diff --git a/changelog.d/2638.fixed.md b/changelog.d/2638.fixed.md new file mode 100644 index 000000000..7c3f5d881 --- /dev/null +++ b/changelog.d/2638.fixed.md @@ -0,0 +1 @@ +A Project name, repository, default branch, owner id, working folder or status that ends in an emoji at its length bound is now cut on a character boundary, so `state.json` stores a whole character instead of half a surrogate pair that every UTF-8 write showed as a replacement character ([#2638](https://github.com/ThinkFlowLab/FlyBot/issues/2638)). diff --git a/core/src/host/store.js b/core/src/host/store.js index 0527fa6b2..6e8f9abbd 100644 --- a/core/src/host/store.js +++ b/core/src/host/store.js @@ -10,7 +10,7 @@ import { homeLock } from './home-lock.js' import { openJournal } from './journal.js' import { tempWritable } from './real-dir.js' import { TEAM_TURNS_PER_DAY } from './turn-budget.js' -import { codePoints, currentColor, normalize, unquote } from './text.js' +import { codePoints, currentColor, cut, normalize, unquote } from './text.js' // The saved team's format version. Version 2 (#47) adds the identity schema: member // records, a per-Bot owner binding, and the owner's designated Chief. A version-1 file @@ -418,7 +418,9 @@ export function install(rt) { // A Project's working folder is the absolute path the folder picker hands back (#1766), never a // relative one: a record that says 'src' would mean a different folder on every machine. const PROJECT_WORKDIR = /^(?:\/|[A-Za-z]:[\\/]|~[\\/]|\\\\)[^\u0000-\u001f]*$/ - const projectText = (value, limit) => (typeof value === 'string' ? value.trim().slice(0, limit) : '') + // The bound is a code point budget (#2638): a slice at 120 UTF-16 units kept half of an emoji + // at the edge, so the record held a lone surrogate that every UTF-8 write turned into U+FFFD. + const projectText = (value, limit) => (typeof value === 'string' ? cut(value.trim(), limit).text : '') const projectRefusal = (message, code = 'bot/invalid') => { const error = new Error(message) error.code = code diff --git a/core/test/projects.test.js b/core/test/projects.test.js index 37d2452c8..b26bcaa9a 100644 --- a/core/test/projects.test.js +++ b/core/test/projects.test.js @@ -170,6 +170,51 @@ test('the record and its bindings survive a store re-open', async () => { } }) +// #2638: `projectText` bounded every Project field with `String#slice`, which counts UTF-16 +// units, so a name whose last code point is an emoji at the 120 bound stored half a surrogate +// pair; any UTF-8 write of it reached the world as U+FFFD. The kept prefix must end on a code +// point boundary, and what survives must still round-trip through state.json. +test('a Project name cut at the bound keeps whole code points (#2638)', async () => { + const home = mkdtempSync(join(tmpdir(), 'ds-bot-projects-cut-')) + const name = `${'P'.repeat(119)}🙂` + let first + try { + first = await start(home) + const project = created(await first.call('project-create', { name })) + assert.equal(project.name.isWellFormed(), true, 'the stored name is well formed') + assert.ok([...project.name].length <= 120, `at most 120 code points, got ${[...project.name].length}`) + // The file is what the next host reads: no half pair may reach it, in any encoding. + const bytes = readFileSync(join(home, 'state.json')) + assert.equal(bytes.includes(Buffer.from([0xef, 0xbf, 0xbd])), false, 'state.json carries no replacement character') + await first.stop({ keepHome: true }) + + const second = await start(home) + try { + const loaded = created(await second.call('project-read', { id: project.id })) + assert.equal(loaded.name.isWellFormed(), true, 'the name loaded back is well formed') + assert.ok([...loaded.name].length <= 120, `at most 120 code points, got ${[...loaded.name].length}`) + } finally { await second.stop({ keepHome: true }) } + } finally { + await first?.stop({ keepHome: true }).catch(() => {}) + rmSync(home, { recursive: true, force: true, maxRetries: 5 }) + } +}) + +// The other half of #2638: a field under its bound is not shortened, so the boundary rule only +// ever drops text that would not have fitted. +test('a Project field under its bound is kept whole after trim (#2638)', async () => { + const { call, stop } = await start() + try { + const fits = created(await call('project-create', { name: ' Padded ', workDir: `/${'d'.repeat(396)}🙂` })) + assert.equal(fits.name, 'Padded') + assert.equal(fits.workDir, `/${'d'.repeat(396)}🙂`, 'a working folder under 400 units is kept whole') + // A working folder whose last code point is an emoji at the 400 bound is cut on a boundary. + const overBound = created(await call('project-create', { name: 'Beyond', workDir: `/${'d'.repeat(398)}🙂` })) + assert.equal(overBound.workDir.isWellFormed(), true, 'the kept working folder is well formed') + assert.ok([...overBound.workDir].length <= 400, `at most 400 code points, got ${[...overBound.workDir].length}`) + } finally { await stop() } +}) + // #1704: the id tables are plain objects, so `state.projects['__proto__']` and // `state.bots['__proto__']` answered `Object.prototype` (which `isRecord` accepts). An id that // is not an own key must resolve as absent, and no request may write `Object.prototype`. diff --git a/docs/subsystems/core-host.md b/docs/subsystems/core-host.md index d0bc97b57..f2bbe9b16 100644 --- a/docs/subsystems/core-host.md +++ b/docs/subsystems/core-host.md @@ -229,7 +229,7 @@ An admin's `@` used to be the room's control plane: every `@Dev #1234 rebase and ### Team state and access -- 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. +- 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. Since #2638 every text field a Project stores goes through `cut()` (`core/src/shared/text-boundary.js`) instead of `String#slice`: the bound counts UTF-16 units as before, but the kept prefix stops on a code-point boundary, so a name whose last character is an emoji at the 120 bound is stored whole or dropped whole rather than as half a surrogate pair that every UTF-8 write reads as U+FFFD. 