docs: sync with goclaw source changes c651cde5..b1f6eadf (EN+VI+ZH) (#56)

Major updates aligned with new goclaw subsystems:
- advanced/hooks-quality-gates.md: rewrite for new lifecycle hooks system (7 events, 3 handler types)
- advanced/context-pruning.md: reframe as opt-in (requires cache-ttl mode)
- advanced/tts-voice.md: add ElevenLabs model variants, agent-level voice config, STT note
- reference/websocket-protocol.md: add hooks.* RPC methods and config.defaults
- reference/rest-api.md: add TTS/github-releases endpoints, remove stale skill-apply
- reference/database-schema.md: bump to v55, add hooks/hook_agents/hook_executions/tenant_hook_budget tables, vault scope CHECK
- deployment/upgrading.md: add migrations 050-055
- getting-started/what-is-goclaw.md: add ACP Provider, Hooks System, Audio/TTS Manager
- core-concepts/how-goclaw-works.md: add Hooks Dispatcher, Audio/TTS Manager
- channels/pancake.md: add 8 new config fields

Also:
- .claude/skills/goclaw-docs-audit/mapping.json: extend coverage for audio/security/updater/webui/facebook/bgalert subsystems and docs/01-24 source files
- build-llms.js: generate llms-full.txt for all 3 languages (EN/VI/ZH)
- llms.txt + llms-full.txt × 3: regen and sync entries for hooks-quality-gates and system-prompt-anatomy

Author: thieung

.claude/skills/goclaw-docs-audit/mapping.json

@@ -33,6 +33,7 @@
     {"pattern": "internal/channels/zalo/*", "docs": ["channels/zalo-oa.md", "channels/zalo-personal.md", "troubleshooting/channels.md"], "priority": "medium"},
     {"pattern": "internal/channels/whatsapp/*", "docs": ["channels/whatsapp.md", "troubleshooting/channels.md"], "priority": "medium"},
     {"pattern": "internal/channels/pancake/*", "docs": ["channels/pancake.md", "troubleshooting/channels.md"], "priority": "high"},
+    {"pattern": "internal/channels/facebook/*", "docs": ["channels/facebook.md", "troubleshooting/channels.md"], "priority": "medium"},
     {"pattern": "internal/channels/slack/*", "docs": ["channels/slack.md", "troubleshooting/channels.md"], "priority": "medium"},
     {"pattern": "internal/channels/media/*", "docs": ["advanced/media-generation.md"], "priority": "low"},
     {"pattern": "internal/channels/typing/*", "docs": ["channels/overview.md"], "priority": "low"},
@@ -80,6 +81,18 @@
     {"pattern": "internal/skills/*", "docs": ["advanced/skills.md"], "priority": "medium"},
     {"pattern": "internal/sandbox/*", "docs": ["advanced/sandbox.md", "advanced/exec-approval.md"], "priority": "low"},
     {"pattern": "internal/tts/*", "docs": ["advanced/tts-voice.md"], "priority": "low"},
+    {"pattern": "internal/audio/elevenlabs/*", "docs": ["advanced/tts-voice.md"], "priority": "medium"},
+    {"pattern": "internal/audio/minimax/*", "docs": ["advanced/tts-voice.md"], "priority": "medium"},
+    {"pattern": "internal/audio/openai/*", "docs": ["advanced/tts-voice.md"], "priority": "medium"},
+    {"pattern": "internal/audio/edge/*", "docs": ["advanced/tts-voice.md"], "priority": "medium"},
+    {"pattern": "internal/audio/music/*", "docs": ["advanced/media-generation.md"], "priority": "low"},
+    {"pattern": "internal/audio/stt/*", "docs": ["advanced/tts-voice.md", "core-concepts/tools-overview.md"], "priority": "medium"},
+    {"pattern": "internal/audio/*", "docs": ["advanced/tts-voice.md", "advanced/media-generation.md"], "priority": "medium"},
+    {"pattern": "internal/security/*", "docs": ["deployment/security-hardening.md"], "priority": "medium"},
+    {"pattern": "internal/updater/*", "docs": ["deployment/upgrading.md", "getting-started/installation.md"], "priority": "medium"},
+    {"pattern": "internal/webui/*", "docs": ["getting-started/web-dashboard-tour.md"], "priority": "low"},
+    {"pattern": "internal/bgalert/*", "docs": ["deployment/observability.md"], "priority": "low"},
+    {"pattern": "internal/store/*", "docs": ["reference/database-schema.md"], "priority": "low"},
     {"pattern": "internal/permissions/*", "docs": ["agents/sharing-and-access.md", "advanced/api-keys-rbac.md", "advanced/usage-quota.md"], "priority": "medium"},
     {"pattern": "internal/config/*", "docs": ["reference/config-reference.md", "reference/environment-variables.md", "getting-started/configuration.md"], "priority": "medium"},
     {"pattern": "internal/workspace/*", "docs": ["agent-teams/creating-managing-teams.md", "advanced/sandbox.md"], "priority": "medium"},
@@ -123,12 +136,35 @@
     {"pattern": ".github/workflows/release*", "docs": ["deployment/upgrading.md", "getting-started/installation.md"], "priority": "low"},
 
