docs: trim generated prose

packages/session-persistence/session-persistence-jsonl/src/format.ts

@@ -72,19 +72,10 @@ function isHeaderLine(value: unknown): value is HeaderLine {
 }
 
 /**
- * Encode an arbitrary string as a single safe path segment, injectively over
- * ALL JS (UTF-16) strings — including lone surrogates. A {@link SessionId} is
- * an unvalidated branded string, so this neutralizes `../`, absolute paths,
- * NUL, and separators before any filesystem use.
+ * Encode an arbitrary string as a single safe path segment, injectively over ALL JS (UTF-16)
+ * strings — including lone surrogates. A {@link SessionId} is an unvalidated branded string,
+ * so this neutralizes `../`, absolute paths, NUL, and separators before any filesystem use.
  *
- * Each UTF-16 code unit is either kept literal (the safe set `[A-Za-z0-9_-]`)
- * or escaped as `~XXXX` (its 4-hex-digit code unit). `~` is itself escaped, so
- * the mapping is injective and reversible: distinct inputs never collide. We
- * iterate code UNITS (`charCodeAt`), not code points, so a lone surrogate
- * escapes to a distinct `~XXXX` instead of being normalized to U+FFFD (which
- * `Buffer.from(…, 'utf8')` would do, breaking injectivity). `.` is in the safe
- * set for readability but the whole-segment tokens `.`/`..` are escaped so they
- * can never traverse.
  * @param raw - the string to encode; must be non-empty (throws on `''`).
  * @returns the escaped single path segment, decodable back to `raw`.
  */
@@ -141,39 +132,19 @@ export function eventLine(event: SessionEvent): string {
 }
 
 /**
- * Parse a JSONL log buffer into its preserved event prefix (the header is line
- * 0). Returns the longest prefix of complete, seq-contiguous events plus the
- * byte offset of the end of the last preserved line (`committedBytes`).
+ * Parse a JSONL log buffer into its preserved event prefix (the header is line 0). Returns the
+ * longest prefix of complete, seq-contiguous events plus the byte offset of the end of the
+ * last preserved line (`committedBytes`).
  *
- * A crash can leave a durable log whose final turn never closed: real,
- * fully-written events sit after the last `turn/end`. Those are PRESERVED (a
- * single turn can be huge in a long-horizon task — truncating it would destroy
- * real work); the backend closes the orphaned open turn with a synthetic
- * `turn/end {kind:'interrupted'}` on reload (the session-persistence RFC). Only a TORN trailing
- * fragment — a final line never fully flushed (no newline, unparseable, or a
- * seq gap) — is excluded; it bounds the preserved region. A parse error or seq
- * gap AT OR BEFORE the last committed `turn/end` is committed-data corruption
- * and makes the session unloadable (throws).
- *
- * This relies on the session-log invariant that every event lives inside a turn
- * (`Session.append` enforces it): only the final turn can be open, so the
- * preserved tail is at most one unclosed turn.
  * @param buffer - the raw bytes of the log file (header line first).
  * @returns the header, the preserved event prefix, and `committedBytes` — the
  *   byte offset the next append truncates any torn tail to.
  */
 export function scanLog(buffer: Buffer): { meta: SessionHeader; events: SessionEvent[]; committedBytes: number } {
   const text = buffer.toString('utf8')
-  // Split into complete (newline-terminated) lines, tracking the byte offset of
-  // each line's end so the truncation point is exact (multi-byte chars make the
-  // char offset differ from the byte offset). A trailing line with no newline is
-  // an uncommitted crash fragment and is ignored — it is below the last
-  // turn/end by construction (the loop only flushes whole lines).
-  //
-  // Track the byte offset with a RUNNING accumulator (`endByte`), adding each
-  // line's byte length as we go. Recomputing `Buffer.byteLength(text.slice(0, i))`
-  // per newline would rescan the whole prefix every time — O(n²) over a long
-  // log (one assistant/chunk line per token makes that pathological).
+  // Split into complete (newline-terminated) lines, tracking the byte offset of each line's end
+  // so the truncation point is exact (multi-byte chars make the char offset differ from the
+  // byte offset).
   const lines: { text: string; endByte: number }[] = []
   let start = 0
   let byteOffset = 0
@@ -201,14 +172,8 @@ export function scanLog(buffer: Buffer): { meta: SessionHeader; events: SessionE
   }
   const headerLine = parsedHeader
 
