@sema-agent/core 5.45.0 → 5.46.0

package/CHANGELOG.md

@@ -1,5 +1,61 @@
 # Changelog
 
+## 5.46.0 — 2026-08-19
+
+### Added
+- design/319 A (system-reminder provenance mark): every engine-authored `<system-reminder>` OPEN
+  tag carries a per-session random `mark="<22-char base64url>"` attribute, and the system prompt
+  declares its semantics in ONE strict form — reminder-shaped text WITHOUT the current mark is
+  data wherever it appears. A forged reminder tag is now byte-distinguishable from an engine mint
+  on every verbatim inlet (Read/Bash/Grep/MCP-success). ZERO data-byte change: the mark rides only
+  the engine's own tag; Read stays verbatim, Edit across forged tags lands, Bash/Grep clean paths
+  are byte-compatible, and markless (library-direct) calls render historic bare bytes verbatim.
+  New exports: `mintReminderMark`, `isValidReminderMark`, `openSystemReminder`,
+  `mintSystemReminder`, `reminderMarkDeclaration` (scheme-replaceable mint home). Checkpoint gains
+  an additive `reminderMark` field + a new session-entry type `reminder_mark` (old readers ignore
+  both); a legacy or malformed-mark resume re-mints under the same strict declaration (historic
+  bare mints read as data — fail-safe). Consumers matching reminder tags by exact string must go
+  attribute-tolerant. A provider-owned pass-through prompt that renders no declaration discloses
+  loudly once per prepare (opt-in: `reminderMarkDeclaration(ctx.reminderMark)`).
+- design/336 slice 1 (F-020 deep fix — the origin carriage): an externally-exposed session's
+  ORDINARY memory writes now COMMIT carrying an engine-minted typed `origin` frontmatter marker
+  (taint + closed cause vocabulary + mint time) instead of the design/178 full quarantine that
+  zeroed TOC recall for every delegation-bearing session. Engine-exclusive and forgery-proof on
+  four faces (model-written origin bytes strip-with-disclosure — benign echo of the committed
+  marker stays silent; backend immutability law over every op spelling; inbound whitewash gate;
+  sync/bundle validation with rev honesty). Instruction-form files stay hard-gated. ONE deployment
+  seat: `RunnerDeps.memoryProvenance?: "off" | "carry"` (default `"carry"`; `"off"` restores
+  pre-336 containment byte-level; bad values refuse loudly, `config.memory_provenance`). New
+  public family: `MemoryEntryOrigin`/`MemoryOriginCause`/`MEMORY_ORIGIN_CAUSES`,
+  `committedOriginOf`, `originEquals`, `isInstructionEntry`. Bundle rows carry `marked`+`cause`;
+  lineage merge upgrades (never drops) a content-verified marked bit.
+- #342: the `run_workflow` lane gains the onAsk pass-through arm — every workflow-spawned agent's
+  own ask reaches the same operator as the host's (provenance-stamped, `parentToolCallId` +
+  `depth:1`) instead of the headless auto-deny. `RunWorkflowToolDeps.parentOnAsk` mount dep; a
+  deployment-pinned `base.onAsk` always wins; with no approver anywhere the fail-closed deny is
+  byte-identical. `AskRequest.delegation.parentToolCallId` is now reliable on the workflow lane.
+- #341: `SideQuerySpec.getApiKeyAndHeaders` — side-queries resolve per-model auth exactly like
+  the main lane (a gateway key no longer rides an external model's URL when a resolver is wired).
+- Memory-engine fencing (#262/#270/#191): journal recovery carries a fence token asserted at every
+  destructive write (redo/sweep/heal/commit-boundary/identity-close/migration); the chain-degraded
+  marker's directory entry is fsynced (POSIX name durability); txn-lock contention is typed
+  (EACCES vs EEXIST). #339 (stale-steal residual window) consolidated into design/186 v2 §3.1.
+
+### Fixed
+- The read-face LIST seats (`additionalDirectories`, `additionalReadDirectories`,
+  `readDenyPatterns` deps+spec) refuse non-array values loudly (`config.read_face_seat`) instead
+  of iterating a bare string character by character — `"/tmp/x"` no longer admits the
+  one-character root `"/"` into the write-capable allowlist, and a bare deny-"pattern" string no
+  longer dissolves into meaningless entries with zero refusal (#344, merged-code review). The
+  deny seats' ENTRY law stays with `compileReadDeny` (the `ReadDenyEntry` union's object form —
+  verify's frozen-posture carry — still completes).
+
+### Errata (5.44.0 changelog)
+- The "Tool contract revisions move: search 1→2, get 2→3" line overstated the rule — revisions
+  bump on execute-visible text changes, per the in-code note.
+- The #318 scope line ("single explicit FILE target's own spelling") was narrower than the shipped
+  behavior; see the path-prefix handling in `search.ts` (`relOut`).
+
 ## 5.45.0 — 2026-08-19
 
