From 645a9e95cec3a136b4db4f24a280bcb7c0f6c43d Mon Sep 17 00:00:00 2001 From: Danyang Chen Date: Sat, 7 Nov 2026 23:15:00 +0800 Subject: [PATCH] host: keep a Session added while remove-agent awaits its archives remove-agent wrote back the Session list it read before awaiting one archive per Session, so a Session added meanwhile was dropped; when every archive succeeded it deleted the record and orphaned that Session. The removal now applies its own archives to the live record and keeps a late Session, asking for a retry instead. Refs #2616 --- changelog.d/2616.fixed.md | 1 + core/src/host/agents.js | 21 +++- core/test/agents.test.js | 78 ++++++++++++++- docs/subsystems/core-host.md | 2 +- patches/ds-bot/0001-core-fixes.patch | 139 ++++++++++++++++++++++++++- 5 files changed, 231 insertions(+), 10 deletions(-) create mode 100644 changelog.d/2616.fixed.md diff --git a/changelog.d/2616.fixed.md b/changelog.d/2616.fixed.md new file mode 100644 index 000000000..5fff93862 --- /dev/null +++ b/changelog.d/2616.fixed.md @@ -0,0 +1 @@ +Removing the DSH Agent no longer drops a Session added while its earlier Sessions are still being archived: the removal applies its own archives to the live record, keeps any Session that arrived meanwhile, and asks you to remove the Agent again instead of leaving that Session orphaned ([#2616](https://github.com/ThinkFlowLab/FlyBot/issues/2616)). diff --git a/core/src/host/agents.js b/core/src/host/agents.js index 6b569c3ca..5fb864b7d 100644 --- a/core/src/host/agents.js +++ b/core/src/host/agents.js @@ -185,12 +185,27 @@ export function install(rt) { } } // What could not be archived stays with the Agent, so it keeps its tool - // restriction and the removal can be retried from the same place. + // restriction and the removal can be retried from the same place. The record is + // read again inside the change: a Session added while an archive was awaited is + // not in the snapshot and has to survive. if (kept.length > 0) { - await rt.mutate(() => { record(agentId).sessions = kept }) + const archived = new Set(sessions.filter(id => !kept.includes(id))) + await rt.mutate(() => { + const agent = record(agentId) + agent.sessions = agent.sessions.filter(id => !archived.has(id)) + }) throw failure } - await rt.mutate(() => { delete state.agents[agentId] }) + let late = [] + await rt.mutate(() => { + const agent = record(agentId) + late = agent.sessions.filter(id => !sessions.includes(id)) + agent.sessions = late + if (late.length === 0) delete state.agents[agentId] + }) + // The change landed first, so the Agent keeps the Session that arrived during the + // removal and the retry archives it; removing it outright would orphan that Session. + if (late.length > 0) throw new Error('a Session was added while the Agent was being removed, so the Agent stays; remove it again') } Object.assign(rt, { agentOf, addAgent, createAgentSession, adoptAgentSession, archiveAgentSession, renameAgentSession, removeAgent }) diff --git a/core/test/agents.test.js b/core/test/agents.test.js index 5da35045b..b8c5ad77e 100644 --- a/core/test/agents.test.js +++ b/core/test/agents.test.js @@ -9,6 +9,12 @@ import { fakeContext } from './fake-ctx.js' const flush = async () => { for (let index = 0; index < 8; index += 1) await Promise.resolve() } +const deferred = () => { + let resolve + const promise = new Promise((settle) => { resolve = settle }) + return { promise, resolve } +} + // Enough of the dsh services for the roster and the agents module; tool restrict // calls and archived Sessions are recorded for the assertions. function start(team, { config = {} } = {}) { @@ -19,6 +25,17 @@ function start(team, { config = {} } = {}) { const created = [] const archived = [] const failArchive = { on: false } + // One archive can be made to wait, so a test can add a Session while a removal + // sits between two archives; every other archive settles at once. + const gate = { failOn: undefined, holdOn: undefined, started: undefined, waiting: undefined } + const hold = (sessionId) => { + const started = deferred() + const waiting = deferred() + gate.holdOn = sessionId + gate.started = started + gate.waiting = waiting + return { started: started.promise, release: () => waiting.resolve() } + } const restricted = [] const renamed = [] let sessions = 0 @@ -33,7 +50,15 @@ function start(team, { config = {} } = {}) { return workspace }, archiveSession: async (sessionId) => { - if (failArchive.on) throw new Error('session is running') + if (failArchive.on || gate.failOn === sessionId) throw new Error('session is running') + if (gate.holdOn === sessionId) { + const { started, waiting } = gate + gate.holdOn = undefined + gate.started = undefined + gate.waiting = undefined + started.resolve() + await waiting.promise + } archived.push(sessionId) }, }, @@ -74,7 +99,7 @@ function start(team, { config = {} } = {}) { await ctx.dispose() rmSync(home, { recursive: true, force: true, maxRetries: 5 }) } - return { call, stop, home, created, archived, failArchive, restricted, renamed, createdAgents, ctx } + return { call, stop, home, created, archived, failArchive, gate, hold, restricted, renamed, createdAgents, ctx } } const TEAM = { @@ -195,6 +220,55 @@ test('remove-agent archives every Session and drops the record', async (t) => { assert.deepEqual([...archived].sort(), [agent.sessions[0], second.sessionId].sort()) }) +test('remove-agent drops only the Sessions it archived and keeps one added while it waited', async (t) => { + const { call, stop, archived, gate, hold } = start(TEAM) + t.after(stop) + await call('state', {}) + const agent = (await call('add-agent')).value + const first = agent.sessions[0] + const second = (await call('agent-session', { agentId: agent.id })).value + // s2 refuses to archive, so the removal keeps it; s1's archive is still in flight + // when a second window adds s3 to the same Agent. + gate.failOn = second.sessionId + const waiting = hold(first) + const removing = call('remove-agent', { agentId: agent.id }) + await waiting.started + const third = (await call('agent-session', { agentId: agent.id })).value + assert.deepEqual((await call('state', {})).value.agents[0].sessions, [first, second.sessionId, third.sessionId]) + waiting.release() + const result = await removing + assert.equal(result.ok, false) + assert.equal(result.error.message, 'session is running') + // The archived Session goes; the kept one and the one added meanwhile stay. + assert.deepEqual((await call('state', {})).value.agents[0].sessions, [second.sessionId, third.sessionId]) + assert.deepEqual(archived, [first]) +}) + +test('remove-agent keeps the Agent and answers the retry error when a Session joins during the removal', async (t) => { + const { call, stop, archived, hold } = start(TEAM) + t.after(stop) + await call('state', {}) + const agent = (await call('add-agent')).value + const first = agent.sessions[0] + const second = (await call('agent-session', { agentId: agent.id })).value + // Every archive succeeds, but the last one is still in flight when s3 is added. + const waiting = hold(second.sessionId) + const removing = call('remove-agent', { agentId: agent.id }) + await waiting.started + const third = (await call('agent-session', { agentId: agent.id })).value + waiting.release() + const result = await removing + assert.equal(result.ok, false) + assert.equal(result.error.message, 'a Session was added while the Agent was being removed, so the Agent stays; remove it again') + // The Agent stays with the Session the removal never saw, so nothing is orphaned + // and the retry archives it. + assert.deepEqual((await call('state', {})).value.agents.map(entry => entry.sessions), [[third.sessionId]]) + assert.deepEqual(archived, [first, second.sessionId]) + assert.equal((await call('remove-agent', { agentId: agent.id })).ok, true) + assert.deepEqual((await call('state', {})).value.agents, []) + assert.deepEqual(archived, [first, second.sessionId, third.sessionId]) +}) + test('agents survive a state reload', async (t) => { const { call, stop, home } = start(TEAM) await call('state', {}) diff --git a/docs/subsystems/core-host.md b/docs/subsystems/core-host.md index e032144b9..22ada47ac 100644 --- a/docs/subsystems/core-host.md +++ b/docs/subsystems/core-host.md @@ -231,7 +231,7 @@ An admin's `@` used to be the room's control plane: every `@Dev #1234 rebase and - The saved team (`state.json`) is versioned. Version 2 (#47) carries the identity schema — `members` records, a per-Bot `ownerId`, the owner's `designatedChiefId`. A legacy version-1 file is migrated on load with a one-time `state.json.v1` backup; an existing backup counts only when it is a readable file holding a parseable version-1 state, and anything else (or any malformed ownership) fails closed (read-only). An older binary refuses a newer version read-only. This is schema foundation only — team mode stays disabled, see [team](team.md). On top of it, a durable **Project** record (#1691): `state.projects` holds `{id, name, repository, defaultBranch, ownerUserId, createdAt, updatedAt, status}`, `bot.projectId` / `room.projectId` and `state.projectRuns[runId]` bind a member (a group, a Bot or a workflow run) to at most one Project, and the `api/bot` endpoints `projects`, `project-create`, `project-read`, `project-bind`, `project-of` and `project-board` sit in the task allow list. An unbound member resolves `null`, so an install with zero Projects behaves exactly as before. The read-only board over those bindings is `project-board` (#1696): Project id in, `{ tasks: [...] }` out, one row per core task id with `source` (`bot`/`group`/`workflow`), `column`, `assignee`, `updatedAt` and `runId`/`nodeId` when a run holds it, plus the card's own `title` (`null` when the record has none), `priority` (`priorityOf`, `'normal'` when the record stored none) and `board` (the `{ kind, id }` the row opens, `null` on a `workflow` row) so a row draws a card and opens the board it lives on: the open `tasks` read a page joins by id keeps open cards only, so a finished card in the `done` half has no record there and would otherwise draw as `#` with no priority and nowhere to go. `core/src/host/project-board.js` reads `state.tasks` and the bindings and asks the registered providers through `rt.projectRunRefs` (`flybot.tasks.onProjectProvider`); it never reads `workflows.json` and writes nothing. Since #2021 the board's record halves