docs: clarify memory flush behavior

CHANGELOG.md

@@ -23,10 +23,11 @@
 - Plugins: add `clawdbot plugins install` (path/tgz/npm), plus `list|info|enable|disable|doctor` UX.
 - Plugins: voice-call plugin now real (Twilio/log), adds start/status RPC/CLI/tool + tests.
 - Docs: add plugins doc + cross-links from tools/skills/gateway config.
+- Docs: clarify memory flush behavior + writable workspace requirement in Memory/Session/FAQ.
 - Docs: add beginner-friendly plugin quick start + expand Voice Call plugin docs.
 - Tests: add Docker plugin loader + tgz-install smoke test.
 - Tests: extend Docker plugin E2E to cover installing from local folders (`plugins.load.paths`) and `file:` npm specs.
-- Tests: add coverage for pre-compaction memory flush settings.
+- Tests: add coverage for pre-compaction memory flush settings (including read-only/CLI skips).
 - Tests: modernize live model smoke selection for current releases and enforce tools/images/thinking-high coverage. (#769) — thanks @steipete.
 - Agents/Tools: add `apply_patch` tool for multi-file edits (experimental; gated by tools.exec.applyPatch; OpenAI-only).
 - Agents/Tools: rename the bash tool to exec (config alias maintained). (#748) — thanks @myfunc.
@@ -71,6 +72,7 @@
 - Agents: skip pre-compaction memory flush when the session workspace is read-only.
 - Auto-reply: allow inline `/status` for allowlisted senders (stripped before the model); unauthorized senders see it as plain text.
 - Auto-reply: include config-only allowlisted models in `/model` even when the catalog is partial.
+- Auto-reply: ignore inline `/status` directives unless the message is directive-only.
 - Auto-reply: align `/think` default display with model reasoning defaults. (#751) — thanks @gabriel-trigo.
 - Auto-reply: flush block reply buffers on tool boundaries. (#750) — thanks @sebslight.
 - Auto-reply: allow sender fallback for command authorization when `SenderId` is empty (WhatsApp self-chat). (#755) — thanks @juanpablodlc.

docs/concepts/memory.md

@@ -31,10 +31,10 @@ These files live under the workspace (`agents.defaults.workspace`, default
 
 ## Automatic memory flush (pre-compaction ping)
 
-When a session is **close to auto-compaction**, Clawdbot triggers a **silent
+When a session is **close to auto-compaction**, Clawdbot triggers a **silent,
 agentic turn** that reminds the model to write durable memory **before** the
-context is compacted. The default prompt encourages the model to respond with
-`NO_REPLY` when there's nothing to store, so the user never sees this turn.
+context is compacted. The default prompts explicitly say the model *may reply*,
+but usually `NO_REPLY` is the correct response so the user never sees this turn.
 
 This is controlled by `agents.defaults.compaction.memoryFlush`:
 
@@ -60,6 +60,7 @@ Details:
 - **Soft threshold**: flush triggers when the session token estimate crosses
   `contextWindow - reserveTokensFloor - softThresholdTokens`.
 - **Silent** by default: prompts include `NO_REPLY` so nothing is delivered.
+- **Two prompts**: a user prompt plus a system prompt append the reminder.
 - **One flush per compaction cycle** (tracked in `sessions.json`).
 - **Workspace must be writable**: if the session runs sandboxed with
   `workspaceAccess: "ro"` or `"none"`, the flush is skipped.

docs/concepts/session.md

@@ -25,6 +25,12 @@ All session state is **owned by the gateway** (the “master” Clawdbot). UI cl
 Clawdbot trims **old tool results** from the in-memory context right before LLM calls by default.
 This does **not** rewrite JSONL history. See [/concepts/session-pruning](/concepts/session-pruning).
 
+## Pre-compaction memory flush
+When a session nears auto-compaction, Clawdbot can run a **silent memory flush**
+turn that reminds the model to write durable notes to disk. This only runs when
+the workspace is writable. See [Memory](/concepts/memory) and
+[Compaction](/concepts/compaction).
+
 ## Mapping transports → session keys
 - Direct chats collapse to the per-agent primary key: `agent:<agentId>:<mainKey>`.
   - Multiple phone numbers and providers can map to the same agent main key; they act as transports into one conversation.

docs/start/faq.md

@@ -208,7 +208,8 @@ Clawdbot memory is just Markdown files in the agent workspace:
 - Curated long-term notes in `MEMORY.md` (main/private sessions only)
 
 Clawdbot also runs a **silent pre-compaction memory flush** to remind the model
-to write durable notes before auto-compaction. See [Memory](/concepts/memory).
+to write durable notes before auto-compaction. This only runs when the workspace
+is writable (read-only sandboxes skip it). See [Memory](/concepts/memory).
 
 ## Where things live on disk