc-agents.opencode-adapter#question.fakeService

These behaviours are exercised against a fake OpenCode service; a real service is exercised only by the live scripts under tests/live, outside the graph and the gate.

Provisional: The unit evidence stands for the protocol; the live scripts remain the check against a real service.

holds no Specs

non-blocking · spec:cc-agents.opencode-adapter#question.yoloRefused

OpenCode refuses the mode yolo, which the Relay-compatible job header accepts for every backend, so a Kimi, Grok or ZCode job that states yolo is refused by the check; no test pins that pairing.

Provisional: Described as built.

holds no Specs

non-blocking · spec:cc-agents.pane#question.untriedSurfaces

The Desktop band, the VS Code extension and Linux were not tried in a real session; the pane is verified against scripted status answers and mod mounts only.

Provisional: Only the surfaces the tests mount are claimed.

holds no Specs

non-blocking · spec:cc-agents.relay-job-type#question.writeNotYolo

Relay's job defaulted to a sandbox-free mode, while this agent defaults to write and runs without a sandbox only when the header states yolo.

Provisional: Write by default, with a note in the state block, as built.

holds no Specs

non-blocking · spec:cc-agents.relay-job-type#question.opencodeBackendsAndYolo

Backends kimi, grok and zcode run on OpenCode, which refuses yolo, so a job that states yolo on those backends is refused by the check; no test pins that.

Provisional: Described as built.

holds no Specs

non-blocking · spec:cc-agents.runner#question.teams

Agent-team teammates are refused by design for now, and the question of whether they should ever be supported is deferred.

Provisional: A foreign agent runs as a subagent only; the mod denies a spawn that asks to be a teammate.

holds no Specs

non-blocking · spec:cc-agents.runner#question.nativeGrok

Grok runs through OpenCode only; a native adapter for it was left for later.

Provisional: Every family other than GPT goes through the OpenCode adapter.

holds no Specs

non-blocking · spec:cc-agents.sidecar#question.insideTheProcess

The README says the agents run inside the Claude Code process, while the code runs them in a detached sidecar and separate harness processes whose lifetime is tied to the host.

Provisional: The code is the truth; the README sentence needs a correction in the documents.

holds no Specs

non-blocking · spec:cc-agents.work-containment#question.detachedBeforeScan

A process that leaves the guard's group and is reparented to the system between two scans is in no record, so the guard neither ends it nor counts it. Should the guarantee grow to cover it?

Provisional: No. The guarantee covers the guard's group and the groups a scan recorded; a descendant that detaches and is orphaned within one scan interval, two seconds by default, escapes cleanup and accounting. Covering it needs a code change, such as a process-tree watcher or an operating-system containment feature, and none is made here.

holds no Specs

non-blocking · spec:hq.infra#question.rollbackPoint

Where did infra's orchestration trouble start, at the takeover of PR #13 where Kimi K3.1 replaced Opus 5.5 or earlier, and which earlier delivery does infra's tooling roll back to?

holds no Specs

non-blocking · spec:hq.infra#question.takeover

Is HQ ready to take over infra, and what must hold first?

holds no Specs