mirror of
https://github.com/backnotprop/plannotator.git
synced 2026-09-14 14:17:26 +08:00
cb6667e991
* fix(ai): drive Codex Ask AI via app-server + answer-first review prompts (#971) Codex Ask AI previously ran via @openai/codex-sdk (codex exec), which forces approval_policy=never and breaks in enterprise-managed Codex environments that ban it (#971). Replace the transport with a long-lived 'codex app-server' process over JSON-RPC. - New provider packages/ai/providers/codex-app-server.ts (registered as 'codex-sdk' to preserve cookie/agents.ts/UI-gate); omits approvalPolicy so Codex resolves the user's + managed policy, pins read-only sandbox, and surfaces interactive approvals through the existing PermissionCard. - Delete codex-sdk.ts and drop the @openai/codex-sdk dependency (and its 6 prebuilt platform binaries); gate registration on 'which codex'. - SessionManager: additive, optional dispose?() hook to kill the spawned process on evict/remove — a no-op for Claude/OpenCode/Pi (they don't implement it). Also rework the Ask AI prompts (all providers, separate from the transport): - Every mode now instructs the agent to answer the user's message directly and not launch an unprompted review of the context. - Code review stops pasting the whole diff for git-reproducible diff types and instead tells the agent how to inspect it (git diff <base>..HEAD, three-dot for merge-base); non-git/PR/workspace types still paste. - Claude gains the Bash tool so it can run git (still gated by approvals). - The UI passes diffType/base (session) and what the user is viewing (per question) into the context. Verified: full typecheck, full test suite (101 ai tests), and a live end-to-end smoke against codex app-server. * fix(review): pin AI approval card above the input/model bar Render pending approval cards just above the input + provider/model bar in both the document chat (DocumentAIChatPanel) and code-review AI tab, instead of at the top of the scroll, so the user sees them where they act. * fix(ai): harden Codex abort/cancel + add Ask AI Stop button Addresses code-review findings on the codex app-server provider: - turn/interrupt was sent as a notification (no id) so Codex ignored it and abort never took effect. It's now a proper JSON-RPC request. - Filter turn events/approvals by turnId and reject an aborted turn's stragglers, so a stopped turn can no longer leak output into — or prematurely finish — the next turn (ask-stop-ask race). - Guard listeners by query generation and end the drain loop on the abort signal, so a superseded/stopped turn can't touch the live one and abort returns promptly instead of waiting for turn/completed. - Handle abort during startup: once the turn id is known, interrupt it instead of running it in the background. - Add a sendAndWait timeout so a stalled (alive-but-unresponsive) process errors instead of hanging forever. - Drain stderr (stdio 'ignore') to avoid a pipe-buffer deadlock. Also add a Stop button to both Ask AI surfaces (plan/annotate DocumentAIChatPanel and code-review AITab via ReviewSidebar). It replaces Send while streaming and calls the hook's abort -> /api/ai/abort -> session.abort(); the hook already exposed abort but nothing surfaced it. * feat(ai): drive Codex models + reasoning levels from model/list - Codex provider fetches model/list at startup (throwaway app-server, like Pi/OpenCode) and populates the real models plus each model's actual supportedReasoningEfforts + defaultReasoningEffort. Replaces the hardcoded model list and the static AI_REASONING_EFFORTS (which mislabeled xhigh as 'Max' and omitted minimal). - AIProviderBar + AIConfigBar now show the selected model's real efforts and hide the control when a model reports none. xhigh is shown verbatim. - Fix: the Stop button now also appears in the populated code-review chat state (a prior edit missed the second GeneralInput due to indentation). * fix(ai): scope Claude Ask AI Bash to read-only git; clear stale approval cards on Stop - Claude Ask AI no longer auto-allows bare Bash (which ran arbitrary shell with no Allow/Deny prompt). Replace it with scoped read-only git rules (Bash(git diff:*), show, log, status, rev-parse, merge-base, ls-files). git reads auto-run so the agent can inspect large diffs itself; any other command (write git, arbitrary, or injected compound) falls through to the permission card. Keeps the git-inspect approach (large diffs don't fit in the prompt) while closing the auto-exec hole. - useAIChat.abort() now drops still-undecided permission cards: abort cancels them server-side, so leaving them visible was a dead Allow/Deny. * feat(ai): code-review Ask AI shares the agent-review prompt machine, delivered as user messages Code-review Ask AI built its own diff description (gitInspectInstruction) in the system prompt from just diffType+base, which was wrong for full-stack, hide-whitespace, untracked files, and PR worktrees. Replace it with the same machine the review jobs use, delivered on the user's messages. - Server: buildCurrentAiReviewContext() reuses buildAgentReviewUserMessageForTarget (contextOnly) for the current view and ships it as aiReviewContext in every diff payload (/api/diff + switch/PR/scope). Mirrored in the Pi server. - Client: review-editor latches aiReviewContext onto each question via the pure buildReviewContextPreamble (packages/ui/utils/aiPrompt.ts) and