diff --git a/docs/operations.md b/docs/operations.md index ddf1c4d..2d4b638 100644 --- a/docs/operations.md +++ b/docs/operations.md @@ -37,7 +37,7 @@ A task's `merge_title` is the title of the squash commit Merge makes. It is the A task's participants are the users who put a message bubble with their name in its transcript, derived from its events (`Store.Participants`): the actors of its `user.message` events, joined to `users` so `byre` and `agent` drop out. That covers messages sent to the agent and inbox answers, whose delivery message carries the name of the first responder in it (`Deliver` in `internal/agents/inbox.go`); dismissing an item puts nothing in the transcript and doesn't count. A fork's participants also include the user who forked it, the actor of its `task.created` event (whose payload carries `forked_from`), whose "forked this task" note opens its transcript. They are ordered by their first such event. `GET /api/tasks/{id}/co-authors` returns the participants other than the caller, with their git name and email from `PUT /api/me` (empty for a user who hasn't set one). The Merge confirm fetches it and lists `Name ` for each co-author, and separately those with no git identity, who get no trailer. -`POST /api/tasks/{id}/merge` starts the same turn, with the prompt's closing invitation to revise the title left out since the human just confirmed it, and records in `tasks.merging_by` that the task is to be merged by the requesting user, who must have a git identity (400 otherwise). Every turn end of the task's session reads and clears it. It survives a byre restart during the turn: startup resumes the session with the restart notice, and the merge happens when that resumed turn ends. When that turn ends normally (not interrupted, not an error), byre squashes the worktree, now containing the default branch, onto it with `git merge-tree --merge-base`, makes one commit titled with the task's `merge_title` with `git commit-tree`, authored and committed by the merging user with no agent attribution, its body one `Co-authored-by: Name ` trailer per co-author with a git identity (`squashMessage` in `internal/agents/mergein.go`; the co-authors are computed when the squash runs, relative to the user who clicked Merge), and pushes that commit to the default branch on the `origin` remote of the project's checkout together with its note (below), in one atomic push (`git push --atomic --porcelain origin :refs/heads/ :refs/notes/byre`, run in the checkout), so either both land or neither does. Only once the push is accepted does it point the checkout's `refs/notes/byre` at the notes commit, run `git merge --ff-only` in the project's checkout (which must have the default branch checked out) and close the task; the `task.merged` event carries the commit and `pushed` (`origin/`), and the transcript shows both. When the merge changes nothing, no commit is made and nothing is pushed. +`POST /api/tasks/{id}/merge` starts the same turn, with the prompt's closing invitation to revise the title left out since the human just confirmed it, and records in `tasks.merging_by` that the task is to be merged by the requesting user (emitting `task.merge_started` with that user as actor, not drawn), who must have a git identity (400 otherwise). Every turn end of the task's session reads and clears it. It survives a byre restart during the turn: startup resumes the session with the restart notice, and the merge happens when that resumed turn ends. When that turn ends normally (not interrupted, not an error), byre squashes the worktree, now containing the default branch, onto it with `git merge-tree --merge-base`, makes one commit titled with the task's `merge_title` with `git commit-tree`, authored and committed by the merging user with no agent attribution, its body one `Co-authored-by: Name ` trailer per co-author with a git identity (`squashMessage` in `internal/agents/mergein.go`; the co-authors are computed when the squash runs, relative to the user who clicked Merge), and pushes that commit to the default branch on the `origin` remote of the project's checkout together with its note (below), in one atomic push (`git push --atomic --porcelain origin :refs/heads/ :refs/notes/byre`, run in the checkout), so either both land or neither does. Only once the push is accepted does it point the checkout's `refs/notes/byre` at the notes commit, run `git merge --ff-only` in the project's checkout (which must have the default branch checked out) and close the task; the `task.merged` event carries the commit and `pushed` (`origin/`), and the transcript shows both. When the merge changes nothing, no commit is made and nothing is pushed. Before starting the turn, Merge runs `git fetch origin` (every configured refspec, so the