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-      // Cognee memory plugin — DISABLED as of kb #75 (H3): superseded by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

openai/docker-compose.yml

@@ -210,17 +210,17 @@ services:
       ["node", "dist/index.js", "gateway", "--bind", "lan", "--port", "18789"]
     restart: unless-stopped
 
-  # cognee-llm — stateless one-shot Kimi-CLI wrapper for Cognee's batch cognify
+  # hindsight-llm — standalone clone of cognee-llm (kb#76, H4 option B): the
-  # (P3). Opposite policy to kimi-agent: no resume, non-streaming, text-only.
+  # dedicated Kimi-CLI wrapper that is now Hindsight's LLM, so the whole cognee
-  # Note (SPIKE-FINDINGS gate 5): Cognee should DEFAULT its LLM to LiteLLM; this
+  # stack (incl. cognee-llm) can be decommissioned. Own port (:8012) + own
-  # is the optional low-volume path. Needs `kimi login` in its own volume.
+  # kimi-code volume; needs a one-time `kimi login` seeded into hindsight-llm-home.
-  cognee-llm:
+  hindsight-llm:
-    build: ./cognee-llm
+    build: ./hindsight-llm
-    container_name: cognee-llm
+    container_name: hindsight-llm
     ports:
-      - "8011:8011"
+      - "8012:8012"
     volumes:
-      - cognee-llm-home:/root/.kimi-code
+      - hindsight-llm-home:/root/.kimi-code
     restart: unless-stopped
 
   # adolf-llm — conversational Kimi-CLI wrapper (:8010), the model backend for
@@ -244,68 +244,6 @@ services:
       - "host.docker.internal:host-gateway"
     restart: unless-stopped
 