buildDefaultPrompt — full block on the first message / when the view changes (incl. after a provider switch via the !sessionId fresh-session check), a short reminder otherwise (never re-pastes a large diff). - context.ts: delete the duplicate gitInspectInstruction; code-review system prompt is now role-only. Providers untouched (provider-agnostic user message). - Tests: machine scenario gaps (plain PR, full-stack default, PR-worktree origin/<base> + stale-main warning, untracked mention, jj-evolog, workspace lines); composition (first/reminder, command/pasted, preamble ordering). * fix(ai): agentic remote-PR context, UTF-8 stream decode, real Stop on supersede/disconnect Addresses review findings on the Ask AI prompt work: - Remote PR without a confirmed local checkout no longer gets URL-only. The agent is told it's in a PR worktree that's being prepared, to verify the PR files exist before relying on them, and to diff with git diff origin/<base>... HEAD (URL fallback). Inform + trust the agent rather than pasting. Shared machine, so review jobs get the same framing. - Decode Codex stdout with a streaming TextDecoder instead of per-chunk toString(), so multi-byte UTF-8 split across chunks no longer corrupts into U+FFFD (matches the Pi provider). - Stop now actually stops the server turn: ask() awaits /api/ai/abort when a new question supersedes a streaming one (awaiting avoids racing the new query into session_busy), and the /api/ai/query SSE stream gains a cancel handler so tab-close/navigation aborts the turn too. Both reuse the existing per-provider session.abort(); factored a shared postServerAbort helper. * fix(ai): per-model reasoning effort, shared PR-checkout readiness, Stop-then-ask race, type hole - Reasoning effort is now tracked per model (a map keyed by model) instead of one global value, so switching to a model that doesn't support the prior level (e.g. xhigh) no longer posts a stale/unsupported effort that Codex rejects. Each model keeps its own level; nothing leaks across. - Extract resolvePoolCwd into packages/shared/worktree-pool.ts (ready/pending/ absent) and use it from both servers' resolvePRLocalCwd so the readiness rule can't drift. Fix the Pi Ask AI helper to ready-check like Bun, so a warming PR checkout no longer claims 'checked out at PR head' and misdirects the diff. - Stop-then-ask no longer races into session_busy: the abort promise (from Stop or a superseding question) is stashed and the next ask() awaits it before sending. Stop still kills the turn instantly; a follow-up just waits the one abort round-trip. - Declare aiReviewContext on the initial /api/diff response type. * fix(ai): surface real Codex error messages, skip transient retries, auto-deny permission escalations Validated against codex-rs: - Codex's ErrorNotification nests the text at params.error.message (TurnError.message); we read params.message → always 'Unknown error'. Read the nested field (top-level fallback) so auth/usage-limit/stream failures show their real, actionable text. - Skip transient error notifications (willRetry=true): Codex retries on its own and the turn continues, so surfacing them flashed a spurious failure before the real answer. - Handle item/permissions/requestApproval: respond {permissions:{}, scope:'turn'} — byte-for-byte Codex's own cancel response (codex_delegate.rs) — instead of 'Unsupported request'. Ask AI is read-only, so denying the escalation lets the turn continue sandboxed rather than failing. Interactive grant deferred. * refactor(ai): share AI provider/model config in one hook; aggregate paginated model/list - Extract useAIProviderConfig (packages/ui/hooks): one home for provider/model/ reasoning-effort selection — initial state, auto-resolve on capabilities load, per-model effort (no leak across models), and persistence. Both the plan and code-review apps now call it and only compose the session reset (the hook can't own reset without a cycle through useAIChat). Plan editor adapted to the effect-based resolve (adds aiDefaultProvider state). This fixes the plan editor's stale-effort-on-model-switch bug by construction and stops the two apps' copies from drifting again. - fetchModels now follows model/list's nextCursor and aggregates every page into one list, so larger model catalogs aren't silently truncated (with a page guard against a misbehaving cursor). Skipped per discussion: legacy v1 approval methods (we're a v2 client). * feat(agents): per-agent review default; bound Codex model discovery so it can't stall the AI panel - The selected review profile is now tracked per review engine (claude/codex/ cursor/opencode) instead of one flat global value, so each agent keeps its own review default. Public hook API (reviewProfileId/setReviewProfileId) is unchanged — getter derives the current engine's value, setter writes it — so AgentsTab needs no changes. One-shot migration seeds every engine with any existing flat pick. Adds parseReviewProfileByEngine + tests. - fetchModels (Codex model discovery) now uses a short 6s timeout for its initialize + model/list RPCs instead of the 30s default. /api/ai/capabilities awaits model discovery, so an installed-but-unauthenticated codex could otherwise block the AI panel for ~30s; it now falls back to the static model list fast. Authed codex is unaffected (discovery completes in tens of ms).
