mirror of
https://github.com/stablyai/orca.git
synced 2026-09-23 16:02:24 +00:00
* feat(native-chat): port structured Codex sessions from restructure-recovery Rebuilds the desktop structured native-chat implementation from brennanb2025/native-chat-restructure-recovery (tip 4e31c08db3) on top of current main as a single commit, scoped to the local Codex path. Ported: - Structured agent-session core: durable record store + single-writer lease, canonical journal, agent-session wire host/attach/eviction/subscribers, `agentSession.*` RPC surface (registered via ALL_RPC_METHODS; host-side mobile allowlist included for wire compat), pty write gate, transcript additions, and the Codex app-server adapter/launch resolution. - Renderer: NativeChatStructuredSession view/composer stack, structured launch path with the single-flight guard, local structured session tabs sync, activation gate + structured inventory (read-only `agentSession.handoffStatus` probe), agent-session tabs in the tab strip, AI-vault structured session activation, and the settings pane with the parent Experimental Chat UI toggle plus the nested "Use updated structured native chat" toggle. New sessions require both flags, agent codex, no prompt, and a local non-WSL, non-Windows-host execution host (structured-native-chat-availability). - Fixes 72c013cea6 (verified Codex launch recovery), 8ddbaf5e3d (defer native terminal view switching affordances), and 4e31c08db3 (release the launch gate after a visibility retry) with their regression tests, including the third-launch-after-retry guard case. - Cross-version agent-session wire test + CI lane, packaging entries (proper-lockfile, agent-tooling asar excludes), and the wire-compat doc section. Deliberately not ported: mobile/ changes, the Claude structured runtime (only the claude-transcript-branch-proof and claude-structured-owner-identity leaf modules remain, backing the kept TUI-recovery arms), the terminal↔chat adoption/handoff flow (`agentSession.adoptTerminal`/`requestHandoff`, the handoff request engine, TUI adoption machinery, orca-runtime adoption methods), renderer switching affordances and their dead leftovers, the hook/subagent-status refactor cluster, and unrelated branch changes. The crash-during-acquisition recovery path (restart handoff adjudication, restore/reverse re-acquire, lease schema handoff keys) is kept because every plain direct launch depends on it; a trimmed handoff coordinator exposes only status/restore/close. Branch edits that targeted files main has since split (ipc/pty.ts, worktrees.ts, rpc/methods/terminal.ts, useIpcEvents, pty-connection, store/slices/terminals.ts, runtime-types, web preload) were re-applied to the split modules, preserving main's newer logic (Windows CIM fallback, browser tab close rework, cold-restore resume flow, dispatcher threading). Known seam: the mobile clipboard image-provenance CONSUMER gate ships (agentSession.send refuses unproven mobile image refs with agent_session_image_untrusted) but the producer hunk in rpc/methods/clipboard.ts stays with the unported mobile cluster, so mobile image sends into structured chat fail closed until that side ports. * fix(native-chat): trust only authenticated local image uploads * fix(build): preserve Windows process-tree patch application * test(windows): include process creation time in addon fixture * fix(build): run windows-process-tree node-gyp from the physical package dir gyp expands the node-addon-api dependency by probing node, whose cwd resolves to the package's physical directory in the store, so the emitted target is a store-relative ../../../../node-addon-api@... hop. gyp then resolves that hop against the rebuild cwd; from the node_modules symlink/junction it escapes the store and configure fails with "node_addon_api.gyp not found" (run 32999886072). Rebuild from realpath(package dir) so both bases agree, matching how the package manager itself runs native install scripts. The regression test replays gyp's expansion+resolution against the planned cwd and fails without the fix. * fix(native-chat): keep chat tabs visible through terminal closes and empty-worktree launches Two proven blockers in the native Codex tab contract: closeTerminalTab pre-empted the canonical unified close. With one terminal left it deactivated the worktree on a terminal/editor/browser-only check, blanking a workspace that still held a renderable agent-session tab; with two or more it pre-picked a successor from terminal entities only, re-stamping the group active before closeUnifiedTab's MRU/neighbor repair could land on the chat tab. Successor choice now defers to