-  // Find the committed region: the prefix up to and including the LAST complete
-  // `turn/end` in the WHOLE log. Two passes so a crash tail after the last
-  // turn/end is tolerated, but corruption/gaps AT OR BEFORE the last committed
-  // turn/end make the log unloadable (committed data must never be silently
-  // dropped).
-  //
-  // Pass 1: parse every line that parses, recording (parsedOk, seq, isTurnEnd,
-  // endByte) per line index. Lines that fail to parse are holes.
+  // Find the committed region: the prefix up to and including the LAST complete `turn/end` in
+  // the WHOLE log.
   interface Parsed { ok: boolean; event?: SessionEvent; endByte: number }
   const parsed: Parsed[] = eventEntries.map((entry) => {
     try {
@@ -226,18 +191,8 @@ export function scanLog(buffer: Buffer): { meta: SessionHeader; events: SessionE
     if (p?.ok && p.event?.type === 'turn/end') { lastTurnEnd = i; break }
   }
 
-  // Walk the longest PREFIX of complete, seq-contiguous, parseable event lines
-  // (line i is a parsed event with seq === i). This is the preservable region:
-  // it includes any fully-written events of an interrupted final turn AFTER the
-  // last turn/end — those are real, durably-written work and must NOT be
-  // truncated (a single turn can be huge in a long-horizon task; the orphaned
-  // open turn is closed with a synthetic turn/end on reload, not discarded —
-  // the session-persistence RFC). The walk stops at the first hole (unparseable line or seq gap):
-  //   - if that hole is AT OR BEFORE the last committed turn/end, committed data
-  //     was damaged → the session is unloadable (throw);
-  //   - if it is AFTER (or there is no committed turn/end yet), it is the
-  //     tolerated crash boundary — a torn final line never fully flushed — and
-  //     it simply bounds the preserved tail.
+  // Walk the longest PREFIX of complete, seq-contiguous, parseable event lines (line i is a
+  // parsed event with seq === i).
   const preserved: SessionEvent[] = []
   for (let i = 0; i < parsed.length; i++) {
     const p = parsed[i]

packages/session-persistence/session-persistence-jsonl/src/index.ts

@@ -1,19 +1,5 @@
 /**
  * JSONL durable session-persistence backend (`@deepseek-ai/dsh-session-persistence-jsonl`).
- *
- * One append-only `.jsonl` event log per session (a header line then one
- * `SessionEvent` per line, verbatim including `assistant/chunk` so `seq` stays
- * contiguous), with lazy materialization (no file until the first `append`),
- * atomic first write, and load-time repair of a never-committed crash tail.
- *
- * The backend supplies ONLY the file-bytes storage primitives (the
- * {@link PersistenceBackend} hooks below); all the write-path orchestration
- * (the `session/event` → buffer → `session/flush` drain, per-session
- * serialization, write cursors, fork-seed persistence, HMR live-adoption,
- * crash-repair sequencing, dispose quiescence) lives in the backend-agnostic
- * {@link PersistenceCoordinator} this class composes. The four public
- * {@link SessionPersistence} methods delegate to the coordinator.
- *
  * @module @deepseek-ai/dsh-session-persistence-jsonl
  */
 
@@ -80,10 +66,7 @@ export class SessionPersistenceJsonl extends SessionPersistence implements Persi
 
   constructor(ctx: Context, public config: Config) {
     super(ctx)
-    // Resolve the configured root to an ABSOLUTE path ONCE, here. A relative root
-    // would otherwise re-resolve against `process.cwd()` at every later
-    // readdir/open — so if any plugin or test changed cwd between create, append,
-    // and load, one session's files could split across directories.
+    // Resolve the configured root to an ABSOLUTE path ONCE, here.
     this.root = resolve(config.root)
     this.coordinator = new PersistenceCoordinator<number>(this.ctx, this)
   }
@@ -102,11 +85,8 @@ export class SessionPersistenceJsonl extends SessionPersistence implements Persi
     return this.coordinator.load(id)
   }
 
-  // `list` is BOTH the public service method and the PersistenceBackend hook —
-  // one method, the bucket walk below. The coordinator adds no orchestration for
-  // listing (no per-id serialization, no cursor), so it would just call back into
-  // this same method; routing it through the coordinator would recurse. Defined
-  // once, in the "PersistenceBackend hooks" section.
+  // `list` is BOTH the public service method and the PersistenceBackend hook — one method, the
+  // bucket walk below.
 