notes too) and `git merge --ff-only origin/` in the checkout, so the agent merges in what the remote has; the request waits for the fetch, and a failure (network, or a checkout with commits the remote lacks) is returned as the request's error. If the push is still refused, for example because someone pushed during the turn, or fails for any other reason, byre files the error in the inbox and the task stays active; clicking Merge again fetches and goes round once more. A refused push leaves the checkout's default branch where it was, since the squash commit was never moved onto it. If the squash fails, for example because the default branch moved again during the turn, byre also files an error and the task stays active. The agent calls `stop_merge` (`internal/agents/mergein.go`) with a `reason` when its conflict resolution took substantive changes: it clears `merging_by` and releases the project's merge at once, and records a `task.merge_stopped` event carrying the reason, which the transcript shows as a note. The turn then ends without a squash, the task stays active, its snapshot is reviewed, and the human clicks Merge again when satisfied. Called with no merge pending (a Sync turn, say), it changes nothing and tells the agent so. An interrupted or failed turn, an agent process that exits mid-turn, or a session that can't be resumed after a restart clears `merging_by` and leaves the task active without squashing. `POST /api/tasks/{id}/discard` removes everything without merging. @@ -145,10 +145,10 @@ Each user has one long-running lead agent, shown in the left pane. It is not tie - **Sessions.** A lead session is an `agent_sessions` row with `owner` set to the user's login, `role` `lead` and no `task_id`. Its events carry `owner` and no project or task. It runs in `leads/` with `leadGuidance` (passed and re-attached the same way as a task agent's guidance) and the lead tools instead of the task tools. It has no Stop-hook bounce, no snapshots, no end-of-turn commit and no turn summary; a turn that ends in error records the error on its `session.state` event, which the pane shows as a note. - **Messages.** `POST /api/me/lead/messages` sends the caller's message to their lead, starting a lead session when there is none. While the lead is mid-turn the message is held in `lead_inputs`; the lead's PostToolUse hook (Codex: `turn/steer` after each completed tool item) hands held messages over after its next tool call, like a task's queued messages (see "Agent sessions"), and any still held become its next turn. Signals are never handed over mid-turn. The composer stays enabled. `GET /api/me/lead/sessions` lists the caller's lead sessions; interrupt and compact use the usual session endpoints. -- **Signals.** Every published event goes through `Manager.Observe`. These become signals in `lead_inputs` for every user who has a lead session: `inbox.created` (a question with its choices and recommendation, an error or rate limit), `inbox.updated` when a human answered a question or error, `task.created` (naming the TODO item it was started from, if any), `task.merged`, `task.discarded`, `turn.ended` with `summary: true` (" finished a turn:" with its `result` cut to 1500 characters), `task.workflow_stage` (" started stage "" of workflow "".") and `task.workflow_finished` (" finished workflow "":" with its output cut to 1500 characters). The human switching the right pane is not a signal. A signal caused by the lead itself (actor ` (lead)`) is skipped, as is the update from an answer it gave. A task's `task.created` event carries the actor that created it, separately from its `created_by` login: tasks the lead creates with `create_task` or `start_todo` keep the human's login as `created_by` but have actor ` (lead)`. Whenever the lead is idle, byre sends the oldest held message from the human as its own turn, or else every held signal as one `byre` message headed "Signals since your last turn (n)", followed by "Tasks now:" with the `list_tasks` text and a line saying what the lead's right pane shows (task or project, and selected tab) and whether the human is working in it (`leadStateText` in `internal/agents/lead.go`). If collecting that fails, for example because a project's repository is gone, the batch is still sent, ending instead with "The task list and right pane state are unavailable:" and the error, which is also logged as `lead state`. Its guidance tells it not to respond to the human's own actions, and to make its final message exactly `NO_REPLY` when a batch needs nothing from it. A transcript (`quietReply` in `web/src/task.ts`) never draws an `agent.message` whose last line is `NO_REPLY` (the model sometimes writes a sentence before it), and hides the live partial message while its text is still a prefix of it; the partial message starts hidden and is first shown by its 100ms render, so an empty one never takes up space. A lead turn that byre starts without a handoff (a signal batch or a handoff continuation) is held (`ctx.held`): its `byre` message is never drawn, and the turn isn't opened, so the scanner stays off, and its partial message stays hidden, until the lead draws something else, such as a tool call, thinking or a real message. When such a turn ends in `NO_REPLY`, everything it drew is removed with it (tool calls, thinking), so the transcript keeps nothing of it; a turn that ends in a real message keeps all of it. +- **Signals.