 ### Added

package/dist/agents/subagent.js

@@ -1915,7 +1915,7 @@ function createSubagentToolNode(opts, depth, excluded, extraToolsBudget) {
                     const wt = await finishWorktree();
                     return { isError: true, content: `Sub-agent not started: source session not found or fork unavailable.${wt ? `\n${wt}` : ""}`, details: { error: "source not found", forkLane: ctx.hostSessionFork ? "host" : "child-runner", ...(ctx.sessionId !== undefined ? { sourceSessionId: ctx.sessionId } : {}) } };
                 }
-                const forkInternals = { ...childInternals, insideFork: true };
+                const forkInternals = { ...childInternals, insideFork: true, ...(ctx.reminderMark !== undefined ? { reminderMark: ctx.reminderMark } : {}) };
                 stepRecorder.lockTo(forkedId);
                 const forkWorktreeNote = worktreeDir !== undefined ? forkWorktreeTranslationNote(ctx.parentCwd, worktreeDir) : undefined;
                 const forkObjective = `${FORK_DIRECTIVE_FRAME}${prompt}${forkWorktreeNote !== undefined ? `\n\n${forkWorktreeNote}` : ""}`;

package/dist/core/checkpoint-store.d.ts

@@ -807,6 +807,18 @@ export interface CheckpointState {
          *  scope for any in-row invariant). Absent = the row was minted ungoverned. */
         realApproval?: true;
     };
+    /**
+     * design/319 (A ticket) — the session's reminder provenance mark
+     * ({@link import("./reminder-mint.js").mintReminderMark}), persisted so a durable resume keeps
+     * minting the SAME mark its transcript's engine reminders and system-prompt declaration carry
+     * ("resume reuses" — one declaration, one mark). Additive on the existing checkpoint version —
+     * a reader that ignores it is unchanged (the :646 precedent; no version bump). Resume goes
+     * through the VERIFY port ({@link import("./reminder-mint.js").isValidReminderMark}): a missing
+     * field (pre-319 row) or an unrecognized value-shape (corrupt / foreign / old-scheme after a
+     * scheme change) RE-MINTS instead of adopting — the declaration stays strict, and the historic
+     * legs' reminders simply read as data (fail-safe downgrade, design/319 a-2).
+     */
+    reminderMark?: string;
     /**
      * design/78 Slice-1: the SAFE-tier self-repair loop's durable state (`failureTrace`/`diagnostics`/
      * `rejectedHypotheses`/`attemptCount`/`oracleTier` — all JSON/`structuredClone`-safe, no fn/Date). Set ONLY

