alvis
b27d31b3ca
docker-compose.yml gains healthchecks and depends_on/condition chains for the litellm/langfuse/postgres tier so dependants wait for a genuinely ready service instead of a started container. Also plumbs AGAP_MCP_TOKEN into the adolf and adolf-llm containers, sourced from openai/.env (gitignored), for the kb#180 bearer auth on the agap MCP server; shared-mcp.json consumes it via bearerTokenEnvVar so the Kimi backbone authenticates too. agent-registry.yaml / agent_registry.py: the version-controlled source of truth for agent identities and trust classes -- the same ids the agap-mcp token map resolves to (`adolf`, `claude-coder`; note `claude-code-cli` is the runtime entry, not an agent identity). model-registry.yaml, litellm-config.yaml, auto-router-routes.json and provision_litellm_keys.py: model tiering, virtual-key provisioning and auto-router routes. tei-reranker/ is the local reranker service backing Hindsight recall. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
555 lines
26 KiB
YAML
555 lines
26 KiB
YAML
services:
|
|
litellm-db:
|
|
image: postgres:16-alpine
|
|
container_name: litellm-db
|
|
environment:
|
|
- POSTGRES_DB=litellm
|
|
- POSTGRES_USER=litellm
|
|
- POSTGRES_PASSWORD=litellm
|
|
volumes:
|
|
- /mnt/ssd/dbs/litellm/postgres:/var/lib/postgresql/data
|
|
restart: always
|
|
# kb#190: cheap connectivity probe, no query load.
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "pg_isready -U litellm -d litellm"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 5
|
|
start_period: 10s
|
|
|
|
litellm:
|
|
image: ghcr.io/berriai/litellm:main-latest
|
|
container_name: litellm
|
|
ports:
|
|
- "4000:4000"
|
|
volumes:
|
|
- ./litellm-config.yaml:/app/config.yaml
|
|
environment:
|
|
- DATABASE_URL=postgresql://litellm:litellm@litellm-db:5432/litellm
|
|
- LITELLM_MASTER_KEY=sk-fjQC1BxAiGFSMs
|
|
- LANGFUSE_PUBLIC_KEY=${LANGFUSE_PUBLIC_KEY:-changeme}
|
|
- LANGFUSE_SECRET_KEY=${LANGFUSE_SECRET_KEY:-changeme}
|
|
- LANGFUSE_HOST=http://langfuse:3000
|
|
- OPENROUTER_API_KEY=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
|
|
command: ["--config", "/app/config.yaml", "--port", "4000"]
|
|
extra_hosts:
|
|
- "host.docker.internal:host-gateway"
|
|
depends_on:
|
|
litellm-db:
|
|
condition: service_healthy
|
|
langfuse:
|
|
condition: service_healthy
|
|
restart: always
|
|
# kb#190: /health/liveliness is litellm's cheap liveness probe (no
|
|
# provider/model call), unlike /health which pings every configured model.
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "node -e \"fetch('http://localhost:4000/health/liveliness').then(r=>process.exit(r.ok?0:1)).catch(()=>process.exit(1))\""]
|
|
interval: 15s
|
|
timeout: 10s
|
|
retries: 5
|
|
start_period: 20s
|
|
|
|
kimi-agent:
|
|
build: ./kimi-agent
|
|
container_name: kimi-agent
|
|
volumes:
|
|
- /home/alvis/kimi-workspace:/workspace
|
|
- kimi-agent-home:/root/.kimi-code
|
|
restart: unless-stopped
|
|
|
|
langfuse-db:
|
|
image: postgres:16-alpine
|
|
container_name: langfuse-db
|
|
environment:
|
|
- POSTGRES_DB=langfuse
|
|
- POSTGRES_USER=langfuse
|
|
- POSTGRES_PASSWORD=langfuse
|
|
volumes:
|
|
- /mnt/ssd/dbs/langfuse/postgres:/var/lib/postgresql/data
|
|
restart: always
|
|
# kb#190: cheap connectivity probe, no query load.
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "pg_isready -U langfuse -d langfuse"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 5
|
|
start_period: 10s
|
|
|
|
langfuse:
|
|
image: ghcr.io/langfuse/langfuse:2
|
|
container_name: langfuse
|
|
ports:
|
|
- "3200:3000"
|
|
environment:
|
|
- DATABASE_URL=postgresql://langfuse:langfuse@langfuse-db:5432/langfuse
|
|
- NEXTAUTH_URL=https://lf.alogins.net
|
|
- NEXTAUTH_SECRET=532a746b24ac40afa39f9d317031cab94d4d6881107ea3b1209b28020f1a9761
|
|
- SALT=7927b3b0092afe4542274940b557becea6418a5fed79f7acd25c3a789349fdc9
|
|
- AUTH_DISABLE_SIGNUP=true
|
|
depends_on:
|
|
langfuse-db:
|
|
condition: service_healthy
|
|
restart: always
|
|
# kb#190: langfuse's Next.js server binds the container's bridge IP,
|
|
# NOT 127.0.0.1/localhost (confirmed via `ss -tlnp` inside the
|
|
# container: 127.0.0.1 connection is refused) -- so the probe must
|
|
# address it by its own compose DNS name, which resolves to that same
|
|
# bridge IP from inside the container.
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "wget -q -O- http://langfuse:3000/api/public/health || exit 1"]
|
|
interval: 15s
|
|
timeout: 10s
|
|
retries: 5
|
|
start_period: 30s
|
|
|
|
qdrant:
|
|
image: qdrant/qdrant
|
|
container_name: qdrant
|
|
ports:
|
|
- "6333:6333"
|
|
- "6334:6334"
|
|
restart: always
|
|
volumes:
|
|
- /mnt/ssd/dbs/qdrant:/qdrant/storage:z
|
|
|
|
# GPU residency decision (kb#191, 2026-07-26, DESIGN-a2a-agents.md sec 3b):
|
|
# the 8GB GTX 1070 only has ~1.7GB free with the never-evict set (bge-m3 +
|
|
# tei-reranker) resident alongside gemma3:4b -- no room for a 4th GPU
|
|
# tenant without risking evicting the reranker (silent Hindsight recall
|
|
# breakage). Runs CPU-only until the card gets more headroom. Never
|
|
# started yet -- kb#175 (Adolf STT) was parked waiting on this call.
|
|
faster-whisper:
|
|
image: fedirz/faster-whisper-server:latest-cuda
|
|
container_name: faster-whisper
|
|
ports:
|
|
- "8880:8000"
|
|
environment:
|
|
- WHISPER__MODEL=deepdml/faster-whisper-large-v3-turbo-ct2
|
|
- WHISPER__INFERENCE_DEVICE=cpu
|
|
- WHISPER__COMPUTE_TYPE=int8
|
|
- WHISPER__LANGUAGE=ru
|
|
volumes:
|
|
- /mnt/ssd/ai/faster-whisper:/root/.cache/huggingface
|
|
restart: always
|
|
|
|
silero-tts:
|
|
build: ./silero-tts
|
|
container_name: silero-tts
|
|
ports:
|
|
- "8881:8881"
|
|
volumes:
|
|
- /mnt/ssd/ai/silero-tts:/cache/torch
|
|
restart: always
|
|
|
|
pipecat:
|
|
build: ./pipecat
|
|
container_name: pipecat
|
|
ports:
|
|
- "8882:8882"
|
|
environment:
|
|
- LIVEKIT_URL=ws://host.docker.internal:7880
|
|
- LIVEKIT_PUBLIC_URL=wss://lk.alogins.net
|
|
- LIVEKIT_API_KEY=devkey
|
|
- LIVEKIT_SECRET=ef3ef4b903ca8469b09b2dd7ab6af529c4d2f3c95668f53832fc351cf67777a9
|
|
- ADOLF_URL=http://host.docker.internal:8000/v1
|
|
- STT_URL=http://host.docker.internal:8880/v1
|
|
- TTS_URL=http://host.docker.internal:8881/v1
|
|
- STT_MODEL=deepdml/faster-whisper-large-v3-turbo-ct2
|
|
- TTS_VOICE=onyx
|
|
extra_hosts:
|
|
- "host.docker.internal:host-gateway"
