docs: rebalance prose cleanup and add trimming skill

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

@@ -75,6 +75,9 @@ 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.
+ * Safe code units remain literal; every other unit, including `~`, becomes
+ * `~XXXX`. Operating on code units preserves lone surrogates, while special-
+ * casing `.` and `..` prevents traversal by an otherwise safe whole segment.
  *
  * @param raw - the string to encode; must be non-empty (throws on `''`).
  * @returns the escaped single path segment, decodable back to `raw`.
@@ -132,9 +135,10 @@ 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). Fully written events in an interrupted final turn remain part of the
+ * prefix. The first unparsable record or seq gap after the last `turn/end`
+ * marks a tolerated torn tail; the same hole in the committed region rejects.
  *
  * @param buffer - the raw bytes of the log file (header line first).
  * @returns the header, the preserved event prefix, and `committedBytes` — the
@@ -142,9 +146,8 @@ export function eventLine(event: SessionEvent): string {
  */
 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).
+  // Track complete lines by byte offset: a non-newline tail is torn and ignored,
+  // and a running counter avoids rescanning a long multi-byte log.
   const lines: { text: string; endByte: number }[] = []
   let start = 0
   let byteOffset = 0
@@ -172,8 +175,8 @@ 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.
+  // Parse every complete record first so the last valid `turn/end` determines
+  // whether an earlier hole is committed corruption or an uncommitted tail.
   interface Parsed { ok: boolean; event?: SessionEvent; endByte: number }
   const parsed: Parsed[] = eventEntries.map((entry) => {
     try {
@@ -191,8 +194,8 @@ 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).
+  // Preserve the contiguous prefix, including a complete interrupted turn;
+  // holes through the last committed boundary throw, while later holes stop.
   const preserved: SessionEvent[] = []
   for (let i = 0; i < parsed.length; i++) {
     const p = parsed[i]

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

@@ -1,5 +1,7 @@
 /**
- * JSONL durable session-persistence backend (`@deepseek-ai/dsh-session-persistence-jsonl`).
+ * JSONL durable session-persistence backend. It stores a header and contiguous
+ * events in one append-only file per session, and delegates orchestration to
+ * {@link PersistenceCoordinator}.
  * @module @deepseek-ai/dsh-session-persistence-jsonl
  */
 
@@ -66,7 +68,7 @@ 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.
+    // Resolve once so later process.cwd() changes cannot split one backend across roots.
     this.root = resolve(config.root)
     this.coordinator = new PersistenceCoordinator<number>(this.ctx, this)
   }
@@ -85,8 +87,8 @@ 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.
+  // One method serves both public `list` and the backend hook; delegating it to
+  // the coordinator would call this hook recursively.
 
   /**
    * The per-session init promises, exposed for white-box tests that await a
@@ -181,8 +183,7 @@ 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.
+    // Materialization is the first write; an existing log is an id collision.
     /* 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 "${meta.id}": a log already exists on disk (load/resume it instead)`)
@@ -207,8 +208,8 @@ export class SessionPersistenceJsonl extends SessionPersistence implements Persi
       await link(tmp, finalPath)
       linked = true
     } finally {
-      // If link failed, the temp is the only reference and must be removed before the original
-      // error propagates.
+      // Remove an unpublished temp on failure. After publication, defer cleanup
+      // until the directory entry is durable so cleanup cannot reject a live log.
       /* v8 ignore next -- link failure is the TOCTOU/IO race guarded above; not reachable in test */
       if (!linked) await rm(tmp, { force: true })
     }
@@ -326,7 +327,7 @@ export class SessionPersistenceJsonl extends SessionPersistence implements Persi
       const entries = await readdir(this.root, { withFileTypes: true })
       return entries.filter(e => e.isDirectory()).map(e => `${this.root}/${e.name}`)
     } catch (error) {
-      // ENOENT = the root has not been created yet → genuinely no sessions.
+      // Only an absent root means no sessions; rethrow every other I/O failure.
       if (isENOENT(error)) return []
       throw error
     }

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

@@ -54,7 +54,8 @@ runPersistenceContract('jsonl', async () => {
   }
 })
 
-// Run the shared coordinator orchestration suite against the real JSONL backend.
+// Two mounts share this temp root to exercise reload. `corruptTail` appends a partial,
+// newline-less fragment past the committed region so coordinator repair runs on real file bytes.
 runCoordinatorContract('jsonl', async (): Promise<CoordinatorFixture> => {
   const dir = await mkdtemp(join(tmpdir(), 'dsh-jsonl-coord-'))
   return {
@@ -344,7 +345,7 @@ describe('SessionPersistenceJsonl: scanLog unit', () => {
     ].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.
+    // stops at the gap. `loadCore`, not this scanner, later closes the orphaned turn.
     expect(scanLog(Buffer.from(log)).events.map(e => e.seq)).toEqual([0])
   })
 
@@ -464,7 +465,8 @@ 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.
+    // A tolerated extra field makes this valid header exceed the 8192-byte read buffer, proving
+    // `readFirstLine` accumulates chunks before `list()` parses it.
     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) })
@@ -484,7 +486,8 @@ 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".
+    // A new Session object reuses the id. Object-keyed initialization must run independently,
+    // detect the disk collision, and reject instead of appending through session A's stale cursor.
     const backend = ctx.sessionPersistence as unknown as { inits: Map<Session, Promise<void>> }
     let b!: Session
     await ctx.plugin(Object.assign((inner: Context) => {
@@ -502,7 +505,9 @@ describe('SessionPersistenceJsonl: edge cases', () => {
     await ctx.sessionPersistence.append(SessionId('x'), oneTurnLog())
     await ctx.fiber.dispose()
 
-    // Backend 2 over the same root.
+    // Backend 2 creates a no-cwd session whose id exists only in `/w`. Exact `loadLive(id,
+    // undefined)` must not adopt across buckets; the any-cwd collision check then rejects instead
+    // of grafting no-cwd events onto a log with mismatched cwd.
     const ctx2 = new Context()
     await ctx2.plugin(SessionStore)
     await ctx2.plugin(SessionPersistenceJsonl, { root })
@@ -570,7 +575,8 @@ 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".
+    // A durable backend must not collapse a storage fault to "no sessions". Making the root a
+    // regular file forces ENOTDIR from `readdir`, which must propagate.
     const filePath = join(root, 'not-a-dir')
     await writeFile(filePath, 'x')
     const ctx2 = new Context()
@@ -581,8 +587,8 @@ 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 non-ENOENT per-id open error must surface rather than become "not found" and permit false
+    // live adoption. Making the cwd bucket a regular file forces ENOTDIR for its child log path.
     const cwd = '/x'
     const ctx2 = new Context()
     await ctx2.plugin(SessionStore)
@@ -703,7 +709,7 @@ describe('SessionPersistenceJsonl: edge cases', () => {
     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.
+    // log. The error therefore surfaces synchronously at append, not later during backend flush.
     expect(() => {
       session.append('user/message', { content: [{ type: 'text', text: 'bad' }], source: { kind: 'user' }, bad: 1n } as never, { surfaceOp: 'append' })
     }).toThrow(/non-JSON-serializable/)