the unified contract whenever the terminal has a unified row, and deactivation is gated on the unified renderable count (matching leaveWorktreeIfEmpty), with the legacy pre-pick kept only for terminals without a unified row. A structured session created on an empty worktree was published into the host's headless group while preserveLocalLayout froze the local layout, leaving the tab in store but permanently off screen. A preserveLocalLayout owner now always takes client-owned placement — repairing a rendered leaf whose group record is missing, or materializing a rendered group on a truly empty worktree — and applies the client-derived layout repair while still rejecting host-authored layout. Regression tests drive the real store through closeTerminalTab (git worktree and folder workspace) and the real snapshot applier for the empty-worktree adoption states; all fail without the fixes. * fix(native-chat): close stale turns and retry rejected sends * fix(native-chat): retire hosted rows on structured tab activation * fix(native-chat): preserve rpc defaults across main merge * chore: format remote wire compatibility guide * test(native-chat): cover retry after unconfirmed send * fix(native-chat): reload outbox on session switch * docs(settings): disclose structured chat platform limits * fix(native-chat): await Codex launch-home preparation * fix(codex): align child-process allowlist with async trust bridge * test(identity): update inventory for tab surface refactor * fix(windows): preserve process-tree CRLF patch sources * fix(native-chat): anchor an unmatched chat echo where it was sent (#16117) * fix(native-chat): anchor an unmatched chat echo where it was sent The reported symptom was old user messages replaying below every new turn, so the conversation read as scrambled. The cause was not that the echo failed to match a transcript row. Claude consumes a mid-turn send through a `queued_command` attachment and writes no `type:"user"` record for it, so some echoes can never match, and no amount of matching will change that. The cause was WHERE an unmatched echo rendered: buildMobileNativeChatTransientData appended every pending item after the entire transcript, so it re-read below each turn that landed afterwards. Render each echo directly after the transcript row it was sent against, using the baseline the send already captures. An unmatched echo is then at worst a duplicate in the right position rather than a scrambled one, and it stays visible. Echoes sharing an anchor keep send order; a send with no baseline, or one whose anchor folding dropped, still falls back to the tail. Deliberately NOT fixed by deleting the echo. Inferring from send ordering that an echo can never match, then removing it, loses the user's own text for a message the agent did receive, and it cannot fire in the common case anyway - measured drain groups are 1,017 of size 1 against 55 larger. It also escalates an existing gap: the count pass has no baseline-tail guard, unlike the glue pass, while `messages` is a 40-row window that head-trims, resets on reconnect and grows at the front on loadEarlier, so a false landing there would license deleting a DIFFERENT outstanding message. That count-pass gap is real and left for a separate change; anchoring makes its worst case a duplicate in place rather than a scrambled conversation. * fix(native-chat): preserve folded echo anchors * fix(native-chat): preserve forward-folded echo anchors * fix(native-chat): keep leading folded echoes in place * fix(workspace-cleanup): show git status for every row (#16690) * fix(native-chat): refuse structured chat on every Windows execution path canUseStructuredNativeChat only refused win32 when a project runtime resolved, so folder-workspace keys (and other keys with no project runtime) failed open into structured chat on Windows. Fail closed on win32 unconditionally after the host check, matching the settings copy: local macOS/Linux only; Windows/WSL/SSH stay on terminal chat. * fix(native-chat): restore runtime refusals behind the win32 gate506d375de3replaced the project-runtime checks with a bare platform test, so a WSL or repair-required runtime resolution would no longer refuse structured chat off-win32. Keep the unconditional win32 refusal and re-run the runtime resolution after it, so the gate does not depend on the resolver's own platform guard. Tests inject WSL and repair-required resolutions on darwin/linux and fail against the regressed gate. * fix structured session journal durability * fix structured tab active pointer after restart * fix(native-chat): await optional lease renewal callbacks * refactor(skills): extract install error messages * fix(agent-session): harden recovery ownership * fix(native-chat): retain panes across tab activation * fix(native-chat): address round-one review findings * test(native-chat): align integration coverage after main merge * fix(native-chat): harden round-two reliability * fix(native-chat): harden round-three reliability * fix(native-chat): close round-four recovery gaps * fix(native-chat): separate bounded journal key forms * fix(native-chat): reset outbox error in render on session switch The switch effect adjusted error state after the sessionId prop changed, tripping react-doctor's no-adjust-state-on-prop-change on the changed-code gate and flashing the old session's banner for a frame. Reset it with the render-time previous-value guard instead. * fix(native-chat): invalidate stale outbox settlements * test(native-chat): restore settled-error session-switch regressiona6e2379bd1replaced this test with the in-flight settlement race test, leaving the render-time error reset unpinned: deleting the reset block still passed the whole native-chat suite. Keep both scenarios pinned; they are distinct (settled error clears on switch vs stale settlement invalidated in the commit-to-passive window). * test(wire): make release checkouts race safe * test(wire): pin cross-process checkout single-flight and importer specifier contract * test(wire): harden release checkout lifecycle * fix(build): drop CR-byte residue from windows-process-tree patch The two trailing CR bytes on the patch's deletion lines are a proven no-op: pnpm hashes patches CRLF-normalized (both forms hash to the lockfile's 946ffb2b) and materializes this package without applying the patch in either form, so the load-bearing build edits come solely from applyWindowsProcessTreeBuildFixes() (#16947), which handles both source EOL forms. Restore byte-identity with main and repin the contract test to the post-#16947 reality: LF-only patch bytes plus lockfile hash sync. * fix(native-chat): skip empty startup recovery
235 lines
8.4 KiB
TypeScript
235 lines
8.4 KiB
TypeScript
// Item-identity → stable journal key. Pure and shared: the host keys upserts
|
|
// with it and clients reconcile optimistic sends against the same string.
|
|
//
|
|
// Components are percent-encoded before joining so a value containing the
|
|
// delimiter cannot collide with a different identity.
|
|
|
|
import type { AgentJournalItemIdentity } from './agent-session-journal-types'
|
|
|
|
const KEY_DELIMITER = ':'
|
|
const VERBATIM_BOUNDED_COMPONENT_TAG = '%FF'
|
|
const BOUNDED_COMPONENT_PATTERN = /^[\s\S]{0,40}~orca-oversized~(?:[1-9]\d*)~[0-9a-f]{16}$/
|
|
const PARSED_JOURNAL_ITEM_KEY = Symbol('parsedJournalItemKey')
|
|
|
|
type ParsedJournalItemIdentity = AgentJournalItemIdentity & {
|
|
readonly [PARSED_JOURNAL_ITEM_KEY]?: string
|
|
}
|
|
|
|
/** Longest raw component a key may embed. Real provider ids are tens of bytes;
|
|
* anything larger would push the composed key past wire page budgets, so it
|
|
* travels as a stable digest instead of verbatim. */
|
|
export const MAX_JOURNAL_KEY_COMPONENT_CHARS = 1024
|
|
|
|
/**
|
|
* Deterministic stand-in for an oversized or ill-formed key component: same
|
|
* input, same output, so revisions and tombstones of one identity still share
|
|
* a key, and re-deriving from a parsed key is a fixed point (the bounded form
|
|
* is well-formed and far below the cap). The head keeps keys debuggable;
|
|
* length plus two independent hashes makes an accidental collision practically
|
|
* impossible. Pure JS because clients derive keys too and cannot reach
|
|
* node:crypto.
|
|
*
|
|
* JSON strings are arbitrary UTF-16 code units, so a component can carry a
|
|
* lone surrogate that `encodeURIComponent` throws on. Those values take the
|
|
* digest form too: the hashes run over the raw code units, so a value and its
|
|
* replacement-character spelling keep distinct keys.
|
|
*/
|
|
export function boundJournalKeyComponent(value: string): string {
|
|
if (value.length <= MAX_JOURNAL_KEY_COMPONENT_CHARS && !hasLoneSurrogate(value)) {
|
|
return value
|
|
}
|
|
const h1 = fnv1a32(value, 0x811c9dc5).toString(16).padStart(8, '0')
|
|
const h2 = fnv1a32(value, 0x0100_0193).toString(16).padStart(8, '0')
|
|
return `${wellFormedBoundedHead(value, 40)}~orca-oversized~${value.length}~${h1}${h2}`
|
|
}
|
|
|
|
/** The diagnostic head must be valid Unicode for `encodeURIComponent`: a pair
|
|
* split by the cut is dropped and a lone surrogate becomes U+FFFD — the
|
|
* hashes over the raw units keep the full key collision-safe regardless.