say what their caps left out and cut the right end of the list: the decision read answers `total` — the files left after the one-row-per-path dedup, before the cut — and takes `.slice(-DECISIONS_MAX)` over the still-ascending sort, so a Project past 200 decisions keeps the newest instead of dropping the ones just written and the order on screen does not change, while the meetings read answers `decidedTotal`/`pendingTotal` per list beside the 100 rows it already kept newest; a list at or under its cap answers the same rows as before, plus the count ([#2021](https://github.com/ThinkFlowLab/FlyBot/issues/2021)). Since #2033 the lookup a decided meeting uses for its own file falls back to the un-truncated dedupe set of that same read when the name is not among the kept rows, so a file that fell off the oldest end of the cut is still named by the meeting (`path` set, and no `sha256`, because only the kept rows carry one) while a name the folder no longer holds still answers `path: ''`; the fallback reads names from that dedupe set and never asks the filesystem, so a crafted `../outside.md` yields no path either ([#2033](https://github.com/ThinkFlowLab/FlyBot/issues/2033)). Since #2037 the name is also checked where the listing is produced, by the same `isDecisionPath` the reader uses: a name with a `..` segment, an absolute path, a symlink standing in for the file, or a name this read never listed yields no row and no meeting `path` (and no `sha256`), so the fallback past the cut cannot bring one back — `archivedOf` reads through `describeFile`, the reader's own `lstat`, never `stat` ([#2037](https://github.com/ThinkFlowLab/FlyBot/issues/2037)). Since #2041 a decision row can be opened: `rt.projectDecision(projectId, name)` reads one name through `readListedFile` and answers the reader's own three states (`text`, `absent`, `too large`), but only for a name the last `projectBoard` read of that Project produced — that read's un-truncated dedupe set is kept per Project, each name with the folder it was read from, so a name past the 200-row cut still opens while `decisions/../outside.md`, an absolute path, a name one level down or a symlink answers `not listed` without a `stat`, an open or a byte of content; the endpoint is `project-decision`, dispatched in `channel.js` beside `project-board` and listed in `authz.js`'s `TASK_ENDPOINTS` ([#2041](https://github.com/ThinkFlowLab/FlyBot/issues/2041)). A decided meeting that saved no folder keeps the cards it decided: its file is one of the Project folder's own rows, and binding those cards to that row is what keeps the name behind the same door as the cards, while a meeting that decided no card still answers through the role list ([#2052](https://github.com/ThinkFlowLab/FlyBot/issues/2052)). A record that named a folder whose file this read could not open is not that folder-less shape: it binds no cards, so the same relative name in the Project's own folder answers through the role list instead of inheriting the cards of a file in another folder. Since [#2029](https://github.com/ThinkFlowLab/FlyBot/issues/2029) a blocked card also carries the age of its own question: `blockedOf(task, now)` answers `since` (the `inputRequest.requestedAt` stamp `tasks.js` wrote, preserved across a re-ask) and `waitedMs` (`now - since`, the same shape `waitingOf` answers), both `null` when the ask wrote no stamp — never derived from `createdAt`/`updatedAt` — and `buildQueues` sorts `blocked` oldest-first with the comparator `waiting.sort` already uses, so an undated card sorts last; the Waiting group's own output is unchanged. Tests: `core/test/project-board.test.js`. On top of the record and the board sits the **Project Assistant** (#1712, Stage 2.5): `project-delete` removes the Project, its bindings and its memory; the assistant's digest is one stored note plus one `deliver()` to the owner, idempotent per Asia/Shanghai day, and its identity is the connector account and never the shared app — no connector signed in, or a multi-member host whose Project owner is not this host's own user, refuses and escalates with nothing written. Per-owner memory (#1733) keys those three fields by `(Project, owner)` under `projectMemory[id].owners`, mirrors the primary owner onto the row itself so a single-owner Project reads as before, and migrates a pre-#1733 record onto its primary owner on the first write instead of replacing it; the boundary a memory read is checked against is the Project's own owner list, so an owner asking for another owner's entries is refused naming that list, while the assistant's own render walks every owner. A card needs an owner's decision when the Bot that owns the card belongs to that owner, never from the board's `assignee` (a Bot name or null); the ask names the card's own title, at most `MAX_ACTIONABLE` (5) per owner. A quiet window on the assistant record holds a due digest and releases it once, labelled, when the window ends; a window covering 09:00 delivers nothing that day; an owner's opt-out stops generation and pauses the shared 09:00 task once every owner is off, and a re-enable resumes it; delivery goes to each owner's own Session and falls back to the main Bot only