-  # cognee — Adolf's memory backend (P4). FastAPI + embedded Kuzu graph +
-  # Qdrant vectors. LLM via cognee-llm:8011 (Kimi CLI wrapper), embeddings via
-  # ollama directly (host.docker.internal:11436, separate compose project —
-  # hence extra_hosts below). Sole owner of the on-disk Kuzu/SQLite files
-  # under /mnt/ssd/dbs/cognee/ (Kuzu is not safe for concurrent multi-process
-  # access) — never run a second process against those files.
-  cognee:
-    build: ./cognee
-    container_name: cognee
-    restart: unless-stopped
-    environment:
-      # Real OS env var, not just the mounted .env file: the qdrant vector
-      # adapter's registration hook (cognee/Dockerfile's sitecustomize.py)
-      # gates on os.environ.get("VECTOR_DB_PROVIDER") at Python interpreter
-      # start, which only sees actual container env vars — pydantic-settings'
-      # env_file=".env" parsing (used for the rest of cognee.env) never
-      # populates os.environ itself. Without this, cognee raises
-      # "Unsupported vector database provider: qdrant" at startup even though
-      # cognee.env sets VECTOR_DB_PROVIDER=qdrant. Verified 2026-07-05.
-      - VECTOR_DB_PROVIDER=qdrant
-    volumes:
-      - ./cognee/cognee.env:/app/.env
-      - /mnt/ssd/dbs/cognee/data:/data
-      - /mnt/ssd/dbs/cognee/system:/system
-    extra_hosts:
-      - "host.docker.internal:host-gateway"
-    # Not published to the host — only cognee-mcp (same compose network)
-    # needs to reach it. Uncomment for local debugging:
-    # ports:
-    #   - "8000:8000"
-    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
-      interval: 30s
-      timeout: 10s
-      retries: 3
-      start_period: 40s
-
-  # cognee-mcp — thin MCP-to-HTTP proxy in API mode (API_URL=cognee:8000).
-  # Never opens the graph/vector files itself, so it's safe to run alongside
-  # `cognee` without a second writer on the same Kuzu database. Exposes 3
-  # tools: remember / recall / forget.
-  #
-  # Built from a local Dockerfile (kb#70 fix) instead of the bare upstream
-  # image: forget was missing a data_id parameter end-to-end, so agents
-  # could delete a whole dataset but never a single entry. See
-  # ./cognee-mcp/Dockerfile and ./cognee-mcp/src/ for the patched files.
-  cognee-mcp:
-    build: ./cognee-mcp
-    container_name: cognee-mcp
-    restart: unless-stopped
-    environment:
-      - ENV=local
-      - LOG_LEVEL=INFO
-      - PYTHONUNBUFFERED=1
-      - TRANSPORT_MODE=http
-      - API_URL=http://cognee:8000
-      - MCP_ALLOWED_HOSTS=cognee-mcp:*
-    ports:
-      - "8001:8000"
-    depends_on:
-      - cognee
-
   # hindsight — Adolf memory backend, replacing cognee/cognee-mcp/cognee-llm
   # (kb#73, migration doc agap_git/adolf/HINDSIGHT-MIGRATION.md, H1). One
   # container: REST API :8888 (also serves the built-in MCP at /mcp/{bank}/),
@@ -317,7 +255,7 @@ services:
   # LLM + embeddings reconfigured 2026-07-15 (kb#84) to fix two wrong H1
   # choices for a Russian/multilingual use case:
   #
-  # LLM -> cognee-llm:8011 (the existing Kimi-CLI wrapper, same shim cognee
+  # LLM -> hindsight-llm:8012 (dedicated Kimi-CLI wrapper cloned from the shim cognee
   # uses — see cognee/cognee.env's LLM section for the full precedent,
   # including why LLM_INSTRUCTOR_MODE=json_mode isn't needed here since
   # Hindsight's own client doesn't go through `instructor`). Replaces the
@@ -353,11 +291,11 @@ services:
     restart: unless-stopped
     environment:
       - HINDSIGHT_API_LLM_PROVIDER=openai
-      - HINDSIGHT_API_LLM_BASE_URL=http://cognee-llm:8011/v1
+      - HINDSIGHT_API_LLM_BASE_URL=http://hindsight-llm:8012/v1
-      - HINDSIGHT_API_LLM_MODEL=openai/cognee-llm
+      - HINDSIGHT_API_LLM_MODEL=openai/hindsight-llm
-      # cognee-llm ignores the key entirely (Kimi CLI wrapper, no real
+      # hindsight-llm ignores the key entirely (Kimi CLI wrapper, no real
-      # OpenAI auth) — same dummy value cognee.env uses for LLM_API_KEY.
+      # OpenAI auth) — dummy value, non-empty so the client constructs.
-      - HINDSIGHT_API_LLM_API_KEY=sk-cognee-llm-local
+      - HINDSIGHT_API_LLM_API_KEY=sk-hindsight-llm-local
       - HINDSIGHT_API_EMBEDDINGS_PROVIDER=openai
       - HINDSIGHT_API_EMBEDDINGS_OPENAI_BASE_URL=http://host.docker.internal:11436/v1
       - HINDSIGHT_API_EMBEDDINGS_OPENAI_MODEL=bge-m3
@@ -393,7 +331,7 @@ services:
       # file.
       - "host.docker.internal:host-gateway"
     depends_on:
-      - cognee-llm
+      - hindsight-llm
 
   # openclaw-tools — MCP bridge (P5) exposing a minimal slice of the Adolf
   # OpenClaw gateway's agent tools (message/cron/nodes/browser) over MCP
@@ -417,6 +355,6 @@ services:
 volumes:
   kimi-agent-home:
   adolf-state:
-  cognee-llm-home:
+  hindsight-llm-home:
   adolf-llm-workspace:
   adolf-llm-home:

openai/hindsight-llm/Dockerfile

@@ -0,0 +1,11 @@
+FROM node:22-slim
+
+RUN npm install -g @moonshot-ai/kimi-code
+
+WORKDIR /workspace
+
+COPY server.js /app/server.js
+
+EXPOSE 8012
+
+ENTRYPOINT ["node", "/app/server.js"]