     {"pattern": "docs/00-architecture*", "docs": ["getting-started/what-is-goclaw.md", "core-concepts/how-goclaw-works.md"], "priority": "high"},
+    {"pattern": "docs/01-agent-loop*", "docs": ["core-concepts/agents-explained.md", "core-concepts/how-goclaw-works.md", "agents/system-prompt-anatomy.md", "advanced/context-pruning.md"], "priority": "high"},
+    {"pattern": "docs/02-providers*", "docs": ["providers/overview.md", "providers/*.md"], "priority": "high"},
+    {"pattern": "docs/03-tools*", "docs": ["core-concepts/tools-overview.md", "advanced/custom-tools.md"], "priority": "high"},
+    {"pattern": "docs/04-gateway-protocol*", "docs": ["reference/websocket-protocol.md", "reference/rest-api.md"], "priority": "high"},
+    {"pattern": "docs/05-channels*", "docs": ["channels/overview.md", "channels/INDEX.md"], "priority": "high"},
+    {"pattern": "docs/06-store*", "docs": ["reference/database-schema.md"], "priority": "high"},
+    {"pattern": "docs/07-bootstrap*", "docs": ["agents/summoning-bootstrap.md", "agents/context-files.md"], "priority": "medium"},
+    {"pattern": "docs/08-scheduling*", "docs": ["advanced/scheduling-cron.md"], "priority": "medium"},
+    {"pattern": "docs/09-security*", "docs": ["deployment/security-hardening.md", "advanced/api-keys-rbac.md"], "priority": "high"},
+    {"pattern": "docs/10-tracing*", "docs": ["deployment/observability.md"], "priority": "medium"},
+    {"pattern": "docs/11-agent-teams*", "docs": ["agent-teams/*"], "priority": "high"},
+    {"pattern": "docs/12-extended-thinking*", "docs": ["advanced/extended-thinking.md"], "priority": "medium"},
+    {"pattern": "docs/13-ws-team-events*", "docs": ["agent-teams/team-messaging.md", "reference/websocket-protocol.md"], "priority": "medium"},
+    {"pattern": "docs/14-skills-runtime*", "docs": ["advanced/skills.md"], "priority": "high"},
+    {"pattern": "docs/15-core-skills*", "docs": ["advanced/skills.md"], "priority": "medium"},
+    {"pattern": "docs/16-skill-publishing*", "docs": ["advanced/skills.md"], "priority": "medium"},
     {"pattern": "docs/17-changelog*", "docs": ["deployment/upgrading.md"], "priority": "high"},
+    {"pattern": "docs/18-http-api*", "docs": ["reference/rest-api.md"], "priority": "high"},
+    {"pattern": "docs/19-websocket-rpc*", "docs": ["reference/websocket-protocol.md"], "priority": "high"},
+    {"pattern": "docs/20-api-keys*", "docs": ["advanced/api-keys-rbac.md"], "priority": "high"},
     {"pattern": "docs/21-agent-evolution*", "docs": ["advanced/agent-evolution.md"], "priority": "high"},
     {"pattern": "docs/22-v3-http*", "docs": ["reference/rest-api.md"], "priority": "high"},
     {"pattern": "docs/23-multi-tenant*", "docs": ["core-concepts/multi-tenancy.md"], "priority": "high"},
     {"pattern": "docs/24-knowledge-vault*", "docs": ["advanced/knowledge-vault.md"], "priority": "high"},
+    {"pattern": "docs/agent-hooks*", "docs": ["advanced/hooks-quality-gates.md"], "priority": "high"},
+    {"pattern": "docs/agent-identity*", "docs": ["agents/user-overrides.md", "agents/sharing-and-access.md"], "priority": "medium"},
+    {"pattern": "docs/packages-github*", "docs": ["advanced/skills.md", "deployment/security-hardening.md"], "priority": "medium"},
     {"pattern": "docs/model-steering*", "docs": ["advanced/model-steering.md", "agents/system-prompt-anatomy.md"], "priority": "high"},
+    {"pattern": "examples/hooks/*", "docs": ["advanced/hooks-quality-gates.md"], "priority": "low"},
 
