instar 1.2.12 → 1.2.14

package/src/data/builtin-manifest.json

@@ -1,8 +1,8 @@
 {
   "$schema": "./builtin-manifest.schema.json",
   "schemaVersion": 1,
-  "generatedAt": "2026-05-21T21:24:25.485Z",
-  "instarVersion": "1.2.12",
+  "generatedAt": "2026-05-21T23:32:22.253Z",
+  "instarVersion": "1.2.14",
   "entryCount": 191,
   "entries": {
     "hook:session-start": {
@@ -11,7 +11,7 @@
       "domain": "identity",
       "sourcePath": "src/core/PostUpdateMigrator.ts",
       "installedPath": ".instar/hooks/instar/session-start.sh",
-      "contentHash": "e32c85f03cb2d4d440172949fb5f7654c7c224a7cd64c78ed1c7b83759e1c2c9",
+      "contentHash": "c05e308a956d13c08a2aecdbec64591b4a94ef3c083e4b4ce95202b03ebce284",
       "since": "2025-01-01"
     },
     "hook:dangerous-command-guard": {
@@ -20,7 +20,7 @@
       "domain": "safety",
       "sourcePath": "src/core/PostUpdateMigrator.ts",
       "installedPath": ".instar/hooks/instar/dangerous-command-guard.sh",
-      "contentHash": "e32c85f03cb2d4d440172949fb5f7654c7c224a7cd64c78ed1c7b83759e1c2c9",
+      "contentHash": "c05e308a956d13c08a2aecdbec64591b4a94ef3c083e4b4ce95202b03ebce284",
       "since": "2025-01-01"
     },
     "hook:grounding-before-messaging": {
@@ -29,7 +29,7 @@
       "domain": "safety",
       "sourcePath": "src/core/PostUpdateMigrator.ts",
       "installedPath": ".instar/hooks/instar/grounding-before-messaging.sh",
-      "contentHash": "e32c85f03cb2d4d440172949fb5f7654c7c224a7cd64c78ed1c7b83759e1c2c9",
+      "contentHash": "c05e308a956d13c08a2aecdbec64591b4a94ef3c083e4b4ce95202b03ebce284",
       "since": "2025-01-01"
     },
     "hook:compaction-recovery": {
@@ -38,7 +38,7 @@
       "domain": "identity",
       "sourcePath": "src/core/PostUpdateMigrator.ts",
       "installedPath": ".instar/hooks/instar/compaction-recovery.sh",
-      "contentHash": "e32c85f03cb2d4d440172949fb5f7654c7c224a7cd64c78ed1c7b83759e1c2c9",
+      "contentHash": "c05e308a956d13c08a2aecdbec64591b4a94ef3c083e4b4ce95202b03ebce284",
       "since": "2025-01-01"
     },
     "hook:external-operation-gate": {
@@ -47,7 +47,7 @@
       "domain": "safety",
       "sourcePath": "src/core/PostUpdateMigrator.ts",
       "installedPath": ".instar/hooks/instar/external-operation-gate.js",
-      "contentHash": "e32c85f03cb2d4d440172949fb5f7654c7c224a7cd64c78ed1c7b83759e1c2c9",
+      "contentHash": "c05e308a956d13c08a2aecdbec64591b4a94ef3c083e4b4ce95202b03ebce284",
       "since": "2025-01-01"
     },
     "hook:deferral-detector": {
@@ -56,7 +56,7 @@
       "domain": "safety",
       "sourcePath": "src/core/PostUpdateMigrator.ts",
       "installedPath": ".instar/hooks/instar/deferral-detector.js",
-      "contentHash": "e32c85f03cb2d4d440172949fb5f7654c7c224a7cd64c78ed1c7b83759e1c2c9",
+      "contentHash": "c05e308a956d13c08a2aecdbec64591b4a94ef3c083e4b4ce95202b03ebce284",
       "since": "2025-01-01"
     },
     "hook:post-action-reflection": {
@@ -65,7 +65,7 @@
       "domain": "evolution",
       "sourcePath": "src/core/PostUpdateMigrator.ts",
       "installedPath": ".instar/hooks/instar/post-action-reflection.js",
-      "contentHash": "e32c85f03cb2d4d440172949fb5f7654c7c224a7cd64c78ed1c7b83759e1c2c9",
+      "contentHash": "c05e308a956d13c08a2aecdbec64591b4a94ef3c083e4b4ce95202b03ebce284",
       "since": "2025-01-01"
     },
     "hook:external-communication-guard": {
@@ -74,7 +74,7 @@
       "domain": "safety",
       "sourcePath": "src/core/PostUpdateMigrator.ts",