|
|
* Digest forms are persisted, so for well-formed input the head must stay
|
|
* byte-stable across builds or one identity would stop sharing a key. */
|
|
function wellFormedBoundedHead(value: string, maxUnits: number): string {
|
|
let head = ''
|
|
let index = 0
|
|
while (index < value.length && index < maxUnits) {
|
|
const unit = value.charCodeAt(index)
|
|
if (unit >= 0xd800 && unit <= 0xdbff) {
|
|
const next = index + 1 < value.length ? value.charCodeAt(index + 1) : 0
|
|
if (next >= 0xdc00 && next <= 0xdfff) {
|
|
if (index + 1 >= maxUnits) {
|
|
break
|
|
}
|
|
head += value.charAt(index) + value.charAt(index + 1)
|
|
index += 2
|
|
continue
|
|
}
|
|
head += '�'
|
|
index += 1
|
|
continue
|
|
}
|
|
head += unit >= 0xdc00 && unit <= 0xdfff ? '�' : value.charAt(index)
|
|
index += 1
|
|
}
|
|
return head
|
|
}
|
|
|
|
function hasLoneSurrogate(value: string): boolean {
|
|
for (let index = 0; index < value.length; index += 1) {
|
|
const unit = value.charCodeAt(index)
|
|
if (unit >= 0xd800 && unit <= 0xdbff) {
|
|
const next = index + 1 < value.length ? value.charCodeAt(index + 1) : 0
|
|
if (next < 0xdc00 || next > 0xdfff) {
|
|
return true
|
|
}
|
|
index += 1
|
|
} else if (unit >= 0xdc00 && unit <= 0xdfff) {
|
|
return true
|
|
}
|
|
}
|
|
return false
|
|
}
|
|
|
|
function fnv1a32(value: string, seed: number): number {
|
|
let hash = seed >>> 0
|
|
for (let index = 0; index < value.length; index += 1) {
|
|
hash ^= value.charCodeAt(index)
|
|
hash = Math.imul(hash, 0x0100_0193) >>> 0
|
|
}
|
|
return hash >>> 0
|
|
}
|
|
|
|
function encodePart(value: string | number): string {
|
|
const raw = String(value)
|
|
const bounded = boundJournalKeyComponent(raw)
|
|
const encoded = encodeURIComponent(bounded)
|
|
// `%FF` is not valid UTF-8 and cannot be emitted by encodeURIComponent.
|
|
return raw === bounded && isBoundedComponentRepresentation(raw)
|
|
? `${VERBATIM_BOUNDED_COMPONENT_TAG}${encoded}`
|
|
: encoded
|
|
}
|
|
|
|
function isBoundedComponentRepresentation(value: string): boolean {
|
|
return BOUNDED_COMPONENT_PATTERN.test(value)
|
|
}
|
|
|
|
/**
|
|
* Stable string key for an item identity.
|
|
*
|
|
* Codex renumbers `item-N` ids on every resume, so its key is the thread, the
|
|
* turn, and the item's ordinal WITHIN that turn — a position that survives
|
|
* renumbering because a completed turn's item list does not change. `thread/fork`
|
|
* copies turns keeping their original turn ids, so the thread id must stay in the
|
|
* key. Claude copies item uuids on `--fork-session`, so its key is the session id
|
|
* plus the uuid. Text never participates.
|
|
*/
|
|
export function agentJournalItemKey(identity: AgentJournalItemIdentity): string {
|
|
// Parsed pre-tag digest keys must keep addressing their persisted revision chain.