for the primary owner. A held digest is released by the next `digest()` call, not by the 09:00 task, which does not make one after a window ends. On top of it, member auth (#48) adds host module `src/host/member-auth.js`, installed after `store` in `MODULES` (`core/index.js`): `invitations` and `authSessions` maps live on state (no `STATE_VERSION` bump), the channel resolves the actor from the `x-flybot-member-session` header, and endpoints are `auth-invite` / `auth-redeem` / `auth-revoke` / `auth-whoami` / `auth-remove-member` / `auth-revoke-invite` with `body.actorId` ignored; `auth-invite` alone also opens for an anonymous caller on a host with no sessions yet (bootstrap first invite), `auth-revoke-invite` kills an unredeemed invitation (redeeming it afterwards fails with `revoked`), `removeMember` refuses a member that still owns a Bot (`has_bots`), and the auth mutations are serialized behind an in-process lock so concurrent `removeMember` calls cannot both pass the last-owner check. Sign-in surface only — still not team mode; details in [team](team.md). On top of it, owner-scoped access (#49) adds host module `src/host/authz.js`, installed after member-auth: when any `authSessions` exist, the channel `authorize()` default-denies cross-owner Bot/room/session access, blocks shared non-isolatable resources (secrets, connectors, folder picks, browser bridge, update-install, diagnostics, set-prefs, `add-agent` — the DSH Agent is one per deployment and carries no owner) with `bot/blocked-shared` when more than one member exists, stamps `create-bot` with `actor.memberId`, and filters `view()`/`live()` to the actor; with no sessions the single-human behavior is unchanged. Session targets resolve through the store's owner maps — a Bot id via `botOf`, current chats and group Sessions and earlier parts via `selfOf`/`groupOwners`/`pastOwners` (a shared room Session also resolves for its current participants, #50) — and unresolvable ids deny. `approval-answer` gates on the approval's own Bot or room (resolved by approval id), never on caller-supplied session fields. `flybot/*` plugin endpoints (src/host/hooks.js) reach any signed-in actor for reads — except a Bot Social read naming a `body.botId` the actor does not own, which `bot/forbidden` refuses before the plugin handler registers that Bot's identity or syncs its grants (#1788, an owner-decided tightening); plugin writes follow the shared rule. `view()`/`live()` narrowing (`rt.ownedView`/`rt.ownedLive` in authz.js) keeps per-session entries (`questions`, `exchangeTurns`) the actor owns, and deployment-wide surfaces (agents, secrets, connectors, memory reviews) only while a single member exists — the same rule as the shared writes; rooms the actor belongs to and the Bots in them (#50) stay visible. `create-room` refuses a request with neither a member Bot nor any participant. On top of it, room membership (#50) adds host module `src/host/room-membership.js`, installed after groups: a room may carry typed `participants` (`human` / local `bot` / granted remote `bot` with `handle` + owner fields, roles `admin` / `member`, `joinedSeq` / `leftSeq`); log lines carry `authorId` + `authorKind`; history is the membership window (current members and the owner of an invited Bot see `seq >=` their interval; leave withdraws access; rejoin starts a new interval); local cross-owner rooms accept each side's *granted* Bots (#90: default deny, Chief included); a friend's Bot from `social/remote-bots` (`cleanRemote`) may be added and ungranted Bots stay private, and a room with a friend's Bot holds only granted local Bots (a Bot that joined by room code, `viaCode`, only for that room); `view()` labels remotes with an owner badge and shows an invited owner **Shared room from \**. Face-to-face rooms (#83) reuse the same `participants` / membership-window / owner-badge presentation with `origin: 'face-to-face'`: room-only remotes may sit in the room without a person-grant or a friendship, `presentRoom` treats the viewer as a member (not Shared room from), leave skips the two-Bot floor, and `fanoutRoomLine` goes to `rt.faceRoomFanout` instead of friend `flybotSend`. Still not team mode — see [team](team.md). Per-Bot grants (#90) add host module `src/host/reach.js`, installed after room-membership: `state.grants[botId]` is the list of independent grants (one Bot → one grantee, optionally room-scoped); default deny, Chief included; a Bot whose owner is not a member has none. Grants are set with `rt.setGrants`, exposed as `BotView.granted`, `flybot.bot.hasGrant` / `hasAnyGrant`, `flybot.grants` and the `bot.grants` event. `reach()` is the owner policy: a friend's Bot may reach only local Bots granted to that sender, only a granted Bot (or one code-joined in that room) may message a friend's Bot, another owner's Bot is reached only if both sides have matching grants or both are members of the room the message belongs to. It is not a middleware: hooks.js runs it before the `bot.send` chain, again on approval release, and on every deliver with a sender or remote origin (resumed, retried, deferred, re-sent), so no verdict or `bypass` can skip it and a queued message is judged by what is true when