openai/hindsight-llm/server.js

@@ -0,0 +1,178 @@
+const http = require('http');
+const fs = require('fs');
+const path = require('path');
+const crypto = require('crypto');
+const { spawn } = require('child_process');
+
+const PORT = 8012;
+const MODEL_ID = 'hindsight-llm';
+const TIMEOUT_MS = 5 * 60 * 1000; // one-shot structured calls; generous but bounded
+// Bounded parallelism: SPIKE-FINDINGS.md gate 5 flagged the Kimi subscription as a
+// single-seat, interactive-oriented plan — batch cognify must not hammer it with
+// unbounded concurrent CLI spawns (rate-limit/throttle risk on a shared live account).
+const MAX_CONCURRENCY = 3;
+
+const WORKSPACE = '/workspace';
+fs.mkdirSync(WORKSPACE, { recursive: true });
+
+// The CLI has no raw sampling-temperature knob (it's an agent loop, not a
+// completions API) — "low temperature" for structured extraction is enforced
+// via an instruction preamble instead, prepended to whatever system prompt
+// the caller (Cognee) supplies.
+const STRUCTURED_SYSTEM_PREAMBLE = [
+  'You are a stateless structured-extraction engine.',
+  'This is a one-shot call with no memory of prior calls: do not reference earlier turns.',
+  'Respond deterministically and concisely. When asked for JSON, output raw JSON only',
+  '- no prose, no markdown code fences, no commentary before or after.',
+].join(' ');
+
+// --- message helpers ---------------------------------------------------------
+// Text only, no media parts: this wrapper's policy is no-media/no-MCP, unlike
+// adolf-llm which persists inbound images and lets the CLI's ReadMediaFile
+// tool read them.
+function textOf(msg) {
+  const c = msg.content;
+  if (Array.isArray(c)) return c.map(p => (typeof p.text === 'string' ? p.text : '')).join('\n');
+  return c == null ? '' : String(c);
+}
+
+function buildPrompt(messages) {
+  const systemParts = messages.filter(m => m.role === 'system').map(textOf);
+  const rest = messages.filter(m => m.role !== 'system');
+  const preamble = [STRUCTURED_SYSTEM_PREAMBLE, ...systemParts].join('\n\n');
+  const transcript = rest
+    .map(m => `${m.role === 'assistant' ? 'Assistant' : 'User'}: ${textOf(m)}`)
+    .join('\n\n');
+  return `${preamble}\n\n${transcript}`.trim();
+}
+
+// --- bounded concurrency queue -----------------------------------------------
+let active = 0;
+const queue = [];
+function drain() {
+  if (queue.length && active < MAX_CONCURRENCY) queue.shift()();
+}
+function withSlot(fn) {
+  return new Promise((resolve, reject) => {
+    const run = () => {
+      active++;
+      fn().then(
+        v => { active--; drain(); resolve(v); },
+        e => { active--; drain(); reject(e); },
+      );
+    };
+    if (active < MAX_CONCURRENCY) run();
+    else queue.push(run);
+  });
+}
+
+// --- kimi invocation: stateless one-shot, no resume --------------------------
+// Fresh temp dir per call, NO -r/-S session flag, discard the dir after.
+// Returns the assembled text from --output-format stream-json:
+//   {"role":"assistant","content":"..."}
+// (reuses the same parse core as kimi-agent/server.js's runKimi, minus the
+// resume/session-id bookkeeping that wrapper needs and this one deliberately
+// does not).
+function runKimi({ prompt, cwd }) {
+  return new Promise((resolve, reject) => {
+    const args = ['-p', prompt, '--output-format', 'stream-json'];
+    const child = spawn('kimi', args, { cwd, timeout: TIMEOUT_MS });
+
+    let stdout = '';
+    let stderr = '';
