Files

T

pastilhasandClaude Opus 5 6b8cf848ff a turn this tab did not start is still a turn in progress

"Turn finished · no closing message" kept appearing over an agent that was
plainly still working, with output resuming a moment later.

isGenerating was set in exactly three places: sendPrompt, and the two reconnect
handshakes. So it answered "am I waiting for a reply I asked for", never "is
this conversation working". Every other way a turn begins left it false — a
commander waking on its own schedule, a queued prompt the server delivered,
another tab driving the same session, or a turn that started before this tab
was looking. The events still render, but buildRows reads isGenerating to
decide whether the last turn is finished, so a live turn was `complete` and the
moment it sat on a completed tool call with nothing said after it, the banner
fired. Same gap left the composer enabled mid-turn, and a message typed then
was not marked injected — which splits the live turn and prints the banner a
second way, the exact failure injected exists to prevent.

session:claude now sets it: the harness's own turn-start signal, and the only
one that arrives before any work does. tool:start sets it too, because
session:claude is not durable and a socket connecting mid-turn never receives
one, while a tool cannot start outside a turn.

Two candidates were measured rather than argued. A genuinely silent turn ending
earns the banner honestly, but 667 of 673 recorded turns end with
assistant:text immediately before result, so that is ~1% and cannot be it. And
a stale sync:live is real but rare: correlating every attach in the officer log
against the agent's own later output, 15 of 549 "not generating" attaches were
contradicted and one provably so. That residue is left alone — the tool:start
fallback now corrects it on the next event — and noted on the refresh card,
which is the same seam.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Officer-Session: f7a62308-0977-4cf4-aa29-c020853fd420

2026-08-25 15:27:49 +00:00

5.9 KiB

Raw Blame History

TODO — the index

Deferred work. The items live in todo/, one file each, grouped by theme; this file is the map over them and is GENERATED — run bun run todo:index after any change rather than editing it here. Format and the two-way-sync contract: todo/README.md. Browse and edit it at /todos in the app.

Context, corrected 2026-08-07. This list used to open by saying Officer was "collapsing from multi-tenant / open-source-ready to a single-user platform", and told you to treat multi-tenant indirection as accidental complexity. That direction was reversed. The permission model shipped on 2026-08-07 to serve a real goal — deploy to the company server, onboard people, give each one their own Gitea account through the platform. Per-user scoping is now a requirement, and the items that proposed deleting it have been removed rather than left to mislead the next reader.

What did NOT reverse: execution permissions (terminal, chat, tasks, files, desktop, browser) run as the owner's OS user and can never be granted. Indirection there really is accidental complexity.

Urgent

due 2026-08-22 — Settings to choose which server each feature uses — fleet/settings-to-choose-which-server-each-feature
An affordance: a scoped agent warns when a request lands outside its scope — affordances/an-affordance-a-scoped-agent-warns-on-the

Themes

97 open, 31 closed, across 32 themes.

Theme	Open	Closed
Affordances	2	0
Agents coordinating agents	3	0
Speaking into a session from the backend	1	1
Backburner	3	0
Background jobs	2	1
Chat interface	1	0
Code editor	1	0
Components — the shared UI layer	1	0
File watchers	1	0
Fleet — one command across every server	5	2
Headscale	0	5
Infra (alpha)	7	0
Known bugs	5	4
Memory — one store instead of per-harness files	1	0
Mobile apps	4	0
Multi-user	17	5
Notifications	1	0
Plugin ecosystem — before it opens to third parties (2026-08-18)	3	0
Plugin infrastructure	2	0
Plugin repos — what writing their READMEs turned up	10	9
Plugin system — gaps the email extraction found (2026-08-18)	3	0
Prompt library	1	0
SendOff	1	0
Settings — portable, and readable by an agent	2	0
Shell — spotlight and the dock	4	1
Sub-agents — agents spawning agents	0	2
Sudo terminal modal	1	0
Tooling — the list about the list	0	1
Transmission	6	0
URL state — routing, query strings and selection	4	0
Waiting on the owner to run it	3	0
Workspaces & Panels	2	0

Records — no items, kept for the reasoning

Newest ten

2026-08-25 An affordance: a scoped agent warns when a request lands outside its scope — affordances/an-affordance-a-scoped-agent-warns-on-the
2026-08-25 Commit signing is inconsistent across harnesses — Claude names itself, opencode names nothing — agent-coordination/commit-signing-is-inconsistent-across-harnesses
2026-08-25 Resurrect Projects/Apps — backburner/resurrect-projects-apps
2026-08-25 Refresh mid-turn folds the live tool call — it reads as finished while still running — known-bugs/refresh-mid-tool-call-renders-the-turn-folded
2026-08-25 The model picker shows claude-code instead of the model that is running — known-bugs/the-model-picker-shows-the-bare-harness
2026-08-25 Understand how Claude and opencode do memory, then centralize both into one vector database — memory/understand-and-centralize-agent-memory-into-a
2026-08-25 Deep-link a todo notification straight to that item's markdown — mobile-apps/deep-link-a-todo-notification-to-its-file
2026-08-25 Add a favorites tab/panel to the file browser — multi-user/add-a-favorites-tab-panel-to-the-file-browser
2026-08-23 A worker cannot verify that the owner delegated to a manager, so it has to ask every time — agent-coordination/a-peer-cannot-verify-a-delegation
2026-08-23 An agent cannot learn its own transcript id, so it cannot sign its own work — agent-coordination/an-agent-cannot-learn-its-own-session-id