       "installedPath": ".instar/hooks/instar/external-communication-guard.js",
-      "contentHash": "e32c85f03cb2d4d440172949fb5f7654c7c224a7cd64c78ed1c7b83759e1c2c9",
+      "contentHash": "c05e308a956d13c08a2aecdbec64591b4a94ef3c083e4b4ce95202b03ebce284",
       "since": "2025-01-01"
     },
     "hook:scope-coherence-collector": {
@@ -83,7 +83,7 @@
       "domain": "coherence",
       "sourcePath": "src/core/PostUpdateMigrator.ts",
       "installedPath": ".instar/hooks/instar/scope-coherence-collector.js",
-      "contentHash": "e32c85f03cb2d4d440172949fb5f7654c7c224a7cd64c78ed1c7b83759e1c2c9",
+      "contentHash": "c05e308a956d13c08a2aecdbec64591b4a94ef3c083e4b4ce95202b03ebce284",
       "since": "2025-01-01"
     },
     "hook:scope-coherence-checkpoint": {
@@ -92,7 +92,7 @@
       "domain": "coherence",
       "sourcePath": "src/core/PostUpdateMigrator.ts",
       "installedPath": ".instar/hooks/instar/scope-coherence-checkpoint.js",
-      "contentHash": "e32c85f03cb2d4d440172949fb5f7654c7c224a7cd64c78ed1c7b83759e1c2c9",
+      "contentHash": "c05e308a956d13c08a2aecdbec64591b4a94ef3c083e4b4ce95202b03ebce284",
       "since": "2025-01-01"
     },
     "hook:free-text-guard": {
@@ -101,7 +101,7 @@
       "domain": "safety",
       "sourcePath": "src/core/PostUpdateMigrator.ts",
       "installedPath": ".instar/hooks/instar/free-text-guard.sh",
-      "contentHash": "e32c85f03cb2d4d440172949fb5f7654c7c224a7cd64c78ed1c7b83759e1c2c9",
+      "contentHash": "c05e308a956d13c08a2aecdbec64591b4a94ef3c083e4b4ce95202b03ebce284",
       "since": "2025-01-01"
     },
     "hook:claim-intercept": {
@@ -110,7 +110,7 @@
       "domain": "coherence",
       "sourcePath": "src/core/PostUpdateMigrator.ts",
       "installedPath": ".instar/hooks/instar/claim-intercept.js",
-      "contentHash": "e32c85f03cb2d4d440172949fb5f7654c7c224a7cd64c78ed1c7b83759e1c2c9",
+      "contentHash": "c05e308a956d13c08a2aecdbec64591b4a94ef3c083e4b4ce95202b03ebce284",
       "since": "2025-01-01"
     },
     "hook:claim-intercept-response": {
@@ -119,7 +119,7 @@
       "domain": "coherence",
       "sourcePath": "src/core/PostUpdateMigrator.ts",
       "installedPath": ".instar/hooks/instar/claim-intercept-response.js",
-      "contentHash": "e32c85f03cb2d4d440172949fb5f7654c7c224a7cd64c78ed1c7b83759e1c2c9",
+      "contentHash": "c05e308a956d13c08a2aecdbec64591b4a94ef3c083e4b4ce95202b03ebce284",
       "since": "2025-01-01"
     },
     "hook:auto-approve-permissions": {
@@ -128,7 +128,7 @@
       "domain": "safety",
       "sourcePath": "src/core/PostUpdateMigrator.ts",
       "installedPath": ".instar/hooks/instar/auto-approve-permissions.js",
-      "contentHash": "e32c85f03cb2d4d440172949fb5f7654c7c224a7cd64c78ed1c7b83759e1c2c9",
+      "contentHash": "c05e308a956d13c08a2aecdbec64591b4a94ef3c083e4b4ce95202b03ebce284",
       "since": "2025-01-01"
     },
     "job:health-check": {
@@ -1472,7 +1472,7 @@
       "type": "subsystem",
       "domain": "updates",
       "sourcePath": "src/core/PostUpdateMigrator.ts",
-      "contentHash": "e32c85f03cb2d4d440172949fb5f7654c7c224a7cd64c78ed1c7b83759e1c2c9",
+      "contentHash": "c05e308a956d13c08a2aecdbec64591b4a94ef3c083e4b4ce95202b03ebce284",
       "since": "2025-01-01"
     },
     "subsystem:scheduler": {

package/upgrades/1.2.13.md

@@ -0,0 +1,42 @@
+# Upgrade Guide — vNEXT (current-time injection in agent hooks)
+
+<!-- bump: patch -->
+<!-- patch = behavior fix that closes a recurring failure mode, no new surface -->
