Adolf: decommission Cognee (H4) + standalone hindsight-llm + vault access

H4 (kb#76) - Cognee -> Hindsight migration finished:
- New openai/hindsight-llm/ (clone of cognee-llm, :8012, own volume) so
  Hindsight's Kimi LLM no longer depends on the cognee stack
- Repointed hindsight service LLM at hindsight-llm:8012 (+ depends_on)
- Removed cognee, cognee-mcp, cognee-llm services + cognee-llm-home volume
  from openai/docker-compose.yml
- Removed the disabled cognee-memory plugin entry from openclaw.json

Vault access (kb#64): wired the shared agap-mcp (:3100, same MCP Claude uses)
into Adolf's registry - "agap" server in shared-mcp.json + openclaw.json
mcp.servers. Adolf can now fetch credentials from Vaultwarden (verified).

Note: agap-mcp/docker-compose.yml (repointed to the adolf46 account) is
deliberately NOT in this commit - it holds the master password in plaintext.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014t8Qg9gi7H7HtT8MncoXAB

adolf/openclaw.json

@@ -131,6 +131,15 @@
           Authorization: "Bearer ${MARKETPLACE_MCP_TOKEN}",
         },
       },
+      // agap-mcp (kb#64) -- the SAME shared agap-mcp instance Claude Code uses
+      // (network_mode: host, :3100, unauthenticated on localhost). Grants Adolf
+      // the same access as Claude: vault (vw_* for credential fetching) plus
+      // gitea/ha/zabbix/radicale. Reached via host.docker.internal like
+      // kanboard/marketplace above.
+      agap: {
+        type: "http",
+        url: "http://host.docker.internal:3100/mcp",
+      },
     },
   },
 
@@ -138,27 +147,6 @@
   // load a plugin at startup (discovery alone is not enough).
   plugins: {
     entries: {
-      // Cognee memory plugin — DISABLED as of kb #75 (H3): superseded by
-      // hindsight-memory below. Left `enabled: false` rather than removed —
-      // full teardown (plugin dir, cognee/cognee-mcp/cognee-llm containers)
-      // is kb #75's H4, a separate step so the Hindsight path can be proven
-      // out first. Kept disabled (not both active) to avoid double
-      // prependContext injection and double persisted turns while both
-      // backends exist side by side.
-      "cognee-memory": {
-        enabled: false,
-        // External (non-bundled) plugins must opt in to conversation + prompt-injection
-        // hook access explicitly. before_prompt_build => allowPromptInjection;
-        // agent_end => allowConversationAccess.
-        hooks: { allowConversationAccess: true, allowPromptInjection: true },
-        // Throttle background cognify hard to stop it draining the Kimi quota:
-        // one cognify per dataset per hour (was 5 min default), and a longer
-        // persist timeout so /add doesn't fail-and-retry when cognee is busy.
-        config: {
-          sweepIntervalMs: 3600000, // 1h (default 300000 = 5min)
-          persistTimeoutMs: 20000,  // 20s (default 8000)
-        },
-      },
       // Hindsight memory plugin (kb #75, H3) — installed external plugin
       // under .openclaw/extensions/hindsight-memory, bind-mounted read-only
       // from openai/hindsight-openclaw-plugin (see that project's