|
|
restart: unless-stopped
|
|
|
|
# Adolf — OpenClaw fork (Matrix-first personal assistant). The OpenClaw
|
|
# gateway config (Matrix channel + allow-list, model provider ->
|
|
# adolf-llm:8010, MCP registry, gateway.tools.allow for cron/nodes) is
|
|
# version-controlled at agap_git/adolf/openclaw.json (repo root, alongside
|
|
# this openai/ project, not nested inside it) and bind-mounted read-only
|
|
# over the adolf-state volume (see volumes below), so git is the single
|
|
# source of truth — not a hand-edited volume file. The volume still
|
|
# holds runtime state only (Matrix crypto/devices, credentials, sessions,
|
|
# workspace/SOUL.md, logs). Matrix creds and ADOLF_KEY come from
|
|
# openai/.env (gitignored, never committed). Source tree: /home/alvis/adolf.
|
|
# To change config: edit ../adolf/openclaw.json + restart adolf.
|
|
adolf:
|
|
build:
|
|
context: ../../adolf
|
|
# Matrix is opt-in at build time (see adolf/Dockerfile); without this,
|
|
# the gateway logs "no-channel-owner" and channels.matrix is inert.
|
|
args:
|
|
OPENCLAW_EXTENSIONS: matrix
|
|
image: adolf:local
|
|
container_name: adolf
|
|
environment:
|
|
- HOME=/home/node
|
|
- OPENCLAW_HOME=/home/node
|
|
- OPENCLAW_STATE_DIR=/home/node/.openclaw
|
|
- OPENCLAW_CONFIG_PATH=/home/node/.openclaw/openclaw.json
|
|
- OPENCLAW_CONFIG_DIR=/home/node/.openclaw
|
|
- OPENCLAW_WORKSPACE_DIR=/home/node/.openclaw/workspace
|
|
- OPENCLAW_GATEWAY_TOKEN=${ADOLF_GATEWAY_TOKEN:-}
|
|
- ADOLF_KEY=${ADOLF_KEY:-}
|
|
- MATRIX_HOMESERVER=${MATRIX_HOMESERVER:-}
|
|
- MATRIX_USER_ID=${MATRIX_USER_ID:-}
|
|
# kb#67: stable token + device_id pin, so restarts reuse the existing
|
|
# Matrix device (matrix-sdk/OpenClaw's own credential cache in the
|
|
# adolf-state volume already does this across restarts -- see
|
|
# extensions/matrix/src/matrix/client/config.ts resolveMatrixAuth --
|
|
# but that cache lives in the volume, so a lost/rebuilt volume would
|
|
# fall through to MATRIX_PASSWORD and mint a brand-new device with no
|
|
# cross-signing. Setting the token here removes that dependency).
|
|
# MATRIX_PASSWORD stays configured as a manual-recovery fallback only:
|
|
# it is never used while MATRIX_ACCESS_TOKEN resolves to a valid token.
|
|
- MATRIX_ACCESS_TOKEN=${MATRIX_ACCESS_TOKEN:-}
|
|
- MATRIX_DEVICE_ID=${MATRIX_DEVICE_ID:-}
|
|
- MATRIX_PASSWORD=${MATRIX_PASSWORD:-}
|
|
- MATRIX_DEVICE_NAME=${MATRIX_DEVICE_NAME:-Adolf OpenClaw Gateway}
|
|
# marketplace-mcp bearer token (kb task #61) -- referenced by
|
|
# openclaw.json's mcp.servers.marketplace.headers.Authorization via
|
|
# ${MARKETPLACE_MCP_TOKEN} substitution; never inlined into that file.
|
|
- MARKETPLACE_MCP_TOKEN=${MARKETPLACE_MCP_TOKEN:-}
|
|
# agap-mcp bearer token (kb#180) -- agap-mcp's :3100 listener requires
|
|
# `Authorization: Bearer <token>` on every route now (DESIGN §4: no
|
|
# unauthenticated JSON-RPC listener; :3100 is host-networked and the
|
|
# LAN carries VPN-terminated peers). Referenced by openclaw.json's
|
|
# mcp.servers.agap.headers.Authorization via ${AGAP_MCP_TOKEN}
|
|
# substitution, and read directly by the todoist-capture plugin's
|
|
# /capture-idea POST. The token must map to agent id `adolf` in
|
|
# agap-mcp's AGAP_MCP_AGENT_TOKENS. Sourced from openai/.env
|
|
# (gitignored); never inlined here.
|
|
- AGAP_MCP_TOKEN=${AGAP_MCP_TOKEN:-}
|
|
- TZ=Europe/Riga
|
|
volumes:
|
|
# Runtime state only (Matrix crypto/devices, credentials, sessions,
|
|
# workspace, logs). The gateway config file itself is overlaid below.
|
|
- adolf-state:/home/node/.openclaw
|
|
# Version-controlled OpenClaw gateway config, mounted read-only on top
|
|
# of the state volume so it is the single source of truth. The gateway
|
|
# reads this JSONC file and snapshots its own .last-good/.rejected
|
|
# copies into the volume dir (writable) — it never rewrites this file,
|
|
# so read-only is safe. Edit the tracked file + restart to change config;
|
|
# runtime/UI edits are intentionally disabled by the ro mount.
|
|
- ../adolf/openclaw.json:/home/node/.openclaw/openclaw.json:ro
|
|
# quota-command plugin (kb #62) — same read-only-bind-over-volume
|
|
# pattern as openclaw.json above, applied to a single external plugin
|
|
# dir instead of the whole state tree. Previously the only precedent
|
|
# (cognee-memory) was docker cp'd straight into the adolf-state volume
|
|
# at runtime with no git backing; this plugin is small enough (no
|
|
# node_modules — only Node built-ins/global fetch) to just bind-mount
|
|
# its tracked source directly at its extensions/<id> path, so git stays
|
|
# the single source of truth the same way it already is for
|
|
# openclaw.json. Activated via plugins.entries.quota-command in that file.
|
|
- ./quota-command-openclaw-plugin:/home/node/.openclaw/extensions/quota-command:ro
|
|
# hindsight-memory plugin (kb #75, H3) — same read-only-bind-over-volume
|
|
# pattern as quota-command above. Structural successor to cognee-memory
|
|
# (still docker cp'd into the adolf-state volume, no git backing; that
|
|
# plugin's activation/container is decommissioned in H4, not here).
|
|
# Forced hooks (before_prompt_build recall / agent_end retain) against
|
|
# the hindsight service (see that service's block below), replacing
|
|
# Cognee as Adolf's memory backend. Activated via
|
|
# plugins.entries.hindsight-memory in openclaw.json.
|
|
- ./hindsight-openclaw-plugin:/home/node/.openclaw/extensions/hindsight-memory:ro
|
|
# kimi-quota-footer plugin (kb #85) — same read-only-bind-over-volume
|
|
# pattern as quota-command/hindsight-memory above. Appends the Kimi
|
|
# usage line to every outgoing reply via reply_payload_sending, reusing
|
|
# quota-command's adolf-llm:8010/usage route. Activated via
|
|
# plugins.entries.kimi-quota-footer in openclaw.json.
|
|
- ./kimi-quota-footer-plugin:/home/node/.openclaw/extensions/kimi-quota-footer:ro
|
|
# todoist-capture plugin (kb#170 component 1) — same read-only-bind-
|
|
# over-volume pattern as quota-command/hindsight-memory/kimi-quota-
|
|
# footer above. Registers /idea (native command, zero Kimi calls);
|
|
# POSTs to agap-mcp's /capture-idea (see agap-mcp/src/server.js +
|
|
# capture.js) which does the actual bge-m3 classify + Todoist create.
|
|
# Activated via plugins.entries.todoist-capture in openclaw.json.
|
|
- ./todoist-capture-plugin:/home/node/.openclaw/extensions/todoist-capture:ro
|
|
extra_hosts:
|
|
- "host.docker.internal:host-gateway"
|
|
# mtx.alogins.net's public A record can't hairpin-NAT back through the
|
|
# router from inside a container; route it to the host gateway instead,
|
|
# matching matrix/docker-compose.yml's lk-jwt-service (same problem,
|
|
# same fix). Caddy on the host terminates TLS on :443 and proxies to
|
|
# synapse:8008.
|
|
- "mtx.alogins.net:host-gateway"