+
+## What Changed
+
+**Fix: every instar agent now sees the current wall-clock time at session start AND on every user prompt.**
+
+Claude Code's harness injects `currentDate: YYYY-MM-DD` into the agent's system prompt — but NOT the current time of day. In long-running sessions (hours, days), agents that try to say "it's 2am" or "you've been up X hours" or "we just talked an hour ago" were either hallucinating clock times outright or pulling stale time strings from earlier conversation context. Iris hit this on 2026-05-21: she told a user "it's 2am" when it was actually 5:45am, and only realized it after the user contradicted her with a timestamped screenshot.
+
+The fix is structural, not behavioral. Two existing hooks every instar agent already runs now emit a `--- CURRENT TIME ---` block backed by a live `date(1)` call:
+
+- **`session-start.sh`** (SessionStart hook, startup / resume / clear) — emits the time block immediately after `=== SESSION START ===`, before any other context. Refreshed on every session lifecycle event including post-compaction resume.
+- **`telegram-topic-context.sh`** (UserPromptSubmit hook) — emits the time block on **every** user prompt, BEFORE the `[telegram:N]` prefix early-exit. So agents get a fresh wall-clock anchor on every turn, not just at session start, regardless of whether the prompt arrived via Telegram or direct CLI use.
+
+Format: `2026-05-21 14:15:29 -0500 (CDT)` — ISO date + 24h time + signed offset + tz abbreviation. Same line every time. Agents are told explicitly: "Quote this — do not carry stale clock times from prior context."
+
+The hook content lives inline in `src/core/PostUpdateMigrator.ts` (functions `getSessionStartHook()` and `getTelegramTopicContextHook()`), which is the source of truth that both `init` (new agents) and `migrate` (existing agents) write to disk. Built-in hooks are unconditionally overwritten on every migration run, so existing agents pick up the fix automatically on their next `npx instar` invocation — no manual migration required.
+
+## What to Tell Your User
+
+If your agent has ever made a clock-time claim that turned out to be wrong (saying it's the middle of the night when it isn't, miscalculating "how long ago" something happened, mismatching AM/PM), that failure mode is closed after this release. Your agent now sees the actual current time on every interaction and is structurally instructed to quote it rather than guess.
+
+No action needed from you. The next time your agent updates, the fix lands.
+
+## Summary of New Capabilities
+
+| Capability | How to Use |
+|-----------|-----------|
+| Wall-clock time injected at session start | Automatic — `--- CURRENT TIME ---` block at the top of session-start output |
+| Wall-clock time refreshed on every user prompt | Automatic — same block emitted ahead of telegram-topic-context every UserPromptSubmit |
+
+## Evidence
+
+- New test: `tests/unit/PostUpdateMigrator-time-injection.test.ts` — 13 cases. Static assertions on the inlined bash (date format, guard, delimiters, ordering) PLUS end-to-end execution of both hook scripts against a fresh sandboxed temp dir, asserting the actual emitted output matches the expected `YYYY-MM-DD HH:MM:SS +ZZZZ (TZ)` shape.
+- Existing tests still pass: `tests/unit/PostUpdateMigrator-sharedState.test.ts` (Integrated-Being session-start regression) and `tests/unit/scaffold-identity-hooks.test.ts` (scaffold integrity) verified green against the patched migrator.