it is delivered. Revoking a grant, or replacing its Chief, removes it from rooms that have friends' Bots or several owners at once (`rt.evictUnshared`). Approval binding (#52) completes the held-send half of this: `state.flybot.approvals` records carry `requestId`, a sha256 `version` over the request content, server-derived `ownerId` and `origin` (`via`/`hop`/audience) — claims in the message (`meta`, text) never confer authority. `flybot/decide` is allowed through authz for any signed-in actor and the per-record check happens in hooks (`decide` requires the sender Bot's owner's session, `bot/forbidden` otherwise, `bot/unauthorized` without a session); `release()` revalidates before dispatch and marks the record `stale` when the request changed, the sender or target Bot is gone (also invalidated eagerly on `deleteBot`), or the Bot changed owners; a demoted Chief's sender-side holds are invalidated eagerly on `setMain` (not inside `staleReason`), and `release()` re-checks immediately before dispatch so an in-flight approve cannot go out after a concurrent invalidation. Unknown `invalidateFor` field values throw. `flybot/approvals` lists only the actor's own holds while enforcement is on; decided stale records keep their attribution in state but appear in no member's list. Which statuses still wait for that decision is one rule in `src/shared/approval-waiting.js` (#754): `decide()`, `heldOf()` in the chat view, the in-flight filter that invalidates holds, `PENDING_MAX` and the `APPROVALS_KEPT` cleanup all ask `isApprovalWaiting()`, and `channel.js` counts a row's waiting replies with it, so a `pending_approval` hold (Bot Social's own spelling) is decidable, drawn as waiting and never dropped mid-wait. -- One writer per home (`src/host/home-lock.js`): the first dsh to load `~/.dsh` takes `state.lock` (pid, host, a random token in the file, its mtime bumped on a timer) and a second window on the same data only reads, answering `bot/read-only` and naming the other host. What such a window still answers is `channel.js`'s own `READS` whitelist: beside `state` it carries the reads a second window's screens draw — the Projects views (`projects`, `project-read`, `project-board`, `project-team`, `project-of`, `project-decision`, `project-memory`), the task boards (`tasks`), the folder rows and browser (`folders`, `folder-list`) and the connector row's app state (`connector-app-status`) — and the write beside each one (`project-create`, `project-bind`, `task-create`, `folder-pick`, `connector-connect`, ...) is still refused, so a missing read is an empty screen and never a change made through the reading window. `diagnostics-clear` is deliberately not on that list (#2302): it truncates `/logs/diagnostics.jsonl`, the file a bug report is supposed to carry, so a reading window is refused with `bot/read-only` instead of erasing the evidence, while `diagnostics` and `diagnostics-log` still read that same file. Takeover is **on the next write**, not on a poll (#1027): a window that was read-only claims the free lock inside `save()` too, and a change made outside a request (a plugin, a scheduled task, a delivery) belongs in `rt.mutate(fn)`, which takes over and adopts what the other host left *before* the change is made and written. The writers that changed `rt.state` inline and then called `save()` are gone (#1048): `delivery.js` (a friend's first line and its unread mark, a team exchange) and `agents.js` (add, adopt, archive and remove of the DSH Agent) take the free lock and adopt first, re-resolving their records inside the change, so a write from a window that was read-only keeps what the other host left instead of replacing it with its older copy. `save()` itself never adopts: `adopt()` replaces `rt.state` whole, so adopting there would discard a change the caller has already made (`#1032`). Either takeover prints one line — `the other dsh has closed; this one now saves the Bot team (was pid on )` — from `refresh()` and from `save()` alike, so a window that writes over the file another host left leaves a trace (#1041). A lock file still naming a live holder on this host (its pid answers) keeps the window read-only, which is the #14 rule. A write that fails does not decide the delivery (#1096): the friend-line mark and the exchange record both land before the agent has the line, so a rejected `mutate()` (the lock was taken away, or the disk refused) prints one warning naming what was not recorded and the line is still handed over — a throw there would drop a message that exists nowhere else. The write chain is also readable: `rt.savesQueued()` is a monotonic watermark — every save this host has accepted since it started, never decremented — and `rt.savesSettled()` resolves once the chain is empty, so a caller that must read `state.json` after a save it did not await — a rollback's own write, in the tests — waits on the store instead of on a delay, where a wait long enough on an idle machine reads a half-written team on a busy one (#1368). A save never writes through a link at the team file's own name (P-556): the write lands on the temp name and the `rename` replaces the name, link included, so the file the link pointed at keeps