|
|
const parsedKey = (identity as ParsedJournalItemIdentity)[PARSED_JOURNAL_ITEM_KEY]
|
|
if (parsedKey !== undefined) {
|
|
return parsedKey
|
|
}
|
|
if (identity.provider === 'codex') {
|
|
return [
|
|
'codex',
|
|
encodePart(identity.threadId),
|
|
encodePart(identity.turnId),
|
|
encodePart(identity.ordinal)
|
|
].join(KEY_DELIMITER)
|
|
}
|
|
if (identity.provider === 'claude') {
|
|
return ['claude', encodePart(identity.sessionId), encodePart(identity.uuid)].join(KEY_DELIMITER)
|
|
}
|
|
if (identity.provider === 'orca') {
|
|
return ['orca', encodePart(identity.clientMessageId)].join(KEY_DELIMITER)
|
|
}
|
|
return [
|
|
'legacy',
|
|
encodePart(identity.agent),
|
|
encodePart(identity.sessionId),
|
|
encodePart(identity.recordId)
|
|
].join(KEY_DELIMITER)
|
|
}
|
|
|
|
/** Key for the pre-dispatch submission placeholder, before any provider echo. */
|
|
export function agentJournalSubmissionKey(clientMessageId: string): string {
|
|
return agentJournalItemKey({ provider: 'orca', clientMessageId })
|
|
}
|
|
|
|
/**
|
|
* Inverse of {@link agentJournalItemKey}. Clients hold item KEYS, but an upsert
|
|
* needs the identity behind one — answering an approval re-appends the same
|
|
* item at the next revision. Components are percent-encoded; raw strings that
|
|
* imitate a bounded component carry a reserved encoded-domain tag.
|
|
*/
|
|
export function parseAgentJournalItemKey(key: string): AgentJournalItemIdentity | null {
|
|
// Persisted keys can be corrupted: a malformed percent sequence must fail
|
|
// the parse, never throw through journal replay or open.
|
|
const parts: string[] = []
|
|
let preserveExactKey = false
|
|
for (const part of key.split(KEY_DELIMITER)) {
|
|
const decoded = decodePart(part)
|
|
if (!decoded) {
|
|
return null
|
|
}
|
|
parts.push(decoded.value)
|
|
preserveExactKey ||= decoded.tagged || isBoundedComponentRepresentation(decoded.value)
|
|
}
|
|
const [provider, ...rest] = parts
|
|
if (provider === 'codex' && rest.length === 3) {
|
|
const ordinal = Number(rest[2])
|
|
return Number.isSafeInteger(ordinal) && ordinal >= 0
|
|
? parsedIdentity(
|
|
{ provider, threadId: rest[0] as string, turnId: rest[1] as string, ordinal },
|
|
key,
|
|
preserveExactKey
|
|
)
|
|
: null
|
|
}
|
|
if (provider === 'claude' && rest.length === 2) {
|
|
return parsedIdentity(
|
|
{ provider, sessionId: rest[0] as string, uuid: rest[1] as string },
|
|
key,
|
|
preserveExactKey
|
|
)
|
|
}
|
|
if (provider === 'orca' && rest.length === 1) {
|
|
return parsedIdentity({ provider, clientMessageId: rest[0] as string }, key, preserveExactKey)
|
|
}
|
|
if (provider === 'legacy' && rest.length === 3) {
|
|
return parsedIdentity(
|
|
{
|
|
provider,
|
|
agent: rest[0] as string,
|
|
sessionId: rest[1] as string,
|
|
recordId: rest[2] as string
|
|
},
|
|
key,
|
|
preserveExactKey
|
|
)
|
|
}
|
|
return null
|
|
}
|
|
|
|
function decodePart(part: string): { value: string; tagged: boolean } | null {
|
|
const tagged = part.startsWith(VERBATIM_BOUNDED_COMPONENT_TAG)
|
|
try {
|
|
const value = decodeURIComponent(
|
|
tagged ? part.slice(VERBATIM_BOUNDED_COMPONENT_TAG.length) : part
|
|
)
|
|
return !tagged || isBoundedComponentRepresentation(value) ? { value, tagged } : null
|
|
} catch {
|
|
return null
|
|
}
|
|
}
|
|
|
|
function parsedIdentity<T extends AgentJournalItemIdentity>(
|
|
identity: T,
|
|
key: string,
|
|
preserveExactKey: boolean
|
|
): T {
|
|
if (preserveExactKey) {
|
|
Object.defineProperty(identity, PARSED_JOURNAL_ITEM_KEY, { value: key })
|
|
}
|
|
return identity
|
|
}
|