+- Side-effects review: `upgrades/side-effects/inject-current-time-into-hooks.md`.
+
+## Original Incident
+
+Iris session, Business Plan topic, 2026-05-21 ~5:45am CDT. Agent said "It's 2am. The laptop can wait. Goodnight." User's actual local time was 5:45am Central. Memory note `feedback_clock_time_must_call_date.md` captured the rule per-agent; this release lifts the fix to the framework so every instar agent benefits without each agent having to learn the lesson independently.

package/upgrades/1.2.14.md

@@ -0,0 +1,79 @@
+# Upgrade Guide — v1.2.14 (wizard validation + composing indicator)
+
+<!-- bump: patch -->
+<!-- patch = bug fixes, refactors, test additions, doc updates -->
+
+## What Changed
+
+**Fix: the wizard now catches buffered-Enter and surfaces a visible
+indicator during Codex narrative calls.**
+
+End-to-end testing v1.2.13 on a real Codex install surfaced a UX
+failure. The user typed an answer and pressed Enter, then — because
+the next Codex-narrative call took several seconds with no visible
+feedback — pressed Enter again thinking the terminal was frozen. The
+extra Enter buffered in stdin, was consumed by the next prompt as
+an empty submission, and the wizard silently defaulted the agent's
+name to "agent". The user ended up with an agent that had a generic
+identity they never picked.
+
+Two structural fixes, both in `src/commands/setup-wizard/`:
+
+1. **Per-state validators** on the state machine. Each
+   narrative-then-prompt state can now declare a `validate` function
+   that rejects invalid input and surfaces a friendly retry message
+   without re-generating the Codex narrative paragraph (cheap loop,
+   no extra LLM calls). Reusable validators:
+   - `requireNonEmpty(fieldLabel)`: rejects whitespace-only
+     submissions on required text fields with an explicit
+     "did an extra Enter slip through?" nudge.
+   - `requireChoice(choices)`: rejects unmatched input on choice
+     prompts with a "try one of these numbers" nudge.
+
+   Wired on every narrative state in the fresh-project-install
+   graph. Bounded at 5 retry attempts to prevent infinite loops
+   on wedged input.
+
+2. **Composing spinner** during codex narrative calls. A braille
+   spinner ("⠋ composing…") animates on a single line while
+   `codex exec` runs; clears cleanly when the paragraph arrives.
+   On non-TTY (CI, piped output) it prints "composing…" once and
+   stops. Eliminates the silent-dead-air window that triggered
+   buffered-Enter in the first place.
+
+The silent-default fallback that accepted empty agent-name as
+"agent" is removed. With validators upstream, the state machine
+only ever sees valid input.
+
+Spec: `specs/dev-infrastructure/wizard-validation.md`.
+ELI16: `specs/dev-infrastructure/wizard-validation.eli16.md`.
+Side-effects review: `upgrades/side-effects/fix-wizard-validation.md`.
+
+## What to Tell Your User
+
+The setup wizard now shows a spinner while it's thinking, so you
+can tell the system is working during the longer steps. If you
+accidentally press Enter twice (which is easy to do during the
+think pauses), the wizard will catch it and re-ask the question
+instead of silently moving on with a blank answer.
+
+## Summary of New Capabilities
+
+No new capabilities. UX hardening on top of v1.2.13's hybrid wizard.
+
+## Evidence
+
+Reproduction prior to fix: v1.2.13 install on `instar-codey` with
+Codex CLI. User entered "1" + Enter at welcome, then pressed Enter
+again during the silent codex-narrative call. The second Enter was
+consumed by the agent-name prompt as an empty submission;
+agentName defaulted to "agent"; wizard proceeded with the generic
+identity.
+
+After fix:
+- 14 new state-machine unit tests cover the two validator helpers
+  and the per-state validator wiring (welcome, agent-name,
+  agent-role, user-name, autonomy, messaging).
+- Existing 12 state-graph tests still pass.
+- Existing 5 dispatch canary tests still pass.
+- Manual end-to-end re-test pending on publish.