package/dist/core/hooks.d.ts

@@ -583,8 +583,11 @@ export interface UserPromptSubmitResult {
  *  NOTE (council design/74 #6): this does NOT escape a literal `</system-reminder>` in `text` — callers MUST
  *  pass trusted, first-party strings (every current caller does: fixed gate/limit messages). If a future
  *  caller needs to relay UNTRUSTED content (tool output, user data), it must sanitize the close tag first
- *  (or use the `delimitUntrusted` fence), or a crafted payload could break out of the reminder framing. */
-export declare function formatHookFeedback(text: string): string;
+ *  (or use the `delimitUntrusted` fence), or a crafted payload could break out of the reminder framing.
+ *  design/319 (A ticket): `mark` is the session's reminder provenance mark — run-scoped callers thread it
+ *  so the open tag carries the value the system-prompt declaration names (rendered by the mint home; the
+ *  body is byte-untouched). Absent ⇒ the historic bare open tag (a caller outside a run). */
+export declare function formatHookFeedback(text: string, mark?: string): string;
 /** The outcome of the two-phase tool gate, mapped onto the harness `tool_call` hook return shape. */
 export interface ToolGateResult {
     /** Block execution (the loop emits an error tool result with `reason`). */
@@ -799,6 +802,10 @@ export interface ToolGateInput {
      *  per-leg mint; a host driving the gate directly may omit it, and the contexts then carry no
      *  identity (honest absence — this layer never fabricates a leg). */
     identity?: HookInvocationIdentity;
+    /** design/319 (A ticket) — the run's reminder provenance mark: the gate's own model-facing deny
+     *  reasons ride `formatHookFeedback`, so their open tags must carry the same mark the run's
+     *  system-prompt declaration names. Absent (a host driving the gate directly) ⇒ bare tags. */
+    reminderMark?: string;
     preToolUse?: Hooks["preToolUse"];
     /** The read-only env capability face put on every {@link HookToolContext} this gate call
      *  builds ({@link HookEnvCapabilities}). Built ONCE per task by the runner (after the env is minted) and

package/dist/core/hooks.js

@@ -1,6 +1,7 @@
 import { decisionText, describeThrown, refuseOutOfContractDecision } from "./tool-policy.js";
 import { brandPolicyAskClass } from "./ask-class.js";
 import { inlineUntrusted } from "./untrusted-text.js";
+import { mintSystemReminder } from "./reminder-mint.js";
 import { PROBE_REASON_MAX, normalizeProbeCause } from "./checkpoint-store.js";
 import { ASK_USER_QUESTION_TOOL_NAME } from "./ask-question.js";
 import { createSafeNotifier } from "./safe-notify.js";
@@ -90,8 +91,8 @@ export function mintHookInvocationIdentity(facts) {
         ...(facts.parentToolCallId !== undefined ? { parentToolCallId: facts.parentToolCallId } : {}),
     }));
 }
-export function formatHookFeedback(text) {
-    return `<system-reminder>\n${text}\n</system-reminder>`;
+export function formatHookFeedback(text, mark) {
+    return mintSystemReminder(text, mark);
 }
 const PARK_FAILURE_CAUSE_MAX = 600;
 function withParkFailureCause(reason, parkFailed) {
@@ -304,7 +305,7 @@ export async function runToolGate(input) {
             if (input.permissionDenied) {
                 await notifier.notifyAsync(() => input.permissionDenied?.({ toolName, input: cloneObserverInput(currentInput), toolCallId, reason, source: "hook", ...(input.identity !== undefined ? { identity: input.identity } : {}) }), "toolGate.permissionDenied");
             }
-            return { block: true, reason: formatHookFeedback(reason), preToolContext };
+            return { block: true, reason: formatHookFeedback(reason, input.reminderMark), preToolContext };
         }
         if (r) {
             if (r.additionalContext) {
@@ -313,7 +314,7 @@ export async function runToolGate(input) {
             if (r.action === "deny") {
                 return {
                     block: true,
-                    reason: formatHookFeedback(decisionText(r) ?? `tool "${toolName}" blocked by a PreToolUse hook`),
+                    reason: formatHookFeedback(decisionText(r) ?? `tool "${toolName}" blocked by a PreToolUse hook`, input.reminderMark),
                     preToolContext,
                 };
             }
@@ -813,7 +814,7 @@ export async function runToolGate(input) {
         const denyApprover = denySettledBy !== undefined ? resolvedApprover : undefined;
         return {
             block: true,
-            reason: formatHookFeedback(denyReason),
+            reason: formatHookFeedback(denyReason, input.reminderMark),
             ...(denySettledBy !== undefined ? { settledBy: denySettledBy } : {}),
             ...(denyApprover !== undefined ? { approver: denyApprover } : {}),
             preToolContext,