|
|
# Local *.alogins.net web services (family wiki / OtterWiki, РодоВики) —
|
|
# same hairpin-NAT dodge: the public A record can't loop back through the
|
|
# router from inside a container, so route the hostname to the host
|
|
# gateway where Caddy terminates TLS on :443 and proxies to the service.
|
|
# Lets Adolf's OpenClaw browser reach them with the real URL + the
|
|
# Vaultwarden creds. Add more *.alogins.net hosts here as needed.
|
|
- "family.alogins.net:host-gateway"
|
|
- "wiki.alogins.net:host-gateway"
|
|
cap_drop:
|
|
- NET_RAW
|
|
- NET_ADMIN
|
|
security_opt:
|
|
- no-new-privileges:true
|
|
init: true
|
|
ports:
|
|
- "18789:18789"
|
|
- "18790:18790"
|
|
command:
|
|
["node", "dist/index.js", "gateway", "--bind", "lan", "--port", "18789"]
|
|
restart: unless-stopped
|
|
|
|
# hindsight-llm — standalone clone of cognee-llm (kb#76, H4 option B): the
|
|
# dedicated Kimi-CLI wrapper that is now Hindsight's LLM, so the whole cognee
|
|
# stack (incl. cognee-llm) can be decommissioned. Own port (:8012) + own
|
|
# kimi-code volume; needs a one-time `kimi login` seeded into hindsight-llm-home.
|
|
hindsight-llm:
|
|
build: ./hindsight-llm
|
|
container_name: hindsight-llm
|
|
ports:
|
|
- "8012:8012"
|
|
volumes:
|
|
- hindsight-llm-home:/root/.kimi-code
|
|
restart: unless-stopped
|
|
# kb#190: GET /v1/models is a static, no-inference route (see
|
|
# hindsight-llm/server.js) -- cheap liveness probe.
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "node -e \"fetch('http://localhost:8012/v1/models').then(r=>process.exit(r.ok?0:1)).catch(()=>process.exit(1))\""]
|
|
interval: 15s
|
|
timeout: 10s
|
|
retries: 5
|
|
start_period: 20s
|
|
|
|
# tei-reranker — GPU cross-encoder rerank sidecar for Hindsight (kb#87).
|
|
# Hindsight's recall reranker ran the multilingual jina-reranker-v2 on the
|
|
# image's CPU-only torch; over the grown adolf bank (269 facts, ~81 rerank
|
|
# candidates) a single recall pinned ~8 cores for ~183s, so the memory
|
|
# plugin's 4s timeout skipped injection every time. The stock HF TEI GPU
|
|
# image needs CUDA sm_75+; this box is a GTX 1070 (Pascal sm_61), so we serve
|
|
# the SAME jina model via plain CUDA torch (Pascal-compatible) behind the
|
|
# TEI-compatible /info + /rerank API that Hindsight's `tei` provider speaks.
|
|
# Shares the GPU with ollama (~1GB fp16 here, ~5.6GB ollama peak, 8GB card).
|
|
# Reuses the already-downloaded model from hindsight's HF cache (no re-DL).
|
|
tei-reranker:
|
|
build: ./tei-reranker
|
|
container_name: tei-reranker
|
|
runtime: nvidia
|
|
environment:
|
|
- NVIDIA_VISIBLE_DEVICES=all
|
|
- NVIDIA_DRIVER_CAPABILITIES=compute,utility
|
|
- RERANKER_MODEL=jinaai/jina-reranker-v2-base-multilingual
|
|
- RERANKER_DEVICE=cuda
|
|
- HF_HOME=/root/.cache/huggingface
|
|
volumes:
|
|
- /mnt/ssd/dbs/hindsight-cache/huggingface:/root/.cache/huggingface
|
|
ports:
|
|
- "8014:80"
|
|
restart: unless-stopped
|
|
# kb#190: /info is TEI's own lightweight metadata endpoint (model name,
|
|
# no rerank/inference call). Container has python3 only (no curl/wget).
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "python3 -c \"import urllib.request,sys; sys.exit(0 if urllib.request.urlopen('http://localhost:80/info',timeout=3).status==200 else 1)\""]