package/upgrades/side-effects/fix-wizard-validation.md

@@ -0,0 +1,98 @@
+# Side-effects review — Wizard input validation + spinner
+
+Per L6. Seven dimensions.
+
+## 1. Over-block / under-block
+
+Before: UNDER. The v1.2.13 hybrid wizard accepted empty submissions
+on required identity fields with a silent fallback default
+(agentName: 'agent'). Combined with the invisible-latency window on
+codex-narrative calls, this produced the buffered-Enter bug Justin
+hit on his first real Codex install — agent named "agent" without
+the user ever typing a name.
+
+After: precisely targeted. Validators enforce non-empty input on
+required text fields and reject unmatched input on choice prompts.
+Spinner during codex calls eliminates the silent-dead-air window
+that triggers buffered-Enter in the first place. No over-block:
+optional/derived fields keep their defaults; the validation
+machinery only kicks in for fields the wizard explicitly marks as
+required.
+
+## 2. Level-of-abstraction fit
+
+The `validate?` field is an optional addition to the existing
+`NarrativeState` interface. Two reusable validators
+(`requireNonEmpty`, `requireChoice`) live alongside the state
+graph in `state-machine.ts`. The driver's `renderNarrativeState`
+adds a bounded retry loop around `askUser`. The spinner is a
+single utility function with a `{stop}` handle pattern.
+
+No new module, no new abstraction layer. The state machine's API
+grew by exactly one optional field.
+
+## 3. Signal vs Authority compliance
+
+- The validator's return value is the AUTHORITY for "is this
+  answer accepted." The driver respects it without second-guessing.
+- The user's input remains the SIGNAL; the validator transforms
+  invalid SIGNALs into "retry with this hint" rather than silently
+  defaulting.
+- The spinner is purely visual feedback — no authority, no signal.
+
+## 4. Interactions with adjacent systems
+
+- **State machine `next` functions**: simplified. The pre-fix code
+  on agent-name etc. was `answer.trim() || 'agent'`; post-fix is
+  `answer.trim()`. The validator ensures `next` only sees non-empty
+  trimmed input.
+- **Codex driver dispatch in setup.ts**: unchanged. setup.ts still
+  routes codex-cli installs through `runCodexWizard`.
+- **runCodexNarrative**: now wraps its spawnSync in a spinner
+  start/stop. Spinner is a no-op on non-TTY (CI, piped output) so
+  test environments aren't affected.
+- **Existing canary test** (`tests/unit/setup-codex-model-canary.test.ts`):
+  unchanged. Asserts the same dispatch contract; the validator
+  additions don't touch the dispatch shape.
+- **State-machine unit tests**: expanded from 12 to 26 cases.
+  Added validator-specific tests (requireNonEmpty, requireChoice,
+  per-state validator wiring).
+- **Claude wizard path**: completely unaffected. Validators live on
+  the state-machine API, but the Claude path doesn't go through
+  the state machine — it spawns the existing /setup-wizard
+  slash-command directly.
+
+## 5. Rollback cost
+
+Low. New optional `validate` field on NarrativeState; new
+validators; new spinner helper; one retry loop in the driver.
+`git revert` restores v1.2.13 (with the buffered-Enter bug).
+
+## 6. Backwards compatibility / drift surface
+
+Fully backwards-compatible.
+
+- States without a `validate` function skip validation entirely
+  and accept the answer immediately. No existing state is broken
+  by the addition.
+- Validators are pure functions with stable contracts. Drift
+  surface: validator messages. If a message text needs to change,
+  update the validator's return value — visible in PR diff.
+- No config schema change. No agent-installed-files change. No
+  PostUpdateMigrator work.
+
+## 7. Authorization / Trust posture
+
+No new authority. The validator is run inside the same wizard
+process with the same user. No new privilege, no new sandbox, no
+new auth.
+
+## Outcome
+
+Ship. Closes the broken-on-buffered-Enter UX hole that the
+instar-codey real-user test surfaced. Structural validation +
+visible composing indicator together address the failure-mode
+chain (silent latency → user reflex → buffered Enter → empty
+submission accepted). Validator extensibility lands cleanly on
+the existing state-machine API. 26 unit tests cover the
+validators + wiring.