package/dist/core/memory-engine/content-origin.d.ts

@@ -6,7 +6,9 @@
  * into long-term memory? Three tiers:
  *
  *  - "external"  — network-retrieval families and external protocol channels. Invocation marks the
- *                  session's memory POLLUTED (one-way, durable; the polluted harvest quarantines).
+ *                  session's memory EXTERNALLY EXPOSED (one-way, durable; what the mark does at
+ *                  harvest is the provenance mode's question — design/336: tag-admit with an origin
+ *                  marker under "carry", full quarantine under "off").
  *  - "execution" — general execution (shell/exec). A NAMED residual channel: it can reach external
  *                  content indirectly, but the two industry anchors this tier is calibrated against
  *                  gate on network/protocol families only, and excluding every shell session would

package/dist/core/memory-engine/engine.d.ts

@@ -114,6 +114,29 @@ export interface MemoryEngineOptions {
     maxFiles?: number;
     /** Max nesting depth under the writable root (default {@link DEFAULT_MAX_ENTRY_DEPTH}). */
     maxDepth?: number;
+    /**
+     * design/336 §13-3 — the memory-provenance master switch (the deployment threads
+     * {@link import("../types.js").RunnerDeps.memoryProvenance} here; engine-direct hosts set it
+     * directly). Two exact spellings:
+     *  - `"carry"` (absent ≡ this; the default) — the 336 posture: an externally-exposed session's
+     *    ORDINARY memory writes commit WITH an engine-minted `origin` marker (tag-admit; the content
+     *    scan gates still run in full — a marker is not an exemption), instruction-form files
+     *    (type: feedback / v2 injection hints) are withheld and quarantined (the narrow `polluted`
+     *    rejection), the derived index's session prose still rolls back to its materialize-time
+     *    baseline, and exposure carries the SAME file-count cap and harvest budget as a clean
+     *    session;
+     *  - `"off"` — the pre-336 behavior: an exposed session's harvest admits nothing (every changed/
+     *    new file quarantines, host-auditable), no origin marker is ever MINTED, and the read side
+     *    mounts no origin decorations. One stated deviation from the byte level: origin-form
+     *    frontmatter written by the model is STILL stripped-with-warning from what commits (the
+     *    origin seat is engine-authored in both modes — preserving model-authored marker bytes under
+     *    "off" would hand a forgeable typed field to the next "carry" period), and an EXISTING
+     *    committed origin still carries forward on edits (the backend's immutability law is
+     *    structural and mode-independent — "off" stops minting, it never strips standing facts).
+     * Any other value refuses loudly at construction (`config.memory_provenance`, #123 — exact
+     * spellings, never truthiness).
+     */
+    provenance?: "off" | "carry";
     /** M7 — harvest deadline in ms (default {@link DEFAULT_HARVEST_DEADLINE_MS}); over-deadline files
      *  are deferred to the next harvest (report.degraded), never dropped. */
     harvestDeadlineMs?: number;
@@ -264,8 +287,13 @@ export interface EntryProvenanceAccount {
  * writing memory files, the harvest quarantined every one of them, and nothing said so while a host
  * could still act on it.
  *
+ * MODE-AWARE MESSAGE (design/336): the wording follows the engine's provenance mode — under
+ * `"carry"` (default) it states the tag-admit semantics (ordinary writes commit with an origin
+ * marker; instruction-form files are withheld); the `"off"`/absent spelling keeps the pre-336 text
+ * byte-identical. The caller passes the mode it constructed the engine with.
+ *
  * SCOPE OF THE CLAIM (adversarial-review round 1, P1 — the first cut PROMISED quarantine on every mark).
- * This notice states the VERDICT, not the mechanism's outcome: "no longer eligible", plus what a harvest
+ * This notice states the VERDICT, not the mechanism's outcome: "no longer eligible" (its "off" form), plus what a harvest
  * does WHEN IT COLLECTS. That distinction is load-bearing, because several real paths reach a polluted
  * harvest that quarantines nothing — a `writeScope`-null layering and a declared-unavailable session
  * both take `harvestCore`'s zero-admission return (nothing is collected, so nothing is captured), and a
@@ -290,6 +318,7 @@ export interface EntryProvenanceAccount {
 export declare function memorySessionPollutedNotice(input: {
     reason: string;