206 lines
6.2 KiB
TypeScript
206 lines
6.2 KiB
TypeScript
/**
|
|
* Session manager — tracks active and historical AI sessions.
|
|
*
|
|
* Each Plannotator server instance (plan review, code review, annotate)
|
|
* gets its own SessionManager. It tracks:
|
|
*
|
|
* - Active sessions (currently streaming or idle but resumable)
|
|
* - The lineage from forked sessions back to their parent
|
|
* - Metadata for UI display (timestamps, mode, status)
|
|
*
|
|
* This is an in-memory store scoped to the server's lifetime. Sessions
|
|
* are not persisted to disk by the manager (the underlying provider
|
|
* handles its own persistence via the agent SDK).
|
|
*/
|
|
|
|
import type { AISession, AIContextMode } from "./types.ts";
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Types
|
|
// ---------------------------------------------------------------------------
|
|
|
|
export interface SessionEntry {
|
|
/** The live session handle (if still active). */
|
|
session: AISession;
|
|
/** What mode this session was created for. */
|
|
mode: AIContextMode;
|
|
/** The parent session ID this was forked from (null if standalone). */
|
|
parentSessionId: string | null;
|
|
/** When this session was created. */
|
|
createdAt: number;
|
|
/** When the last query was sent. */
|
|
lastActiveAt: number;
|
|
/** Short description for UI display (e.g., the user's first question). */
|
|
label?: string;
|
|
}
|
|
|
|
export interface SessionManagerOptions {
|
|
/**
|
|
* Maximum number of sessions to keep in the manager.
|
|
* Oldest idle sessions are evicted when the limit is reached.
|
|
* Default: 20.
|
|
*/
|
|
maxSessions?: number;
|
|
}
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Implementation
|
|
// ---------------------------------------------------------------------------
|
|
|
|
export class SessionManager {
|
|
private sessions = new Map<string, SessionEntry>();
|
|
private aliases = new Map<string, string>();
|
|
private maxSessions: number;
|
|
|
|
constructor(options: SessionManagerOptions = {}) {
|
|
this.maxSessions = options.maxSessions ?? 20;
|
|
}
|
|
|
|
/**
|
|
* Track a newly created session.
|
|
*
|
|
* If the session supports ID resolution (e.g., the real SDK session ID
|
|
* arrives after the first query), call `remapId()` to update the key.
|
|
*/
|
|
track(session: AISession, mode: AIContextMode, label?: string): SessionEntry {
|
|
this.evictIfNeeded();
|
|
|
|
const entry: SessionEntry = {
|
|
session,
|
|
mode,
|
|
parentSessionId: session.parentSessionId,
|
|
createdAt: Date.now(),
|
|
lastActiveAt: Date.now(),
|
|
label,
|
|
};
|
|
this.sessions.set(session.id, entry);
|
|
|
|
// Wire up ID remapping so providers can resolve the real session ID later
|
|
session.onIdResolved = (oldId, newId) => this.remapId(oldId, newId);
|
|
|
|
return entry;
|
|
}
|
|
|
|
/**
|
|
* Remap a session from one ID to another.
|
|
* Used when the real session ID is resolved after initial tracking.