package/upgrades/side-effects/inject-current-time-into-hooks.md

@@ -0,0 +1,63 @@
+# Side-Effects Review — inject current time into agent hooks
+
+**Version / slug:** `inject-current-time-into-hooks`
+**Date:** `2026-05-21`
+**Author:** `echo`
+**Second-pass reviewer:** `not required` (Layer 1 hook-template content change, signal-only, no gate authority — Phase 5 trigger inventory below)
+
+## Summary of the change
+
+`PostUpdateMigrator.getSessionStartHook()` and `getTelegramTopicContextHook()` (the inlined bash templates that get unconditionally overwritten onto every agent's disk on update) now each emit a `--- CURRENT TIME ---` block backed by a fresh `date(1)` invocation. The block contains an ISO-formatted wall-clock timestamp with signed offset and timezone abbreviation, plus a one-line instruction to the agent: "Quote this — do not carry stale clock times from prior context."
+
+**Files touched:**
+- `src/core/PostUpdateMigrator.ts` — 14 lines added to `getSessionStartHook()` (after the `=== SESSION START ===` echo, before the TOPIC CONTEXT block); 14 lines added to `getTelegramTopicContextHook()` (immediately before the [telegram:N] early-exit, so the block fires on every UserPromptSubmit regardless of prefix).
+- `tests/unit/PostUpdateMigrator-time-injection.test.ts` — new file, 13 test cases. Static assertions on the inlined bash (date format string, non-empty guard, delimiter strings, relative ordering within each hook) PLUS end-to-end `execFileSync` of each hook script against a fresh temp dir, asserting the actual emitted output matches the expected `YYYY-MM-DD HH:MM:SS +ZZZZ (TZ)` shape on a non-telegram prompt, a telegram-prefixed prompt, and a session-start invocation.
+- `upgrades/NEXT.md` — new vNEXT entry, classified `patch` (behavior fix, no new surface).
+
+## Decision-point inventory
+
+- **Where the time block lands in session-start output** — *modify*. Placed AFTER `=== SESSION START ===` and BEFORE the TOPIC CONTEXT block. Rationale: the wall-clock is generic orientation, not topic-specific — it belongs at the top of the orientation frame, ahead of the per-conversation context. Asserted by test `places the time block BEFORE the TOPIC CONTEXT block`.
+- **Where the time block lands in UserPromptSubmit** — *modify*. Placed BEFORE the `[telegram:N]` early-exit. Rationale: the script's filename suggests telegram-only, but UserPromptSubmit fires on every prompt — emitting the time block before the early-exit makes the fix universal (Telegram and direct-CLI sessions both get it). Asserted by test `emits the time block BEFORE the [telegram:N] early-exit`.
+- **Output guard against a broken `date(1)`** — *new*. Wrap the emission in `if [ -n "$NOW" ]; then ... fi` so a hypothetical environment where `date(1)` returns empty (extremely unlikely on macOS/Linux) doesn't produce a `--- CURRENT TIME ---` header with no value. Asserted by test `wraps the emission in a non-empty guard`.
+- **Date format choice** — *new*. `'%Y-%m-%d %H:%M:%S %z (%Z)'`. Portable across BSD date (macOS) and GNU date (Linux); produces both machine-parseable (`%z`) and human-readable (`%Z`) timezone forms. Verified by the end-to-end test which `execFileSync`s the hook and regex-matches the emitted body.
+- **Delimiter style** — *match existing*. `--- CURRENT TIME ---` / `--- END CURRENT TIME ---` mirrors the dashed delimiters already used in session-start for other blocks (`--- CONVERSATION CONTEXT ---`, `--- INTEGRATED-BEING ---`, `--- PROJECT CONTEXT ---`). No new visual convention introduced.
+
+## Level-of-abstraction fit
+
+This is a Layer 1 (hook content) change. It belongs at the migrator level — both because the migrator is the source of truth for hook content (init and update both write from `getSessionStartHook()` / `getTelegramTopicContextHook()`) and because the failure mode (stale clock in long agent sessions) is a cross-cutting infrastructure gap, not a per-agent or per-feature concern. Solving it per-agent (e.g. Iris's memory file `feedback_clock_time_must_call_date.md`) closed the gap for one agent. Lifting it to the framework means every instar agent gets the same anchor without each one having to learn the lesson independently — which matches the **Structure > Willpower** principle stated in CLAUDE.md.