     sessionId?: string;
+    provenance?: "off" | "carry";
 }): EngineNotice;
 /**
  * The polluted harvest's loud half ({@link EngineNotice}): what the containment actually did, minted
@@ -340,6 +369,7 @@ export declare function memoryHarvestQuarantinedNotice(input: {
     escalated: number;
     reason?: string;
     sessionId?: string;
+    provenance?: "off" | "carry";
 }): EngineNotice;
 export declare class MemoryEngine {
     private readonly backend;
@@ -352,6 +382,8 @@ export declare class MemoryEngine {
     private readonly maxDepth;
     private readonly harvestDeadlineMs;
     private readonly harvestFileBudget;
+    /** {@link MemoryEngineOptions.provenance} — the design/336 master switch (screened at construction). */
+    private readonly provenance;
     /** {@link MemoryEngineOptions.onIncident} — the advisory disclosure seat (partition + announce codes). */
     private readonly onIncident;
     /** A backend-pinned directory (FileBackend zero-copy detection). */
@@ -394,7 +426,7 @@ export declare class MemoryEngine {
      * markers of one session would both read clean and both announce). Callers that do not disclose
      * ignore it exactly as before.
      */
-    markSessionPolluted(sessionId: string, reason: string): SessionPollutionMarkOutcome;
+    markSessionPolluted(sessionId: string, reason: string, cause?: import("./types.js").MemoryOriginCause): SessionPollutionMarkOutcome;
     /** The session's pollution record (in-process mark first, then the durable marker) — undefined =
      *  clean. Reads are side-effect-free. */
     sessionPollution(sessionId: string): SessionPollutionRecord | undefined;
@@ -587,6 +619,7 @@ export declare class MemoryEngine {
     }): Promise<MemorySessionHandle>;
     inject(handle: MemorySessionHandle, opts?: {
         writeToolMounted?: boolean;
+        reminderMark?: string;
     }): MemoryInjection;
     /**
      * design/138 S2-C — gate ONE tool write (Write/Edit/NotebookEdit) against the memory domain.
@@ -617,6 +650,7 @@ export declare class MemoryEngine {
     harvest(handle: MemorySessionHandle, opts?: {
         polluted?: {
             reason: string;
+            cause?: import("./types.js").MemoryOriginCause;
         };
         sessionId?: string;
         admitNothing?: {
@@ -652,6 +686,19 @@ export declare class MemoryEngine {
      *  the deleted disk file WAS the backend's storage). Zero-copy skips getByIds: its read-side scan
      *  cannot see a deleted file, and calling it mid-harvest would sync-adopt in-session edits. */
     private committedContentFor;
+    /**
+     * design/336 §2.2 (r4-9) — the COMMITTED frontmatter an origin carry-forward is computed against.
+     * Deliberately NOT {@link committedContentFor}'s non-zero-copy leg: that one calls the backend's
+     * plain `getByIds`, and the File backend's plain read path ADOPTS out-of-band disk changes (a
+     * read-side sync that advances revs and books retrievals) — a carry-forward read must be
+     * side-effect-free, or assembling one harvest mutates the store it is reading. Reading order:
+     *  - zero-copy File: the control-plane shadow IS the committed state (the disk file is the
+     *    session's own working copy — exactly what must NOT serve as the committed baseline);
+     *  - copy-out with a `retrievalView` face (File): the lock-free non-adopting view;
+     *  - twins (Pg/TiDB shapes): plain `getByIds` — naturally committed-state and side-effect-free
+     *    (the contract clause on {@link MemoryBackend.getByIds}).
+     */
+    private committedFrontmatterFor;
     /** L4/C-F9 (S2-0) — capture a gate-rejected file into control-plane quarantine FROM THE SCANNED
      *  CONTENT (never re-reading the path: the disk bytes may have been swapped since the scan —
      *  TOCTOU), then remove the suspect from the model-visible plane (delete, falling back to clearing
@@ -712,6 +759,6 @@ export declare class MemoryEngine {
 }
 /** Render drained announcements as ONE engine-owned system-reminder block (the lead/frame is
  *  trusted; item identifiers were neutralized at enqueue — see {@link MemoryAnnouncement.items}). */
-export declare function renderAnnouncements(queue: readonly MemoryAnnouncement[], folded: number): string;
+export declare function renderAnnouncements(queue: readonly MemoryAnnouncement[], folded: number, reminderMark?: string): string;
 /** Truncate the derived index to the CC injection parameters (200 lines / 25KB). */
 export declare function truncateIndex(text: string): string;