|
|
interval: 15s
|
|
timeout: 10s
|
|
retries: 5
|
|
start_period: 30s
|
|
|
|
# adolf-llm — conversational Kimi-CLI wrapper (:8010), the model backend for
|
|
# the Adolf OpenClaw gateway (P2). Real streaming (SSE), chat_id session-keying
|
|
# + 1:1 kimi resume, media, per-session .mcp.json sourced from the shared
|
|
# shared-mcp.json contract (cognee-mcp P4, openclaw-tools P5). Needs
|
|
# `kimi login` in adolf-llm-home.
|
|
adolf-llm:
|
|
build: ./adolf-llm
|
|
container_name: adolf-llm
|
|
environment:
|
|
# marketplace-mcp bearer token (kb#61) -- shared-mcp.json's
|
|
# "marketplace" entry references this by name via
|
|
# `bearerTokenEnvVar: "MARKETPLACE_MCP_TOKEN"` (Kimi CLI's own field
|
|
# for a static bearer token sourced from the environment, confirmed by
|
|
# decompiling @moonshot-ai/kimi-code's dist/main.mjs help text). Kimi
|
|
# reads process.env at request time, so the raw secret never sits in
|
|
# the git-tracked shared-mcp.json -- same secret, same env-var pattern
|
|
# already used for the `adolf` service's openclaw.json Layer-1 config
|
|
# above (${MARKETPLACE_MCP_TOKEN} substitution), sourced from
|
|
# openai/.env (gitignored, never committed).
|
|
- MARKETPLACE_MCP_TOKEN=${MARKETPLACE_MCP_TOKEN:-}
|
|
# agap-mcp bearer token (kb#180) -- same env-var pattern, referenced by
|
|
# shared-mcp.json's "agap" entry via `bearerTokenEnvVar:
|
|
# "AGAP_MCP_TOKEN"`. Without it the Kimi backbone's agap tools all
|
|
# fail with HTTP 401 once agap-mcp restarts with auth on.
|
|
- AGAP_MCP_TOKEN=${AGAP_MCP_TOKEN:-}
|
|
ports:
|
|
- "8010:8010"
|
|
volumes:
|
|
- adolf-llm-workspace:/workspace
|
|
- adolf-llm-home:/root/.kimi-code
|
|
- ./shared-mcp.json:/shared-mcp.json:ro
|
|
extra_hosts:
|
|
# Needed to reach kanboard-mcp-adolf (:3104, network_mode: host, outside
|
|
# this compose project's network) via shared-mcp.json's "kanboard"
|
|
# entry — same host-gateway trick used by adolf/cognee/pipecat above.
|
|
- "host.docker.internal:host-gateway"
|
|
# Local *.alogins.net web services: the Kimi CLI's own web-fetch tool
|
|
# runs IN THIS container, so it needs the same hairpin-NAT dodge as the
|
|
# adolf gateway (the public A record can't loop back through the router).
|
|
# Route to the host gateway where Caddy terminates TLS on :443.
|
|
- "family.alogins.net:host-gateway"
|
|
- "wiki.alogins.net:host-gateway"
|
|
restart: unless-stopped
|
|
# kb#190: GET /v1/models is a static, no-inference route (see
|
|
# adolf-llm/server.js) -- cheap liveness probe, no Kimi call/quota use.
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "node -e \"fetch('http://localhost:8010/v1/models').then(r=>process.exit(r.ok?0:1)).catch(()=>process.exit(1))\""]