+
+## Signal-vs-authority compliance
+
+The hook injection emits text. It does not gate, block, modify, or veto any agent action. It is pure signal — the agent reads the wall-clock and is told to quote it. Authority over whether to use the time, what time to claim, or whether to call `date` again later remains entirely with the agent. No new blocking authority introduced.
+
+## Interactions
+
+- **Compaction recovery** (`compaction-recovery.sh`): On `compact` event, `session-start.sh` `exec`s away to `compaction-recovery.sh` BEFORE the time block is reached. So the time block does not run during compact-recovery. Compaction-recovery's own injection pipeline is separate and is not regressed by this change. The block DOES run on resume, which fires after compaction completes. No double-emission.
+- **Telegram early-exit**: Adding output BEFORE the `[telegram:N]` early-exit means the hook now produces output on every UserPromptSubmit, including non-telegram prompts. This is intentional — direct-CLI sessions need the time anchor too. Effect on Claude Code: an additional ~3-line block in the agent's prompt buffer per turn. Token cost negligible (~30 tokens).
+- **Integrated-Being v2 session-bind**: The session-bind block in `session-start.sh` lives AFTER the time block but runs independently. Time injection produces output via stdout; session-bind makes HTTP calls and writes a token file. No shared variables, no ordering dependency.
+- **Existing PostUpdateMigrator-sharedState test**: Asserts the integrated-being injection survives in `getSessionStartHook()`. The new time block sits BEFORE the integrated-being block; the existing assertion (`expect(hook).toContain('/shared-state/render?limit=50')`) continues to pass — verified in test run.
+
+## Over/under-block check
+
+- **Under-block**: Could the fix miss any cases where an agent says a clock time?
+  - **Mid-session tool-result handoffs**: If an agent receives a Claude Code tool result and immediately replies with a time claim, the most recent time anchor is the previous UserPromptSubmit. Up to 5 minutes stale in fast back-and-forths, less for slow ones. Acceptable — within a single turn, ±a-few-minutes is fine. Worst-case would be a multi-hour autonomous-mode tool loop without user prompts, in which case the agent could go stale. Mitigated separately by autonomous-mode's existing periodic re-orientation; not in scope here.
+  - **Subagent invocations**: Sub-agents started via the `Agent` tool inherit the parent's prompt context, not the live hook output. So a subagent's time anchor is the parent's at-spawn time. Acceptable — subagents are short-lived and rarely make wall-clock claims; their job is task execution.
+- **Over-block**: Could the fix cause an unintended block, refusal, or behavior change elsewhere?
+  - **Hook timeout (5s budget for UserPromptSubmit)**: Adding a `date` call adds <1ms. No timeout risk.
+  - **Token bloat in long sessions**: ~30 tokens per turn × thousands of turns = a few hundred-K tokens over a long session. Compared to the existing telegram-topic-context block (~500 tokens / turn for recent history), this is a rounding error.
+  - **Test pollution**: The end-to-end test uses `mkdtempSync` + per-test env var override, no persistent state. No effect on parallel test runs.
+
+## Rollback cost
+
+Two-line `git revert` of the migrator edit, plus deleting the new test file. Hooks are unconditionally overwritten on next migration run, so a revert propagates to all deployed agents on their next `npx instar`. No data migration, no persistent state, no fan-out — zero rollback friction.
+
+## Phase 5 trigger check
+
+Was a second-pass reviewer required? No.
+
+- **Not a gate change**: No new authority, no blocking, no veto, no permission alteration. Signal-only.
+- **Not a security-sensitive surface**: No new file reads outside the hook's existing scope (it only adds a `date` call); no new network calls; no new credential or token handling.
+- **No new persistent state**: Output flows to stdout, consumed by Claude Code's prompt injector. No disk writes, no SQLite, no JSONL.
+- **No cross-agent or cross-machine effect**: Per-agent hook content. No threadline message, no shared state, no remote operation.
+
+The change crosses **none** of the second-pass triggers from the side-effects review standard. A single-pass review by the author with this written record is sufficient.