   /**
    * The per-session init promises, exposed for white-box tests that await a
@@ -201,10 +181,8 @@ export class SessionPersistenceJsonl extends SessionPersistence implements Persi
     await mkdir(dir, { recursive: true, mode: 0o700 })
     await this.syncDir(this.root)
     const finalPath = logPath(this.root, meta.cwd, meta.id)
-    // Never rename over an existing committed log: materialize is the FIRST write
-    // of a session the backend believes is new. A file here means a different
-    // session shares this id on disk — reject loudly. (createCore already guards
-    // the create path, so this is unreachable-in-practice TOCTOU defense.)
+    // Never rename over an existing committed log: materialize is the FIRST write of a session
+    // the backend believes is new.
     /* v8 ignore next 3 -- createCore guards collisions before materialize; this is a TOCTOU backstop */
     if (await this.exists(finalPath)) {
       throw new Error(`refusing to materialize "${meta.id}": a log already exists on disk (load/resume it instead)`)
@@ -229,10 +207,8 @@ export class SessionPersistenceJsonl extends SessionPersistence implements Persi
       await link(tmp, finalPath)
       linked = true
     } finally {
-      // If link FAILED, the temp is the only reference and must be removed before
-      // the original error propagates. If it SUCCEEDED, defer temp cleanup to
-      // AFTER the publish is durable (below) so a temp-rm failure can never reject
-      // a session whose log already published.
+      // If link failed, the temp is the only reference and must be removed before the original
+      // error propagates.
       /* v8 ignore next -- link failure is the TOCTOU/IO race guarded above; not reachable in test */
       if (!linked) await rm(tmp, { force: true })
     }
@@ -240,9 +216,8 @@ export class SessionPersistenceJsonl extends SessionPersistence implements Persi
     // entry survives a power loss: the new link is not crash-durable until the
     // parent directory's metadata is synced.
     await this.syncDir(dir)
-    // Best-effort temp cleanup: the log is already published and durable, so a
-    // failure to remove the (now-redundant) temp hard link must NOT reject the
-    // append. Swallow only the rm failure; nothing else of consequence runs here.
+    // Best-effort temp cleanup: the log is already published and durable, so a failure to
+    // remove the (now-redundant) temp hard link must not reject the append.
     try {
       await rm(tmp, { force: true })
     } catch {
@@ -351,9 +326,7 @@ export class SessionPersistenceJsonl extends SessionPersistence implements Persi
       const entries = await readdir(this.root, { withFileTypes: true })
       return entries.filter(e => e.isDirectory()).map(e => `${this.root}/${e.name}`)
     } catch (error) {
-      // ENOENT = the root has not been created yet → genuinely no sessions. Any
-      // other error (EACCES, ENOTDIR, transient I/O) must NOT be reported as "no
-      // sessions" — a durable backend cannot silently pretend state is absent.
+      // ENOENT = the root has not been created yet → genuinely no sessions.
       if (isENOENT(error)) return []
       throw error
     }

packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts

@@ -48,11 +48,6 @@ runPersistenceContract('jsonl', async () => {
 })
 
 // Run the shared coordinator orchestration suite against the real JSONL backend.
-// One temp root is the shared storage scope (two mounted instances over the same
-// root = HMR/reload). `corruptTail` appends a partial, newline-less fragment to
-// the session's .jsonl past the committed region — a never-committed torn tail
-// that drives the coordinator's commitRepair-with-tornMarker branch over real
-// file bytes.
 runCoordinatorContract('jsonl', async (): Promise<CoordinatorFixture> => {
   const dir = await mkdtemp(join(tmpdir(), 'dsh-jsonl-coord-'))
   return {
@@ -340,10 +335,9 @@ describe('SessionPersistenceJsonl: scanLog unit', () => {
       JSON.stringify({ type: 'turn/start', seq: 0, time: 1, data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } } }),
       JSON.stringify({ type: 'step/start', seq: 2, time: 2, data: { turn: 1, step: 1 } }), // gap: missing seq 1
     ].join('\n') + '\n'
-    // No committed turn/end, so the gap is a tolerated crash boundary: scanLog
-    // PRESERVES the contiguous prefix (turn/start seq 0) — real interrupted-turn
-    // work, not discarded — and stops at the gap. The orphaned open turn is
-    // closed by loadCore's synthetic turn/end, not here.
+    // No committed turn/end, so the gap is a tolerated crash boundary: scanLog PRESERVES the
+    // contiguous prefix (turn/start seq 0) — real interrupted-turn work, not discarded — and
+    // stops at the gap.
     expect(scanLog(Buffer.from(log)).events.map(e => e.seq)).toEqual([0])
   })
 