** Every published event goes through `Manager.Observe`. These become signals in `lead_inputs` for every user who has a lead session: `inbox.created` (a question with its choices and recommendation, an error or rate limit), `inbox.updated` when a human answered a question or error, `task.created` (naming the TODO item it was started from, if any), `task.merge_started` (" is merging, started by ."), `task.merged`, `task.discarded`, `turn.ended` with `summary: true` (" finished a turn:" with its `result` cut to 1500 characters), `task.workflow_stage` (" started stage "" of workflow "".") and `task.workflow_finished` (" finished workflow "":" with its output cut to 1500 characters). The human switching the right pane is not a signal. A signal caused by the lead itself (actor ` (lead)`) is skipped, as is the update from an answer it gave. A task's `task.created` event carries the actor that created it, separately from its `created_by` login: tasks the lead creates with `create_task` or `start_todo` keep the human's login as `created_by` but have actor ` (lead)`. Whenever the lead is idle, byre sends the oldest held message from the human as its own turn, or else every held signal as one `byre` message headed "Signals since your last turn (n)", followed by "Tasks now:" with the `list_tasks` text and a line saying what the lead's right pane shows (task or project, and selected tab) and whether the human is working in it (`leadStateText` in `internal/agents/lead.go`). If collecting that fails, for example because a project's repository is gone, the batch is still sent, ending instead with "The task list and right pane state are unavailable:" and the error, which is also logged as `lead state`. Its guidance tells it not to respond to the human's own actions, and to make its final message exactly `NO_REPLY` when a batch needs nothing from it. A transcript (`quietReply` in `web/src/task.ts`) never draws an `agent.message` whose last line is `NO_REPLY` (the model sometimes writes a sentence before it), and hides the live partial message while its text is still a prefix of it; the partial message starts hidden and is first shown by its 100ms render, so an empty one never takes up space. A lead turn that byre starts without a handoff (a signal batch or a handoff continuation) is held (`ctx.held`): its `byre` message is never drawn, and the turn isn't opened, so the scanner stays off, and its partial message stays hidden, until the lead draws something else, such as a tool call, thinking or a real message. When such a turn ends in `NO_REPLY`, everything it drew is removed with it (tool calls, thinking), so the transcript keeps nothing of it; a turn that ends in a real message keeps all of it. - **Tools.** `list_tasks` (each project's active tasks, then a line listing the titles of its `TODO.md` items on the default branch that no active task was started from), `read_transcript` (a task's events in brief, the last `limit` or those after `after_seq`), `read_inbox`, `answer_question` (an `option`, `other` or `dismiss` response recorded as the user, through the same checks as `POST /api/inbox/responses`), `send_message` (starts the task's agent if it has none; refused while it is mid-turn), `create_task` and `start_todo` (each with an optional `workflow` to freeze and run), `interrupt`, `compact_task`, `merge_task`, `discard_task`, `show`, `compact_self`, and the workflow tools (see "Workflows"). The lead also has Claude Code's own tools and reads worktrees by path. Messages it sends task agents have actor ` (lead)`, so they don't make the user a participant; tasks, merges, discards and answers are done as the user. Its guidance says to answer a question only when the answer is clear or the human gave it, and to merge or discard only when the human asks. - **Focus.