feat(deploy): add portable external-service stack

deploy/env.example

@@ -0,0 +1,28 @@
+# Copy this file to deploy/.env. Never commit deploy/.env or real credentials.
+# Compose passes these values to the core container at runtime; images contain no secrets.
+
+# Optional application defaults
+PI_PROVIDER=
+PI_MODEL=
+PI_THINKING=
+MAX_PI_PROCESSES=4
+AUTH_MODE=none
+
+# External DWH (example workspace uses the HTTP adapters)
+THT_DB_NAME=
+THT_DWH_REST_URL=
+THT_DWH_API_KEY=
+
+# External vector service. Use a distinct write key where the service supports one.
+THT_VEC_REST_URL=
+THT_VEC_API_KEY=
+THT_VEC_WRITE_API_KEY=
+
+# External embeddings service
+THT_OLLAMA_URL=
+
+# Evidence source visible inside the persistent data volume
+THT_DOCS_ROOT=/data/workspaces/example/evidence-source
+
+# Optional CA file mounted separately by an operator, for example via a Compose override.
+THT_SSL_CA=

deploy/workspaces/example.yaml

@@ -0,0 +1,69 @@
+language: en
+
+dwh:
+  type: thoth_rest
+  database:
+    database: ${THT_DB_NAME}
+    schema: datawarehouse
+  endpoint:
+    base_url: ${THT_DWH_REST_URL}
+    api_key: ${THT_DWH_API_KEY}
+    ssl_ca: ${THT_SSL_CA}
+
+# Relative logical roots are resolved beneath /data/workspaces/example.
+roots:
+  artifacts: artifacts
+  indexes: indexes
+  sessions: sessions
+
+examples:
+  max_per_column: 10
+
+lsh:
+  signature_size: 64
+  n_gram: 3
+  threshold: 0.5
+  max_values_per_column: 1000
+
+eligibility:
+  max_declared_len: 128
+  max_avg_length: 40
+  max_sampled_len: 200
+  ignore_columns: [etl_last_update]
+
+evidence:
+  source_root: ${THT_DOCS_ROOT}
+  evidence_dir: evidence
+
+embeddings:
+  base_url: ${THT_OLLAMA_URL}
+  model: nomic-embed-text-v2-moe
+  dim: 768
+  batch_size: 32
+
+vectors:
+  type: thoth_vector_http
+  reader:
+    base_url: ${THT_VEC_REST_URL}
+    api_key: ${THT_VEC_API_KEY}
+    ssl_ca: ${THT_SSL_CA}
+  writer:
+    base_url: ${THT_VEC_REST_URL}
+    api_key: ${THT_VEC_WRITE_API_KEY}
+    ssl_ca: ${THT_SSL_CA}
+
+vector:
+  max_chunk_chars: 4000
+
+search:
+  rrf_k: 60
+  top_schema_tables: 12
+  schema_chunk_pool: 150
+
+execution:
+  allow: [cte_test, explain, preview, aggregate, export]
+  max_preview_rows: 10
+  max_export_rows: 100000
+  statement_timeout_ms: 30000
+  warn_execution_ms: 5000
+  max_aggregate_cells: 20