every byte and its last write time, and the path the person opened is a regular file of this home's own from that save on. A hard link is that same save for the person who opened the name: `lstat` reports `isSymbolicLink()` `false` while the inode carries a second name, so the name counts as linked only while a regular file's `nlink > 1` (the rule `plainLeaf` in `real-dir.js` already holds), and a file of this host's own (`nlink === 1`) is never counted. The store counts that save — `lstat` on the name before the `rename`, once per save, never for a save over the regular file that followed — and answers `rt.stateLinkReplaced()` as `{ gen, count }`: the count, plus the random generation stamp of the process that made it, because a restarted host starts counting at 0 again and a window holding the previous process's larger count would read the restart's first save as old news (Chief, on review). The pair rides the live part of every `state` answer (`stateFileLinkReplaced`), the `unchanged` one included, because a replaced link moves no revision; `authz.js`'s `ownedLive` names it in its whitelist, so a deployment where anyone has signed in receives it too — a field left out of that whitelist reaches no signed-in client at all (Security, on review). +- One writer per home (`src/host/home-lock.js`): the first dsh to load `~/.dsh` takes `state.lock` (pid, host, a random token in the file, its mtime bumped on a timer) and a second window on the same data only reads, answering `bot/read-only` and naming the other host. What such a window still answers is `channel.js`'s own `READS` whitelist: beside `state` it carries the reads a second window's screens draw — the Projects views (`projects`, `project-read`, `project-board`, `project-team`, `project-of`, `project-decision`, `project-memory`), the task boards (`tasks`), the folder rows and browser (`folders`, `folder-list`) and the connector row's app state (`connector-app-status`) — and the write beside each one (`project-create`, `project-bind`, `task-create`, `folder-pick`, `connector-connect`, ...) is still refused, so a missing read is an empty screen and never a change made through the reading window. `diagnostics-clear` is deliberately not on that list (#2302): it truncates `/logs/diagnostics.jsonl`, the file a bug report is supposed to carry, so a reading window is refused with `bot/read-only` instead of erasing the evidence, while `diagnostics` and `diagnostics-log` still read that same file. Takeover is **on the next write**, not on a poll (#1027): a window that was read-only claims the free lock inside `save()` too, and a change made outside a request (a plugin, a scheduled task, a delivery) belongs in `rt.mutate(fn)`, which takes over and adopts what the other host left *before* the change is made and written. The writers that changed `rt.state` inline and then called `save()` are gone (#1048): `delivery.js` (a friend's first line and its unread mark, a team exchange) and `agents.js` (add, adopt, archive and remove of the DSH Agent) take the free lock and adopt first, re-resolving their records inside the change, so a write from a window that was read-only keeps what the other host left instead of replacing it with its older copy. `remove-agent` follows the same rule against a change made meanwhile, not another host (#2616): it awaits one archive per Session, so it never writes back the Session list it read before them — the change drops exactly the ids it archived and keeps everything else, and when every archive succeeded the change keeps the Sessions that arrived during the removal and the removal answers a retryable error instead of deleting the record, so a Session added meanwhile is never orphaned and the retry archives it. `save()` itself never adopts: `adopt()` replaces `rt.state` whole, so adopting there would discard a change the caller has already made (`#1032`). Either takeover prints one line — `the other dsh has closed; this one now saves the Bot team (was pid on )` — from `refresh()` and from `save()` alike, so a window that writes over the file another host left leaves a trace (#1041). A lock file still naming a live holder on this host (its pid answers) keeps the window read-only, which is the #14 rule. A write that fails does not decide the delivery (#1096): the friend-line mark and the exchange record both land before the agent has the line, so a rejected `mutate()` (the lock was taken away, or the disk refused) prints one warning naming what was not recorded and the line is still handed over — a throw there would drop a message that exists nowhere else. The write chain is also readable: `rt.savesQueued()` is a monotonic watermark — every save this host has accepted since it started, never decremented — and `rt.savesSettled()` resolves once the chain is empty, so a caller that must read `state.json` after a save it did not await — a rollback's own write, in the tests — waits on the store instead of on a delay, where a wait long enough on an idle machine reads a half-written team on a busy one (#1368). A save never writes through a link at the team file's own name (P-556): the write lands on the temp name and the `rename` replaces the name, link