** `users.focus` holds what the user's right pane shows: `project_id`, `task_id`, `tabs` (the tabs put first, in order) and `tab` (the selected one). With a `task_id`, `project_id` is always that task's project, filled in by the server; with only a `project_id`, the pane shows that project with no task, which only the Project tab has anything for. `GET /api/me/focus` reads it; `PUT /api/me/focus` and the lead's `show` set it, refusing an unknown tab, a task that isn't active or an unknown project, and record a `focus.updated` event owned by the user. The page applies the focus on load and on every `focus.updated` it didn't cause itself; the human's own changes (⌘K, the right pane's task picker, clicking a tab, a task link, a notification) are sent with `PUT /api/me/focus`. The URL follows the focus: `#/task/`, `#/project/`, or `#/` for neither. -- **Pane lock.** A `show` of what the pane already shows (the same task, or the same project with no task, on the same selected tab; `sameView`) tells the lead so and applies only its `tabs` order, whether or not the human is in the pane, so the human's selected tab stays selected. Otherwise, while the human is working in the right pane, the lead's `show` is refused with an error telling it to say in chat what it would have shown, unless its selected tab is `project` (the fallback the lead shows when nothing needs the human, so the human being there doesn't hold it) or the pane is finished (`Manager.paneFinished`): its task is merged or discarded, or its selected tab is `inbox` and the task has no open items. When an `inbox.updated`, `task.merged` or `task.discarded` event leaves a user's focused task finished that way, that user's signal for it gets a line "Your right pane is free: has nothing left in its inbox." (or "is merged."/"is discarded."), even when the event itself makes no signal, such as a dismissed error; `inbox.updated` on a task that is no longer active adds none. The lead's guidance tells it to show the next thing that needs the human on that line, or, when nothing does, the project's Project tab with a short status in chat: one line per active task, then up to three TODO items it would start next, each with a reason, starting one only when the human picks it. It writes each item as a link to `#/todo//`; Markdown views draw that (`web/src/todolink.ts`) as the title with a **Start** button that calls `POST /api/projects/{id}/todo/tasks` with the first model, as the Project tab's does, or, once an active task was started from that item, the task's colour, dot and state, linking to it. A chat view refills them whenever its transcript grows or tasks or sessions change. When that status says nothing new since its last one, it replies `NO_REPLY` instead. The page sends `PUT /api/me/pane-focus` with `focused` whenever that changes: true while the browser window has focus and the focused element is inside the right pane. The pane itself is focusable (`tabIndex` -1), so a click anywhere in it counts, not only on inputs and buttons; a re-render that removes the focused element hands focus back to the pane rather than counting as leaving. The page sends false on `pagehide` (with `keepalive`) and resends true when its event stream reconnects. byre keeps the flag in memory per user (`Manager.paneFocused`), so it starts false after a restart until the page resends it. +- **Pane lock.** A `show` of what the pane already shows (the same task, or the same project with no task, on the same selected tab; `sameView`) tells the lead so and applies only its `tabs` order, whether or not the human is in the pane, so the human's selected tab stays selected. Otherwise, while the human is working in the right pane, the lead's `show` is refused with an error telling it to say in chat what it would have shown, unless its selected tab is `project` (the fallback the lead shows when nothing needs the human, so the human being there doesn't hold it) or the pane is finished (`Manager.paneFinished`): its task is merged, discarded or merging (`merging_by` set), or its selected tab is `inbox` and the task has no open items. When an `inbox.updated`, `task.merge_started`, `task.merged` or `task.discarded` event leaves a user's focused task finished that way, that user's signal for it gets a line "Your right pane is free: has nothing left in its inbox." (or "is merging."/"is merged."/"is discarded."), even when the event itself makes no signal, such as a dismissed error; `inbox.updated` on a task that is no longer active adds none. The lead's guidance tells it to show the next thing that needs the human on that line, or, when nothing does, the project's Project tab with a short status in chat: one line per active task, then up to three TODO items it would start next, each with a reason, starting one only when the human picks it. It writes each item as a link to `#/todo//`; Markdown views draw that (`web/src/todolink.ts`) as the title with a **Start** button that calls `POST /api/projects/{id}/todo/tasks` with the first model, as the Project tab's does, or, once an active task was started from that item, the