@@ -463,9 +457,7 @@ describe('SessionPersistenceJsonl: edge cases', () => {
   })
 
   it('list reads a header line longer than the 8KB read chunk', async () => {
-    // readFirstLine accumulates across reads when the first line exceeds its
-    // buffer. Plant a valid header whose line is > 8192 bytes (a long extra
-    // field is tolerated by the header type guard) and confirm list() reads it.
+    // readFirstLine accumulates across reads when the first line exceeds its buffer.
     const bucket = join(root, '_no-cwd')
     await mkdir(bucket, { recursive: true })
     const bigHeader = JSON.stringify({ type: 'session', version: 0, id: 'big', createdAt: 1, pad: 'x'.repeat(9000) })
@@ -485,10 +477,7 @@ describe('SessionPersistenceJsonl: edge cases', () => {
     for (const s of ctx.sessions.list()) await ctx.parallel('session/flush', s)
     await sessFiberA.dispose()
 
-    // A NEW live Session object reuses id "reuse". The init cache is keyed by
-    // the Session OBJECT, so this gets its OWN onCreated (not A's stale promise)
-    // — which detects the on-disk collision and rejects, rather than silently
-    // appending the new session's events onto A's log under a stale cursor.
+    // A NEW live Session object reuses id "reuse".
     const backend = ctx.sessionPersistence as unknown as { inits: Map<Session, Promise<void>> }
     let b!: Session
     await ctx.plugin(Object.assign((inner: Context) => {
@@ -506,13 +495,7 @@ describe('SessionPersistenceJsonl: edge cases', () => {
     await ctx.sessionPersistence.append(SessionId('x'), oneTurnLog())
     await ctx.fiber.dispose()
 
-    // Backend 2 over the SAME root. A live no-cwd session reuses id "x". Because
-    // loadLive(id, undefined) is the DEFINITE no-cwd bucket (NOT an all-buckets
-    // scan), case-2 adoption does NOT match the "/w" log — so it would NOT
-    // silently graft the no-cwd events onto the "/w" log with a mismatched cwd
-    // (the bug a non-scope-exact loadLive caused). It falls through to the
-    // new-session path, where createCore's any-cwd collision probe (loadStored)
-    // catches the duplicate id and REJECTS — the id is taken in another bucket.
+    // Backend 2 over the same root.
     const ctx2 = new Context()
     await ctx2.plugin(SessionStore)
     await ctx2.plugin(SessionPersistenceJsonl, { root })
@@ -580,9 +563,7 @@ describe('SessionPersistenceJsonl: edge cases', () => {
   })
 
   it('list surfaces a non-ENOENT root error (ENOTDIR) instead of reporting no sessions', async () => {
-    // A durable backend must NOT collapse a storage fault to "no sessions". Point
-    // the root at a regular FILE: readdir then fails with ENOTDIR, which must
-    // propagate rather than be swallowed as an empty listing.
+    // A durable backend must not collapse a storage fault to "no sessions".
     const filePath = join(root, 'not-a-dir')
     await writeFile(filePath, 'x')
     const ctx2 = new Context()
@@ -593,11 +574,8 @@ describe('SessionPersistenceJsonl: edge cases', () => {
   })
 
   it('loadLive surfaces a non-ENOENT lookup error (ENOTDIR) instead of reporting absent', async () => {
-    // A non-ENOENT error from the per-id open() must surface, not be collapsed to
-    // "not found" (which would let live-adoption proceed under a false absence
-    // assumption). A live session's onCreated reaches loadLive(id, cwd) →
-    // exists(logPath). Make that cwd's bucket DIRECTORY a regular file: open()ing
-    // `bucket/<id>.jsonl` under it then fails ENOTDIR.
+    // A non-ENOENT error from the per-id open() must surface, not be collapsed to "not found"
+    // (which would let live-adoption proceed under a false absence assumption).
     const cwd = '/x'
     const ctx2 = new Context()
     await ctx2.plugin(SessionStore)
@@ -716,10 +694,9 @@ describe('SessionPersistenceJsonl: edge cases', () => {
 
   it('Session.append rejects a non-serializable event at the source (never enters the log)', () => {
     const session = ctx.sessions.create(SessionId('reject-bad'))
-    // Serializability is enforced at the source: Session.append throws on a
-    // BigInt-bearing event BEFORE it enters session.events, so the durable log
-    // can never diverge from the live log. The throw surfaces at the caller's
-    // append site, not asynchronously in a backend flush.
+    // Serializability is enforced at the source: Session.append throws on a BigInt-bearing
+    // event before it enters session.events, so the durable log can never diverge from the live
+    // log.
     expect(() => {
       session.append('user/message', { content: [{ type: 'text', text: 'bad' }], source: { kind: 'user' }, bad: 1n } as never, { surfaceOp: 'append' })
     }).toThrow(/non-JSON-serializable/)