chore: add memory review queue

docs/agent-memory/README.md

@@ -61,10 +61,11 @@ It does four things automatically:
 
 - injects the reviewed memory index and prompt change log into each agent turn through `before_agent_start`
 - records private raw metrics and session snapshots under `.agent-memory/raw/`
+- creates a reviewable pending memory candidate under `.agent-memory/review/pending/` after each completed agent turn
 - records provider header latency, agent duration, turn duration, tool counts, prompt submission gaps, and compaction/shutdown events
 - exposes memory and timing commands
 
-Raw metrics are intentionally gitignored. They are evidence for later compilation, not reviewed memory.
+Raw metrics and review candidates are intentionally gitignored. They are evidence for later compilation, not reviewed memory.
 
 The extension cannot infer true keystroke-level active typing time from Pi's current public extension events. It records explicit active work blocks plus automatic gap metrics:
 
@@ -85,6 +86,11 @@ Inside Pi:
 /memory-status
 /memory-capture [note]
 /memory-compile [goal]
+/memory-review
+/memory-show [filename-fragment]
+/memory-approve [filename-fragment]
+/memory-discard [filename-fragment]
+/memory-clear
 /prompt-start [label]
 /prompt-pause
 /prompt-resume
@@ -97,6 +103,22 @@ Inside Pi:
 
 `/memory-compile` captures a private snapshot and then asks Pi to run `/pi-evolve` against the latest evidence.
 
+After each agent turn, inspect pending candidates:
+
+```text
+/memory-review
+/memory-show
+```
+
+Approve the latest or matching candidate:
+
+```text
+/memory-approve
+/memory-approve 20260429T120000Z
+```
+
+Approval moves the candidate to `.agent-memory/review/approved/` and launches `/pi-evolve` so reviewed memory and prompt changes can be proposed. Discard candidates with `/memory-discard` or clear all pending candidates with `/memory-clear`.
+
 Use `/prompt-start` when you begin an active prompting/planning block and `/prompt-stop` when you finish. Use `/prompt-pause` before leaving for an extended wait and `/prompt-resume` when you return. `/time-report` writes a private report under `.agent-memory/reports/`.
 
 ## Guardrails

docs/agent-memory/log.md

@@ -16,3 +16,9 @@
 - Added explicit active prompting/work commands: `/prompt-start`, `/prompt-pause`, `/prompt-resume`, `/prompt-stop`, and `/time-report`.
 - Reports are written under `.agent-memory/reports/` and remain private/gitignored.
 - This measures explicit work blocks and idle-capped gaps, not hidden keystroke-level activity.
+
+## [2026-04-29] review | Automatic memory candidates
+
+- Added automatic pending memory candidates under `.agent-memory/review/pending/` after each completed agent turn.
+- Added `/memory-review`, `/memory-show`, `/memory-approve`, `/memory-discard`, and `/memory-clear`.
+- Approval moves a candidate to `.agent-memory/review/approved/` and launches `/pi-evolve`.

docs/agent-memory/prompt-change-log.md

@@ -19,3 +19,9 @@
 - Added `/prompt-start`, `/prompt-pause`, `/prompt-resume`, `/prompt-stop`, and `/time-report`.
 - Active user prompting/work time is measured by explicit work blocks with pause support.
 - Automatic metrics still record prompt gaps, idle-excluded gaps, agent duration, turn duration, provider header latency, and tool counts.
+
+## [2026-04-29] review | Automatic memory review queue
+
+- Added reviewable pending memory candidates after each agent turn.
+- Added `/memory-review`, `/memory-show`, `/memory-approve`, `/memory-discard`, and `/memory-clear`.
+- Durable memory and prompt changes still require approval; automatic capture does not write reviewed memory directly.