task's colour, dot and state, linking to it. A chat view refills them whenever its transcript grows or tasks or sessions change. When that status says nothing new since its last one, it replies `NO_REPLY` instead. The page sends `PUT /api/me/pane-focus` with `focused` whenever that changes: true while the browser window has focus and the focused element is inside the right pane. The pane itself is focusable (`tabIndex` -1), so a click anywhere in it counts, not only on inputs and buttons; a re-render that removes the focused element hands focus back to the pane rather than counting as leaving. The page sends false on `pagehide` (with `keepalive`) and resends true when its event stream reconnects. byre keeps the flag in memory per user (`Manager.paneFocused`), so it starts false after a restart until the page resends it. - **Start hold.** Start on a TODO item in the Project tab leaves the pane where it is. When the user starts one themselves (`StartTodo` with the user as actor, not the lead's `start_todo`), byre records the time in `Manager.startedTodo` for them, and for 10 seconds after it (`startHold`), while the pane's selected tab is `project`, every `show` that would change the view is refused, focused or not, with an error telling the lead the human is likely to start more. The user's own `PUT /api/me/focus` (switching task or tab) or a message to the lead clears it. The refusal and the `show` tool's description both tell the lead the hold lasts 10 seconds. When the 10 seconds pass without it being cleared or restarted by another Start (`endStartHold`, on a timer), byre clears it and, if the pane's selected tab is still `project`, sends the lead the signal "The start hold is over: …" so it can show what it held back; its guidance tells it to reply `NO_REPLY` when nothing was. It is in memory, so a restart clears it. - **Compaction.** The pane's **Compact** button asks the lead for a handoff (`leadHandoffPrompt`). The lead can't see its own context size, so the first time one of its turns ends (other than a handoff or a `compact_self` turn) with the latest `session.context` `used` at half its `window` or more, byre holds a signal for it giving the percentage and asking it to call `compact_self` at the next logical point (`warnLeadContext` in `internal/agents/lead.go`); it is sent once per live process, so a byre restart can send it again once the window is known. The lead calls `compact_self`; when that turn ends normally, byre sends the same request. The handoff turn ends the session, and a new lead session starts from `leadHandoffPreamble` plus the handoff; held input follows once that turn ends. - **Restarts.** On shutdown, byre marks each running lead session idle with "byre stopped mid-turn" and holds a restart notice for it, so a lead is never left `running` for a build without lead support to find. After a crash, startup resumes a running lead like a task session. Startup then delivers any held input. diff --git a/internal/agents/lead.go b/internal/agents/lead.go index 9236633..f00cb43 100644 --- a/internal/agents/lead.go +++ b/internal/agents/lead.go @@ -15,8 +15,8 @@ import ( ) const leadGuidance = `You are the human's lead agent in byre, shown in the left pane of byre's web UI. The human talks to you there, and you coordinate every task agent on their behalf. You don't do task work yourself: task agents work in their own worktrees, and you read, direct and report on them. -- Signals: byre sends you, as messages from byre, what happens across tasks: questions and errors that task agents file, turns they finish with their final message, questions the human answered, tasks created, merged or discarded. Several may arrive in one message, followed by the current task list (as list_tasks gives it) and what your right pane shows, so you rarely need to call list_tasks after a signal. The human doesn't see signals. Messages from the human arrive separately. -- Don't respond to what the human just did. A signal about their own action (a question they answered, a task they created, merged or discarded) tells them nothing new: don't report, confirm or comment on it. Act on it only if it changes what you are doing, and then end the turn with one short line at most. When a batch of signals needs nothing from you to the human, make your final message exactly NO_REPLY and nothing else; byre folds that turn away so the human doesn't see it. +- Signals: byre sends you, as messages from byre, what happens across tasks: questions and errors that task agents file, turns they finish with their final message, questions the human answered, tasks created, starting to merge, merged or discarded. Several may arrive in one message, followed by the current task list (as list_tasks gives it) and what your right pane