+    child.stdout.on('data', d => { stdout += d; });
+    child.stderr.on('data', d => { stderr += d; });
+
+    child.on('error', reject);
+    child.on('close', code => {
+      const parts = [];
+      for (const line of stdout.split('\n')) {
+        const t = line.trim();
+        if (!t) continue;
+        let obj;
+        try { obj = JSON.parse(t); } catch { continue; }
+        if (obj.role === 'assistant' && obj.content) parts.push(obj.content);
+      }
+      const text = parts.join('').trim();
+      if (!text && code !== 0) {
+        reject(new Error(`kimi exited ${code}: ${stderr.slice(0, 2000)}`));
+      } else {
+        resolve(text);
+      }
+    });
+  });
+}
+
+async function handleTurn(messages) {
+  const prompt = buildPrompt(messages || []);
+  const reqId = crypto.randomUUID();
+  const dir = path.join(WORKSPACE, reqId);
+  fs.mkdirSync(dir, { recursive: true });
+  try {
+    return await withSlot(() => runKimi({ prompt, cwd: dir }));
+  } finally {
+    // Stateless one-shot: nothing about this call is meant to survive it, so
+    // the temp dir is discarded unconditionally, success or failure.
+    fs.rm(dir, { recursive: true, force: true }, () => {});
+  }
+}
+
+// --- OpenAI-compatible HTTP surface (non-streaming only) ---------------------
+function completionBody(text) {
+  return {
+    id: `chatcmpl-${Date.now()}`,
+    object: 'chat.completion',
+    created: Math.floor(Date.now() / 1000),
+    model: MODEL_ID,
+    choices: [{
+      index: 0,
+      message: { role: 'assistant', content: text },
+      finish_reason: 'stop',
+    }],
+    usage: { prompt_tokens: 0, completion_tokens: 0, total_tokens: 0 },
+  };
+}
+
+const server = http.createServer((req, res) => {
+  if (req.method === 'GET' && req.url === '/v1/models') {
+    res.writeHead(200, { 'Content-Type': 'application/json' });
+    res.end(JSON.stringify({
+      object: 'list',
+      data: [{ id: MODEL_ID, object: 'model', owned_by: 'moonshot' }],
+    }));
+    return;
+  }
+
+  if (req.method === 'POST' && req.url === '/v1/chat/completions') {
+    let body = '';
+    req.on('data', d => { body += d; });
+    req.on('end', async () => {
+      let parsed;
+      try {
+        parsed = JSON.parse(body);
+      } catch {
+        res.writeHead(400, { 'Content-Type': 'application/json' });
+        res.end(JSON.stringify({ error: 'invalid JSON body' }));
+        return;
+      }
+
+      try {
+        const text = await handleTurn(parsed.messages || []);
+        // Non-streaming policy: always return the full body even if the
+        // caller sets stream:true. Cognee's batch cognify has no use for SSE,
+        // and a one-shot call has nothing to incrementally stream anyway.
+        res.writeHead(200, { 'Content-Type': 'application/json' });
+        res.end(JSON.stringify(completionBody(text)));
+      } catch (err) {
+        res.writeHead(500, { 'Content-Type': 'application/json' });
+        res.end(JSON.stringify({ error: String(err.message || err) }));
+      }
+    });
+    return;
+  }
+
+  res.writeHead(404, { 'Content-Type': 'application/json' });
+  res.end(JSON.stringify({ error: 'not found' }));
+});
+
+server.listen(PORT, () => console.log(`hindsight-llm wrapper listening on :${PORT}`));

openai/shared-mcp.json

@@ -11,6 +11,10 @@
     "kanboard": {
       "type": "http",
       "url": "http://host.docker.internal:3104/mcp"
+    },
+    "agap": {
+      "type": "http",
+      "url": "http://host.docker.internal:3100/mcp"
     }
   }
 }