|
|
*/
|
|
remapId(oldId: string, newId: string): void {
|
|
const entry = this.sessions.get(oldId);
|
|
if (entry) {
|
|
this.sessions.delete(oldId);
|
|
this.sessions.set(newId, entry);
|
|
// Keep the old ID as an alias so clients using the original ID still work
|
|
this.aliases.set(oldId, newId);
|
|
}
|
|
}
|
|
|
|
/** Resolve an alias to the canonical ID, or return the ID as-is. */
|
|
private resolve(sessionId: string): string {
|
|
return this.aliases.get(sessionId) ?? sessionId;
|
|
}
|
|
|
|
/**
|
|
* Get a tracked session by ID (or alias).
|
|
*/
|
|
get(sessionId: string): SessionEntry | undefined {
|
|
return this.sessions.get(this.resolve(sessionId));
|
|
}
|
|
|
|
/**
|
|
* Mark a session as recently active (updates lastActiveAt).
|
|
*/
|
|
touch(sessionId: string): void {
|
|
const entry = this.sessions.get(this.resolve(sessionId));
|
|
if (entry) {
|
|
entry.lastActiveAt = Date.now();
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Remove a session from tracking.
|
|
* Does NOT abort the session — call session.abort() first if needed.
|
|
*/
|
|
remove(sessionId: string): void {
|
|
const canonical = this.resolve(sessionId);
|
|
const entry = this.sessions.get(canonical);
|
|
this.sessions.delete(canonical);
|
|
// Release any long-lived resources (e.g. a spawned subprocess). No-op for
|
|
// providers whose sessions don't implement dispose().
|
|
entry?.session.dispose?.();
|
|
// Clean up any aliases pointing to this session
|
|
for (const [alias, target] of this.aliases) {
|
|
if (target === canonical) this.aliases.delete(alias);
|
|
}
|
|
}
|
|
|
|
/**
|
|
* List all tracked sessions, newest first.
|
|
*/
|
|
list(): SessionEntry[] {
|
|
return [...this.sessions.values()].sort(
|
|
(a, b) => b.lastActiveAt - a.lastActiveAt
|
|
);
|
|
}
|
|
|
|
/**
|
|
* List sessions forked from a specific parent.
|
|
*/
|
|
forksOf(parentSessionId: string): SessionEntry[] {
|
|
return this.list().filter(
|
|
(e) => e.parentSessionId === parentSessionId
|
|
);
|
|
}
|
|
|
|
/**
|
|
* Get the number of tracked sessions.
|
|
*/
|
|
get size(): number {
|
|
return this.sessions.size;
|
|
}
|
|
|
|
/**
|
|
* Abort all active sessions and clear tracking.
|
|
*/
|
|
disposeAll(): void {
|
|
for (const entry of this.sessions.values()) {
|
|
if (entry.session.isActive) {
|
|
entry.session.abort();
|
|
}
|
|
// Release long-lived resources. No-op for providers without dispose().
|
|
entry.session.dispose?.();
|
|
}
|
|
this.sessions.clear();
|
|
this.aliases.clear();
|
|
}
|
|
|
|
// -------------------------------------------------------------------------
|
|
// Internal
|
|
// -------------------------------------------------------------------------
|
|
|
|
private evictIfNeeded(): void {
|
|
if (this.sessions.size < this.maxSessions) return;
|
|
|
|
// Find the oldest idle session to evict
|
|
let oldest: { id: string; at: number } | null = null;
|
|
for (const [id, entry] of this.sessions) {
|
|
if (entry.session.isActive) continue; // don't evict active sessions
|
|
if (!oldest || entry.lastActiveAt < oldest.at) {
|
|
oldest = { id, at: entry.lastActiveAt };
|
|
}
|
|
}
|
|
|
|
if (oldest) {
|
|
const entry = this.sessions.get(oldest.id);
|
|
this.sessions.delete(oldest.id);
|
|
// Release long-lived resources held by the evicted session. No-op for
|
|
// providers whose sessions don't implement dispose().
|
|
entry?.session.dispose?.();
|
|
// Clean up aliases pointing to the evicted session
|
|
for (const [alias, target] of this.aliases) {
|
|
if (target === oldest.id) this.aliases.delete(alias);
|
|
}
|
|
}
|
|
}
|
|
}
|