shows, so you rarely need to call list_tasks after a signal. The human doesn't see signals. Messages from the human arrive separately. +- Don't respond to what the human just did. A signal about their own action (a question they answered, a task they created, merged, started merging or discarded) tells them nothing new: don't report, confirm or comment on it. Act on it only if it changes what you are doing, and then end the turn with one short line at most. When a batch of signals needs nothing from you to the human, make your final message exactly NO_REPLY and nothing else; byre folds that turn away so the human doesn't see it. - "Your right pane is free" means the human finished what was in the right pane. Show them the next thing that needs them, most urgent first (questions and errors, then finished turns, then tasks ready to merge), with one line saying what it is. If nothing needs them, show that project's project tab, then post a short status: one line per active task (what it's doing or waiting on), then up to three TODO items you'd start next (from list_tasks), each with a one-line reason. Write each item as a link to #/todo//, for example [Fix login redirect](#/todo/3f2a9c1b7d4e/Fix%20login%20redirect): byre draws it with a Start button the human can click, and once the task exists, its state. Start one with start_todo only when the human picks it. If that says nothing new since your last status, make your final message NO_REPLY. - Steering the right pane is a core part of your job, as important as what you write. The right pane shows one task, or a project with no task; point it with show (the task or project, the tabs to put first, the tab to select). By default, keep it on whatever you and the human are discussing, so they can see it while they read your reply; don't make them go looking for it. Call show in the same turn you bring something up: - Discussing, picking or starting TODO items, or a project's tasks as a whole: the project's project tab (show with project_id when no single task of that project is involved). @@ -312,7 +312,7 @@ func (m *Manager) warnLeadContext(ctx context.Context, l *live) error { func (m *Manager) Observe(ev api.Event) { switch ev.Kind { - case "inbox.created", "inbox.updated", "task.created", "task.merged", "task.discarded", "turn.ended", "task.workflow_stage", "task.workflow_finished": + case "inbox.created", "inbox.updated", "task.created", "task.merge_started", "task.merged", "task.discarded", "turn.ended", "task.workflow_stage", "task.workflow_finished": default: return } @@ -371,7 +371,7 @@ func (m *Manager) signal(ctx context.Context, ev api.Event) error { func (m *Manager) freedText(ctx context.Context, owner string, ev api.Event) (string, error) { switch ev.Kind { - case "inbox.updated", "task.merged", "task.discarded": + case "inbox.updated", "task.merge_started", "task.merged", "task.discarded": default: return "", nil } @@ -431,6 +431,9 @@ func (m *Manager) signalText(ctx context.Context, ev api.Event) (string, error) } return fmt.Sprintf("%s was created by %s from TODO item %q.", m.taskLabel(ctx, task.Id), ev.Actor, *task.TodoItem), nil + case "task.merge_started": + return fmt.Sprintf("%s is merging, started by %s.", m.taskLabel(ctx, deref(ev.TaskId)), ev.Actor), nil + case "task.merged": commit, _ := ev.Payload["commit"].(string) if commit == "" { diff --git a/internal/agents/leadtools.go b/internal/agents/leadtools.go index d6d2df8..142b234 100644 --- a/internal/agents/leadtools.go +++ b/internal/agents/leadtools.go @@ -444,6 +444,13 @@ func (m *Manager) paneFinished(ctx context.Context, f api.Focus) (string, error) if task.Status != api.TaskStatusActive { return "is " + string(task.Status), nil } + mergingBy, err := m.store.MergingBy(ctx, task.Id) + if err != nil { + return "", err + } + if mergingBy != "" { + return "is merging", nil + } if f.Tab != api.TabInbox { return "", nil } diff --git a/internal/store/store.go b/internal/store/store.go index 6e459be..3e57d20 100644 --- a/internal/store/store.go +++ b/internal/store/store.go @@ -773,8 +773,15 @@ func (s *Store) SetMergeTitle(ctx context.Context, id, title, actor string) erro func (s *Store) SetMergingBy(ctx context.Context, id, login string) error { return s.write(ctx, func(tx *sql.Tx, emit emitFunc) error { - _, err := tx.ExecContext(ctx, `UPDATE tasks SET merging_by = ? WHERE id = ?`, login, id) - return err + projectID := "" + err := tx.QueryRowContext(ctx, `UPDATE tasks SET merging_by = ? WHERE id = ? RETURNING project_id`, login, id).Scan(&projectID) + if errors.Is(err, sql.ErrNoRows) { + return ErrNotFound + } + if err != nil { + return err + } + return emit(api.Event{Kind: "task.merge_started", ProjectId: &projectID, TaskId: &id, Actor: login, Payload: map[string]any{"id": id}}) }) }