     {"pattern": "README.md", "docs": ["getting-started/what-is-goclaw.md"], "priority": "medium"},
     {"pattern": "CLAUDE.md", "docs": ["getting-started/what-is-goclaw.md"], "priority": "low"},

advanced/context-pruning.md

@@ -17,7 +17,7 @@ Context pruning is distinct from [session compaction](../core-concepts/sessions-
 
 ## How Pruning Triggers
 
-Pruning runs automatically on every agent request unless explicitly disabled with `mode: "off"`. The flow:
+Pruning is **opt-in** — it only runs when `mode: "cache-ttl"` is set on the agent. The flow:
 
 ```
 history → limitHistoryTurns → pruneContextMessages → sanitizeHistory → LLM
@@ -76,12 +76,12 @@ This placeholder is configurable. Hard clear can also be disabled entirely.
 
 ## Configuration
 
-Context pruning is **on by default**. To disable it, set `mode: "off"` in the agent config.
+Context pruning is **opt-in**. To enable it, set `mode: "cache-ttl"` in the agent config.
 
 ```json
 {
   "contextPruning": {
-    "mode": "off"
+    "mode": "cache-ttl"
   }
 }
 ```
@@ -93,6 +93,7 @@ All other fields have sensible defaults and are optional.
 ```json
 {
   "contextPruning": {
+    "mode": "cache-ttl",
     "keepLastAssistants": 3,
     "softTrimRatio": 0.25,
     "hardClearRatio": 0.5,
@@ -112,7 +113,7 @@ All other fields have sensible defaults and are optional.
 
 | Field | Default | Description |
 |-------|---------|-------------|
-| `mode` | *(unset — pruning active)* | Set to `"off"` to disable pruning entirely. |
+| `mode` | *(unset — pruning disabled)* | Set to `"cache-ttl"` to enable pruning. Omit or leave empty to keep pruning off. |
 | `keepLastAssistants` | `3` | Number of recent assistant turns to protect from pruning. |
 | `softTrimRatio` | `0.25` | Trigger soft trim when context fills this fraction of the context window. |
 | `hardClearRatio` | `0.5` | Trigger hard clear when context fills this fraction after soft trim. |
@@ -127,12 +128,12 @@ All other fields have sensible defaults and are optional.
 
 ## Configuration Examples
 
-### Disable pruning entirely
+### Enable pruning (minimum config)
 
 ```json
 {
   "contextPruning": {
-    "mode": "off"
+    "mode": "cache-ttl"
   }
 }
 ```
@@ -144,6 +145,7 @@ Trigger earlier and keep less context per tool result:
 ```json
 {
   "contextPruning": {
+    "mode": "cache-ttl",
     "softTrimRatio": 0.2,
     "hardClearRatio": 0.4,
     "softTrim": {
@@ -160,6 +162,7 @@ Trigger earlier and keep less context per tool result:
 ```json
 {
   "contextPruning": {
+    "mode": "cache-ttl",
     "hardClear": {
       "enabled": false
     }
@@ -172,6 +175,7 @@ Trigger earlier and keep less context per tool result:
 ```json
 {
   "contextPruning": {
+    "mode": "cache-ttl",
     "hardClear": {
       "placeholder": "[Tool output removed to save context]"
     }
@@ -217,7 +221,7 @@ Once the consolidation pipeline has promoted a body of knowledge to L0 (via drea
 
 **Pruning never triggers**
 
-Confirm that `mode` is not set to `"off"`. Also confirm that `contextWindow` is set on the agent — pruning needs a token count to calculate ratios.
+Confirm that `mode` is set to `"cache-ttl"` — pruning is opt-in and disabled by default. Also confirm that `contextWindow` is set on the agent — pruning needs a token count to calculate ratios.
 
 **Agent re-runs tools unexpectedly**
 
@@ -227,7 +231,7 @@ Hard clear removes tool result content entirely. If the agent needs that content
 
 Increase `softTrim.headChars` and `softTrim.tailChars`, or raise `softTrim.maxChars` so fewer results are eligible for trimming.
 
-**Context still overflows despite pruning**
+**Context still overflows despite pruning being enabled**
 
 Pruning only acts on tool results. If long user messages or system prompt components dominate the context, pruning will not help. Consider [session compaction](../core-concepts/sessions-and-history.md) or reduce the system prompt size.