|
|
interval: 15s
|
|
timeout: 10s
|
|
retries: 5
|
|
start_period: 20s
|
|
|
|
# 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}/),
|
|
# UI :9999, built-in Postgres (pg0) bind-mounted to
|
|
# /mnt/ssd/dbs/hindsight/ (host dir created + chowned 1000:1000 to match
|
|
# the image's non-root `hindsight` user, confirmed via
|
|
# `docker run --entrypoint id`).
|
|
#
|
|
# LLM + embeddings reconfigured 2026-07-15 (kb#84) to fix two wrong H1
|
|
# choices for a Russian/multilingual use case:
|
|
#
|
|
# 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
|
|
# H1 choice of LiteLLM + ollama/gemma3:4b (a tiny local model): validated
|
|
# 2026-07-15 that cognee-llm returns clean, JSON-parseable structured
|
|
# extraction for Russian input (see kb#84 probe B) — gemma3:4b's fluency
|
|
# on Russian was never actually verified, it was picked only to dodge
|
|
# qwen3:8b's <think>-token empty-content bug. Kimi is also the flat-rate
|
|
# subscription already paid for, so this isn't a new cost.
|
|
#
|
|
# Embeddings -> ollama's bge-m3 on the GPU (host.docker.internal:11436,
|
|
# separate compose project, same extra_hosts trick as cognee/adolf-llm
|
|
# below), via ollama's OpenAI-compatible /v1/embeddings endpoint
|
|
# (confirmed 200 + 1024-dim vector 2026-07-15, kb#84 probe A). Replaces
|
|
# the H1 choice of Hindsight's built-in `local` provider
|
|
# (BAAI/bge-small-en-v1.5, English-only, 384-d, CPU-bound in-process
|
|
# SentenceTransformers). The hindsight image itself is CPU-only (torch
|
|
# +cpu build, no onnxruntime GPU provider — confirmed 2026-07-15), so its
|
|
# in-process local/onnx embedders can never reach the GPU; routing
|
|
# through ollama's `openai` embeddings provider (HTTP, not the bespoke
|
|
# cognee-style `ollama` provider Hindsight doesn't have) is how GPU
|
|
# serving happens here. Dimensions var matches cognee.env's own bge-m3
|
|
# swap (kb#60): 1024.
|
|
#
|
|
# Runs ALONGSIDE cognee/cognee-mcp/cognee-llm during the migration; those
|
|
# are untouched here and only decommissioned in H4, after H2/H3/H5 prove
|
|
# this service out. Not yet wired into openclaw.json/shared-mcp.json
|
|
# (that's H2, kb#74) — this block only stands the service up and proves
|
|
# retain/recall against a throwaway bank.
|
|
hindsight:
|
|
image: ghcr.io/vectorize-io/hindsight:latest
|
|
container_name: hindsight
|
|
restart: unless-stopped
|
|
environment:
|
|
# ALL stages on the local model (alvis, 2026-07-26): retain/extraction
|
|
# moved OFF Kimi (hindsight-llm:8012) onto ollama/gemma3:4b via LiteLLM,
|
|
# joining consolidation + reflect which were already local. Kimi is no
|
|
# longer in the Hindsight path at all, so the memory backend costs zero
|
|
# quota and Adolf's 5h window is left entirely for conversation.
|
|
#
|
|
# ⚠️ Accepted tradeoff: the kb#88/kb#84 rationale for keeping retain on
|
|
# Kimi was fact QUALITY — gemma3:4b's Russian fluency was never verified
|
|
# (it was originally picked only to dodge qwen3:8b's <think>-token bug),
|
|
# and this bank's content is largely Russian. Watch extraction quality on
|
|
# the next retains; if facts degrade, this is the first thing to revert.
|
|
- HINDSIGHT_API_LLM_PROVIDER=openai
|
|
- HINDSIGHT_API_LLM_BASE_URL=http://litellm:4000/v1
|
|
- HINDSIGHT_API_LLM_MODEL=ollama/gemma3:4b
|
|
- HINDSIGHT_API_LLM_API_KEY=sk-fjQC1BxAiGFSMs
|
|
- HINDSIGHT_API_CONSOLIDATION_LLM_PROVIDER=openai
|
|
- HINDSIGHT_API_CONSOLIDATION_LLM_BASE_URL=http://litellm:4000/v1
|
|
- HINDSIGHT_API_CONSOLIDATION_LLM_MODEL=ollama/gemma3:4b
|
|
- HINDSIGHT_API_CONSOLIDATION_LLM_API_KEY=sk-fjQC1BxAiGFSMs
|
|
- HINDSIGHT_API_REFLECT_LLM_PROVIDER=openai
|
|
- HINDSIGHT_API_REFLECT_LLM_BASE_URL=http://litellm:4000/v1
|
|
- HINDSIGHT_API_REFLECT_LLM_MODEL=ollama/gemma3:4b
|
|
- HINDSIGHT_API_REFLECT_LLM_API_KEY=sk-fjQC1BxAiGFSMs
|
|
- HINDSIGHT_API_EMBEDDINGS_PROVIDER=openai
|
|
- HINDSIGHT_API_EMBEDDINGS_OPENAI_BASE_URL=http://host.docker.internal:11436/v1
|
|
- HINDSIGHT_API_EMBEDDINGS_OPENAI_MODEL=bge-m3
|
|
- HINDSIGHT_API_EMBEDDINGS_OPENAI_DIMENSIONS=1024
|
|
# ollama doesn't check this value at all (no auth), but the openai
|
|
# embeddings client requires a non-empty key to construct.
|
|
- HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY=ollama
|
|
# Stable worker id (compose service name), not the container hostname
|
|
# default -- without this, recreating the container orphans any
|
|
# in-flight async retain/consolidation tasks under the old hostname
|
|
# (startup log warns about exactly this).
|
|
- HINDSIGHT_API_WORKER_ID=hindsight
|
|
# Reranker -> TEI GPU sidecar (kb#87). Was `local` = the same
|
|
# multilingual jina-reranker-v2, but on this image's CPU-only torch it
|
|
# pinned ~8 cores for ~183s over the grown adolf bank (269 facts / ~81
|
|
# rerank candidates), so the memory plugin's 4s recall timeout skipped
|
|
# injection every time. Now the identical jina model is served on the
|
|
# GPU by the tei-reranker sidecar behind the TEI /rerank API.
|
|
- HINDSIGHT_API_RERANKER_PROVIDER=tei
|
|
- HINDSIGHT_API_RERANKER_TEI_URL=http://tei-reranker:80
|
|
- HINDSIGHT_API_RERANKER_TEI_HTTP_TIMEOUT=60
|
|
volumes:
|
|
- /mnt/ssd/dbs/hindsight:/home/hindsight/.pg0
|
|
# Persist HuggingFace/sentence-transformers model cache so the jina
|
|
# reranker (~1GB) doesn't re-download on every container recreate.
|
|
- /mnt/ssd/dbs/hindsight-cache:/home/hindsight/.cache
|
|
ports:
|
|
- "8888:8888"
|
|
- "9999:9999"
|
|
extra_hosts:
|
|
# Needed to resolve host.docker.internal from inside the container
|
|
# for the ollama embeddings call above — ollama lives in a separate
|
|
# compose project, same trick as cognee/adolf-llm elsewhere in this
|
|
# file.
|
|
- "host.docker.internal:host-gateway"
|
|
depends_on:
|
|
# kb#217: litellm is now on the critical path for all three LLM stages
|
|
# (HINDSIGHT_API_*_LLM_BASE_URL above all point at litellm:4000) since
|
|
# the 2026-07-26 gemma3:4b re-route (59af13f); gate on its healthcheck
|
|
# (added by kb#190) so a cold boot doesn't race hindsight up before it.
|
|
litellm:
|
|
condition: service_healthy
|
|
# hindsight-llm dropped (kb#217): it was the Kimi-CLI wrapper that used
|
|
# to serve retain before the re-route above; nothing in this service's
|
|
# config points at hindsight-llm:8012 any more (grep confirms only
|
|
# model-registry.yaml still lists it, unrelated to this container's
|
|
# startup). The hindsight-llm service/volume are left in place — that's
|
|
# a separate decommission decision, not this task's scope.
|
|
tei-reranker:
|
|
condition: service_healthy
|
|
# kb#190: /health is hindsight's own liveness+DB-connectivity endpoint
|
|
# (returns {"status":"healthy","database":"connected"}), confirmed cheap
|
|
# (curl is present in this image).
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "curl -sf http://localhost:8888/health || exit 1"]
|
|
interval: 15s
|
|
timeout: 10s
|
|
retries: 5
|
|
start_period: 30s
|
|
|
|
# openclaw-tools — MCP bridge (P5) exposing a minimal slice of the Adolf
|
|
# OpenClaw gateway's agent tools (message/cron/nodes/browser) over MCP
|
|
# Streamable HTTP, so Kimi CLI sessions (adolf-llm) can call them instead of
|
|
# bypassing OpenClaw entirely. Proxies each MCP tool call to the gateway's
|
|
# `POST /tools/invoke` HTTP surface (http://adolf:18789). NOTE: `cron` and
|
|
# `nodes` are hard-denied on that surface by default until P6 adds them to
|
|
# `gateway.tools.allow` in the adolf openclaw.json — see openclaw-tools/
|
|
# server.js for the full gate writeup. Not useful until `adolf` (P6) is
|
|
# configured and running; safe to build/run standalone before that.
|
|
openclaw-tools:
|
|
build: ./openclaw-tools
|
|
container_name: openclaw-tools
|
|
environment:
|
|
- OPENCLAW_GATEWAY_URL=http://adolf:18789
|
|
- OPENCLAW_GATEWAY_TOKEN=${ADOLF_GATEWAY_TOKEN:-}
|
|
ports:
|
|
- "8020:8020"
|
|
restart: unless-stopped
|
|
|
|
volumes:
|
|
kimi-agent-home:
|
|
adolf-state:
|
|
hindsight-llm-home:
|
|
adolf-llm-workspace:
|
|
adolf-llm-home:
|