docs: cover compaction notifyUser config and provider replay hooks

docs/concepts/compaction.md

@@ -58,6 +58,26 @@ capable model for better summaries:
 }
 ```
 
+## Compaction start notice
+
+By default, compaction runs silently. To show a brief notice when compaction
+starts, enable `notifyUser`:
+
+```json5
+{
+  agents: {
+    defaults: {
+      compaction: {
+        notifyUser: true,
+      },
+    },
+  },
+}
+```
+
+When enabled, the user sees a short message (for example, "Compacting
+context...") at the start of each compaction run.
+
 ## Compaction vs pruning
 
 |                  | Compaction                    | Pruning                          |

docs/gateway/configuration-reference.md

@@ -1064,6 +1064,7 @@ Periodic heartbeat runs.
         identifierInstructions: "Preserve deployment IDs, ticket IDs, and host:port pairs exactly.", // used when identifierPolicy=custom
         postCompactionSections: ["Session Startup", "Red Lines"], // [] disables reinjection
         model: "openrouter/anthropic/claude-sonnet-4-6", // optional compaction-only model override
+        notifyUser: true, // send a brief notice when compaction starts (default: false)
         memoryFlush: {
           enabled: true,
           softThresholdTokens: 6000,
@@ -1082,6 +1083,7 @@ Periodic heartbeat runs.
 - `identifierInstructions`: optional custom identifier-preservation text used when `identifierPolicy=custom`.
 - `postCompactionSections`: optional AGENTS.md H2/H3 section names to re-inject after compaction. Defaults to `["Session Startup", "Red Lines"]`; set `[]` to disable reinjection. When unset or explicitly set to that default pair, older `Every Session`/`Safety` headings are also accepted as a legacy fallback.
 - `model`: optional `provider/model-id` override for compaction summarization only. Use this when the main session should keep one model but compaction summaries should run on another; when unset, compaction uses the session's primary model.
+- `notifyUser`: when `true`, sends a brief notice to the user when compaction starts (for example, "Compacting context..."). Disabled by default to keep compaction silent.
 - `memoryFlush`: silent agentic turn before auto-compaction to store durable memories. Skipped when workspace is read-only.
 
 ### `agents.defaults.contextPruning`

docs/plugins/architecture.md

@@ -590,7 +590,7 @@ Provider plugins now have two layers:
   runtime load, plus `providerAuthChoices` for cheap onboarding/auth-choice
   labels and CLI flag metadata before runtime load
 - config-time hooks: `catalog` / legacy `discovery`
-- runtime hooks: `resolveDynamicModel`, `prepareDynamicModel`, `normalizeResolvedModel`, `capabilities`, `prepareExtraParams`, `wrapStreamFn`, `formatApiKey`, `refreshOAuth`, `buildAuthDoctorHint`, `isCacheTtlEligible`, `buildMissingAuthMessage`, `suppressBuiltInModel`, `augmentModelCatalog`, `isBinaryThinking`, `supportsXHighThinking`, `resolveDefaultThinkingLevel`, `isModernModelRef`, `prepareRuntimeAuth`, `resolveUsageAuth`, `fetchUsageSnapshot`
+- runtime hooks: `resolveDynamicModel`, `prepareDynamicModel`, `normalizeResolvedModel`, `capabilities`, `prepareExtraParams`, `wrapStreamFn`, `formatApiKey`, `refreshOAuth`, `buildAuthDoctorHint`, `isCacheTtlEligible`, `buildMissingAuthMessage`, `suppressBuiltInModel`, `augmentModelCatalog`, `isBinaryThinking`, `supportsXHighThinking`, `resolveDefaultThinkingLevel`, `isModernModelRef`, `prepareRuntimeAuth`, `resolveUsageAuth`, `fetchUsageSnapshot`, `buildReplayPolicy`, `sanitizeReplayHistory`, `validateReplayTurns`
 
 OpenClaw still owns the generic agent loop, failover, transcript handling, and
 tool policy. These hooks are the extension surface for provider-specific behavior without
@@ -633,6 +633,9 @@ The "When to use" column is the quick decision guide.
 | 19  | `prepareRuntimeAuth`          | Exchange a configured credential into the actual runtime token/key just before inference | Provider needs a token exchange or short-lived request credential                    |
 | 20  | `resolveUsageAuth`            | Resolve usage/billing credentials for `/usage` and related status surfaces               | Provider needs custom usage/quota token parsing or a different usage credential      |
 | 21  | `fetchUsageSnapshot`          | Fetch and normalize provider-specific usage/quota snapshots after auth is resolved       | Provider needs a provider-specific usage endpoint or payload parser                  |
+| 22  | `buildReplayPolicy`          | Return a replay policy controlling transcript handling for the provider                  | Provider needs custom transcript policy (for example, thinking-block stripping)      |
+| 23  | `sanitizeReplayHistory`      | Rewrite replay history after generic transcript cleanup                                  | Provider needs provider-specific replay rewrites beyond shared compaction helpers     |
+| 24  | `validateReplayTurns`        | Final replay-turn validation or reshaping before the embedded runner                     | Provider transport needs stricter turn validation after generic sanitation            |
 
 If the provider needs a fully custom wire protocol or custom request executor,
 that is a different class of extension. These hooks are for provider behavior

docs/plugins/sdk-provider-plugins.md

@@ -312,6 +312,9 @@ API key auth, and dynamic model resolution.
       | 20 | `resolveUsageAuth` | Custom usage credential parsing |
       | 21 | `fetchUsageSnapshot` | Custom usage endpoint |
       | 22 | `onModelSelected` | Post-selection callback (e.g. telemetry) |
+      | 23 | `buildReplayPolicy` | Custom transcript policy (e.g. thinking-block stripping) |
+      | 24 | `sanitizeReplayHistory` | Provider-specific replay rewrites after generic cleanup |
+      | 25 | `validateReplayTurns` | Strict replay-turn validation before the embedded runner |
 
       For detailed descriptions and real-world examples, see
       [Internals: Provider Runtime Hooks](/plugins/architecture#provider-runtime-hooks).