included, so the file the link pointed at keeps every byte and its last write time, and the path the person opened is a regular file of this home's own from that save on. A hard link is that same save for the person who opened the name: `lstat` reports `isSymbolicLink()` `false` while the inode carries a second name, so the name counts as linked only while a regular file's `nlink > 1` (the rule `plainLeaf` in `real-dir.js` already holds), and a file of this host's own (`nlink === 1`) is never counted. The store counts that save — `lstat` on the name before the `rename`, once per save, never for a save over the regular file that followed — and answers `rt.stateLinkReplaced()` as `{ gen, count }`: the count, plus the random generation stamp of the process that made it, because a restarted host starts counting at 0 again and a window holding the previous process's larger count would read the restart's first save as old news (Chief, on review). The pair rides the live part of every `state` answer (`stateFileLinkReplaced`), the `unchanged` one included, because a replaced link moves no revision; `authz.js`'s `ownedLive` names it in its whitelist, so a deployment where anyone has signed in receives it too — a field left out of that whitelist reaches no signed-in client at all (Security, on review). - `list_bots` (`src/host/tools.js`) tags a Bot with `N to approve` while one of its outbound sends is held for the owner's decision (#587): a count of that Bot's pending held sends (`state.flybot.approvals`), never the held message's text, so a coordinator reading the roster sees who is blocked and the tag clears once the owner decides. Covered by the roster case in `core/test/flybot.test.js`. - The bot **write** tools keep the same owner rule (#1844): with authz on, `stop_bot`, `update_bot` and `archive_bot` (`src/host/tools.js`, `writableBot`) accept a target only when its `ownerId` is the caller's owner or `hasGrant(bot.id, ownerId)` holds, and `inRoom` takes no part — a Bot that is only visible because it sits in the same room is not writable, and `listed()` stays a read predicate. With authz off the predicate is the old `findTeamBot`, so a single-owner install is unchanged. All three answer an unknown and a foreign name with the same bare `No Bot named .` instead of a `Team:` list, so the text neither confirms that a Bot the actor cannot see exists nor names one. Covered by `core/test/update-bot.test.js`, `core/test/archive-bot.test.js` and `core/test/bot-messages.test.js`. diff --git a/patches/ds-bot/0001-core-fixes.patch b/patches/ds-bot/0001-core-fixes.patch index d5f99f0cb..aa014b4b4 100644 --- a/patches/ds-bot/0001-core-fixes.patch +++ b/patches/ds-bot/0001-core-fixes.patch @@ -3515,18 +3515,36 @@ diff --git a/src/host/agents.js b/src/host/agents.js const kept = [] let failure for (const sessionId of sessions) { -@@ -174,12 +174,10 @@ export function install(rt) { +@@ -172,14 +172,27 @@ export function install(rt) { + } + } // What could not be archived stays with the Agent, so it keeps its tool - // restriction and the removal can be retried from the same place. +- // restriction and the removal can be retried from the same place. ++ // restriction and the removal can be retried from the same place. The record is ++ // read again inside the change: a Session added while an archive was awaited is ++ // not in the snapshot and has to survive. if (kept.length > 0) { - agent.sessions = kept - await rt.save() -+ await rt.mutate(() => { record(agentId).sessions = kept }) ++ const archived = new Set(sessions.filter(id => !kept.includes(id))) ++ await rt.mutate(() => { ++ const agent = record(agentId) ++ agent.sessions = agent.sessions.filter(id => !archived.has(id)) ++ }) throw failure } - delete state.agents[agentId] - await rt.save() -+ await rt.mutate(() => { delete state.agents[agentId] }) ++ let late = [] ++ await rt.mutate(() => { ++ const agent = record(agentId) ++ late = agent.sessions.filter(id => !sessions.includes(id)) ++ agent.sessions = late ++ if (late.length === 0) delete state.agents[agentId] ++ }) ++ // The change landed first, so the Agent keeps the Session that arrived during the ++ // removal and the retry archives it; removing it outright would orphan that Session. ++ if (late.length > 0) throw new Error('a Session was added while the Agent was being removed, so the Agent stays; remove it again') } Object.assign(rt, { agentOf, addAgent, createAgentSession, adoptAgentSession, archiveAgentSession, renameAgentSession, removeAgent }) @@ -8854,6 +8872,63 @@ diff --git a/src/shared/mentions.js b/src/shared/mentions.js diff --git a/test/agents.test.js b/test/agents.test.js --- a/test/agents.test.js +++ b/test/agents.test.js +@@ -9,6 +9,12 @@ import { fakeContext } from './fake-ctx.js' + + const flush = async () => { for (let index = 0; index < 8; index += 1) await Promise.resolve() } + ++const deferred = () => { ++ let resolve ++ const promise = new Promise((settle) => { resolve = settle }) ++ return { promise, resolve } ++} ++ + // Enough of the dsh services for the roster and the agents module; tool restrict + // calls and archived Sessions are recorded for the assertions. + function start(team, { config = {} } = {}) { +@@ -19,6 +19,17 @@ function start(team, { config = {} } = {}) { + const created = [] + const archived = [] + const failArchive = { on: false } ++ // One archive can be made to wait, so a test can add a Session while a removal ++ // sits between two archives; every other archive settles at once. ++ const gate = { failOn: undefined, holdOn: undefined, started: undefined, waiting: undefined } ++ const hold = (sessionId) => { ++ const started = deferred() ++ const waiting = deferred() ++ gate.holdOn = sessionId ++ gate.started = started ++ gate.waiting = waiting ++ return { started: started.promise, release: () => waiting.resolve() } ++ } + const restricted = [] + const renamed = [] + let sessions = 0 +@@ -33,7 +33,15 @@ function start(team, { config = {} } = {}) { + return workspace + }, + archiveSession: async (sessionId) => { +- if (failArchive.on) throw new Error('session is running') ++ if (failArchive.on || gate.failOn === sessionId) throw new Error('session is running') ++ if (gate.holdOn === sessionId) { ++ const { started, waiting } = gate ++ gate.holdOn = undefined ++ gate.started = undefined ++ gate.waiting = undefined ++ started.resolve() ++ await waiting.promise ++ } + archived.push(sessionId) + }, + }, +@@ -74,7 +74,7 @@ function start(team, { config = {} } = {}) { + await ctx.dispose() + rmSync(home, { recursive: true, force: true, maxRetries: 5 }) + } +- return { call, stop, home, created, archived, failArchive, restricted, renamed, createdAgents, ctx } ++ return { call, stop, home, created, archived, failArchive, gate, hold, restricted, renamed, createdAgents, ctx } + } + + const TEAM = { @@ -153,6 +153,20 @@ test('agent-rename retitles an owned Session and refuses others', async (t) => { assert.equal((await call('agent-rename', { agentId: agent.id, sessionId: 'm1', title: 'x' })).ok, false) }) @@ -8875,6 +8950,62 @@ diff --git a/test/agents.test.js b/test/agents.test.js test('remove-agent keeps the Agent with the Sessions it could not archive', async (t) => { const { call, stop, archived, failArchive } = start(TEAM) t.after(stop) +@@ -181,6 +181,55 @@ test('remove-agent archives every Session and drops the record', async (t) => { + assert.deepEqual([...archived].sort(), [agent.sessions[0], second.sessionId].sort()) + }) + ++test('remove-agent drops only the Sessions it archived and keeps one added while it waited', async (t) => { ++ const { call, stop, archived, gate, hold } = start(TEAM) ++ t.after(stop) ++ await call('state', {}) ++ const agent = (await call('add-agent')).value ++ const first = agent.sessions[0] ++ const second = (await call('agent-session', { agentId: agent.id })).value ++ // s2 refuses to archive, so the removal keeps it; s1's archive is still in flight ++ // when a second window adds s3 to the same Agent. ++ gate.failOn = second.sessionId ++ const waiting = hold(first) ++ const removing = call('remove-agent', { agentId: agent.id }) ++ await waiting.started ++ const third = (await call('agent-session', { agentId: agent.id })).value ++ assert.deepEqual((await call('state', {})).value.agents[0].sessions, [first, second.sessionId, third.sessionId]) ++ waiting.release() ++ const result = await removing ++ assert.equal(result.ok, false) ++ assert.equal(result.error.message, 'session is running') ++ // The archived Session goes; the kept one and the one added meanwhile stay. ++ assert.deepEqual((await call('state', {})).value.agents[0].sessions, [second.sessionId, third.sessionId]) ++ assert.deepEqual(archived, [first]) ++}) ++ ++test('remove-agent keeps the Agent and answers the retry error when a Session joins during the removal', async (t) => { ++ const { call, stop, archived, hold } = start(TEAM) ++ t.after(stop) ++ await call('state', {}) ++ const agent = (await call('add-agent')).value ++ const first = agent.sessions[0] ++ const second = (await call('agent-session', { agentId: agent.id })).value ++ // Every archive succeeds, but the last one is still in flight when s3 is added. ++ const waiting = hold(second.sessionId) ++ const removing = call('remove-agent', { agentId: agent.id }) ++ await waiting.started ++ const third = (await call('agent-session', { agentId: agent.id })).value ++ waiting.release() ++ const result = await removing ++ assert.equal(result.ok, false) ++ assert.equal(result.error.message, 'a Session was added while the Agent was being removed, so the Agent stays; remove it again') ++ // The Agent stays with the Session the removal never saw, so nothing is orphaned ++ // and the retry archives it. ++ assert.deepEqual((await call('state', {})).value.agents.map(entry => entry.sessions), [[third.sessionId]]) ++ assert.deepEqual(archived, [first, second.sessionId]) ++ assert.equal((await call('remove-agent', { agentId: agent.id })).ok, true) ++ assert.deepEqual((await call('state', {})).value.agents, []) ++ assert.deepEqual(archived, [first, second.sessionId, third.sessionId]) ++}) ++ + test('agents survive a state reload', async (t) => { + const { call, stop, home } = start(TEAM) + await call('state', {}) diff --git a/test/approval-notices.test.js b/test/approval-notices.test.js --- a/test/approval-notices.test.js +++ b/test/approval-notices.test.js