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. `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). diff --git a/patches/ds-bot/0002-flybot-api-host.patch b/patches/ds-bot/0002-flybot-api-host.patch index b36bac15b..2262c0a07 100644 --- a/patches/ds-bot/0002-flybot-api-host.patch +++ b/patches/ds-bot/0002-flybot-api-host.patch @@ -839,7 +839,7 @@ diff --git a/src/host/store.js b/src/host/store.js +import { openJournal } from './journal.js' +import { tempWritable } from './real-dir.js' +import { TEAM_TURNS_PER_DAY } from './turn-budget.js' -+import { codePoints, currentColor, normalize, unquote } from './text.js' ++import { codePoints, currentColor, cut, normalize, unquote } from './text.js' + +// The saved team's format version. Version 2 (#47) adds the identity schema: member +// records, a per-Bot owner binding, and the owner's designated Chief. A version-1 file @@ -1083,7 +1083,7 @@ diff --git a/src/host/store.js b/src/host/store.js // LEGACY: Bots saved with a lab ran on that lab's default model; the model they // last ran on becomes their own, so dropping the lab changes nothing for them. if ('lab' in bot) { -@@ -160,13 +160,497 @@ export function install(rt) { +@@ -160,13 +160,499 @@ export function install(rt) { room.notice ??= '' migrated = true } @@ -1163,7 +1163,9 @@ diff --git a/src/host/store.js b/src/host/store.js + // A Project's working folder is the absolute path the folder picker hands back (#1766), never a + // relative one: a record that says 'src' would mean a different folder on every machine. + const PROJECT_WORKDIR = /^(?:\/|[A-Za-z]:[\\/]|~[\\/]|\\\\)[^\u0000-\u001f]*$/ -+ const projectText = (value, limit) => (typeof value === 'string' ? value.trim().slice(0, limit) : '') ++ // The bound is a code point budget (#2638): a slice at 120 UTF-16 units kept half of an emoji ++ // at the edge, so the record held a lone surrogate that every UTF-8 write turned into U+FFFD. ++ const projectText = (value, limit) => (typeof value === 'string' ? cut(value.trim(), limit).text : '') + const projectRefusal = (message, code = 'bot/invalid') => { + const error = new Error(message) + error.code = code diff --git a/patches/ds-bot/files/test/projects.test.js b/patches/ds-bot/files/test/projects.test.js index 37d2452c8..b26bcaa9a 100644 --- a/patches/ds-bot/files/test/projects.test.js +++ b/patches/ds-bot/files/test/projects.test.js @@ -170,6 +170,51 @@ test('the record and its bindings survive a store re-open', async () => { } }) +// #2638: `projectText` bounded every Project field with `String#slice`, which counts UTF-16 +// units, so a name whose last code point is an emoji at the 120 bound stored half a surrogate +// pair; any UTF-8 write of it reached the world as U+FFFD. The kept prefix must end on a code +// point boundary, and what survives must still round-trip through state.json. +test('a Project name cut at the bound keeps whole code points (#2638)', async () => { + const home = mkdtempSync(join(tmpdir(), 'ds-bot-projects-cut-')) + const name = `${'P'.repeat(119)}🙂` + let first + try { + first = await start(home) + const project = created(await first.call('project-create', { name })) + assert.equal(project.name.isWellFormed(), true, 'the stored name is well formed') + assert.ok([...project.name].length <= 120, `at most 120 code points, got ${[...project.name].length}`) + // The file is what the next host reads: no half pair may reach it, in any encoding. + const bytes = readFileSync(join(home, 'state.json')) + assert.equal(bytes.includes(Buffer.from([0xef, 0xbf, 0xbd])), false, 'state.json carries no replacement character') + await first.stop({ keepHome: true }) + + const second = await start(home) + try { + const loaded = created(await second.call('project-read', { id: project.id })) + assert.equal(loaded.name.isWellFormed(), true, 'the name loaded back is well formed') + assert.ok([...loaded.name].length <= 120, `at most 120 code points, got ${[...loaded.name].length}`) + } finally { await second.stop({ keepHome: true }) } + } finally { + await first?.stop({ keepHome: true }).catch(() => {}) + rmSync(home, { recursive: true, force: true, maxRetries: 5 }) + } +}) + +// The other half of #2638: a field under its bound is not shortened, so the boundary rule only +// ever drops text that would not have fitted. +test('a Project field under its bound is kept whole after trim (#2638)', async () => { + const { call, stop } = await start() + try { + const fits = created(await call('project-create', { name: ' Padded ', workDir: `/${'d'.repeat(396)}🙂` })) + assert.equal(fits.name, 'Padded') + assert.equal(fits.workDir, `/${'d'.repeat(396)}🙂`, 'a working folder under 400 units is kept whole') + // A working folder whose last code point is an emoji at the 400 bound is cut on a boundary. + const overBound = created(await call('project-create', { name: 'Beyond', workDir: `/${'d'.repeat(398)}🙂` })) + assert.equal(overBound.workDir.isWellFormed(), true, 'the kept working folder is well formed') + assert.ok([...overBound.workDir].length <= 400, `at most 400 code points, got ${[...overBound.workDir].length}`) + } finally { await stop() } +}) + // #1704: the id tables are plain objects, so `state.projects['__proto__']` and // `state.bots['__proto__']` answered `Object.prototype` (which `isRecord` accepts). An id that // is not an own key must resolve as absent, and no request may write `Object.prototype`.