refactor(mcp)!: remove remaining order integration artifacts

Remove order compatibility fields, routing notices and migration references
from Wiki source, skills and documentation. Bump capability schema to v6
and validate the remaining Wiki query response contract.

Move retired runtime configuration, database and completed job archives to
the independent order project, uninstall legacy units and clear stale
bytecode. Keep Git history for provenance.

Validation: 173 Wiki tests pass; live independent order MCP authentication,
queries and write rejection pass after cleanup. No integration filenames,
config keys or source references remain in the Wiki working tree.

BREAKING CHANGE: query results and capability metadata no longer contain
legacy business-related fields. Wiki consumers must use the v6 schema.
This commit is contained in:
Codex
2026-10-31 10:25:32 +00:00
parent 2396bd2d3e
commit 1dd5d8d753
11 changed files with 13 additions and 57 deletions
+1 -7
View File
@@ -37,8 +37,6 @@ obsidian-wiki setup --project . # also drop project-local skills + AGENTS.md int
obsidian-wiki setup --copy # copy skill files instead of symlinking
```
Operational sales-order queries and Kingdee synchronization now live in the independent `kingdee-orders-mcp` project. See [the migration note](docs/business-facts.md).
When working from a cloned repo, `scripts/obsidian-wiki-ops.py` is the single repo-local operations entrypoint. It wraps common `obsidian-wiki` commands, daily update, and the managed MCP service:
```bash
@@ -322,10 +320,6 @@ obsidian-wiki file-index stage ./drawing.step --project bjd --doc-type drawing
Staging is for upload/intake only. The normal ingest flow should still classify the file, archive it under `_sources/archive/`, update source registry/catalog pages, and rebuild the file index.
### Independent order service
Sales-order MCP tools, Kingdee synchronization, credentials, and the order database have moved to `kingdee-orders-mcp`. Wiki has no runtime dependency on that project. See [migration and rollback details](docs/business-facts.md).
### Optional: Source File MCP Server
Agents that support MCP can ask for original engineering files through a local stdio server:
@@ -474,7 +468,7 @@ This adds read-oriented OpenCode-backed query tools to the same `wiki-file-asset
The managed service config sets query to `OBSIDIAN_MCP_QUERY_OPENCODE_MODEL=openai/gpt-6.1-sol`, `OBSIDIAN_MCP_QUERY_OPENCODE_VARIANT=low`, and `OBSIDIAN_MCP_QUERY_JOB_TIMEOUT_SECONDS=300` by default, prioritizing response speed over maximum reasoning depth. Tune the server env file if a different balance is needed. GPT-6.1 Sol balances multi-step document/tool work and cost; query uses `low` for latency while ingest uses `high` for synthesis and metadata maintenance. GPT-5.5 retired from Codex with ChatGPT sign-in on October 14, 2026 ([model availability](https://learn.chatgpt.com/docs/models)). Existing installations must update their saved env file and restart the service; changing these defaults does not overwrite saved settings.
`public_only` defaults to `false`, so the answer may use the same full vault visibility that a local operator sees. Set `public_only=true` when the remote answer must exclude `visibility/internal` and `visibility/pii` pages. Job state and logs live under `.runtime/mcp-query/jobs/`, outside the vault; remote query status/result responses expose bounded, path-redacted text and omit local log paths. The final JSON text event must contain `MCP_QUERY_OK`; `MCP_QUERY_FAILED`, a missing marker, a nonzero exit, timeout, or cancellation cannot be reported as a successful answer. Query results keep the legacy `answer` field and also include `answer_markdown`, `citations`, `used_wiki`, `used_business_facts`, `data_freshness`, `warnings`, and `confidence` so agents can parse the response without scraping raw logs. A normal `wiki-query` log entry is allowed. The generated prompt instructs the agent to avoid ingest/update/rebuild workflows, writes, sync/config/timer operations, and arbitrary shell execution. Operational order access belongs to the independent orders MCP; `used_business_facts` is retained for response compatibility and is always `false`.
`public_only` defaults to `false`, so the answer may use the same full vault visibility that a local operator sees. Set `public_only=true` when the remote answer must exclude `visibility/internal` and `visibility/pii` pages. Job state and logs live under `.runtime/mcp-query/jobs/`, outside the vault; remote query status/result responses expose bounded, path-redacted text and omit local log paths. The final JSON text event must contain `MCP_QUERY_OK`; `MCP_QUERY_FAILED`, a missing marker, a nonzero exit, timeout, or cancellation cannot be reported as a successful answer. Query results keep the legacy `answer` field and also include `answer_markdown`, `citations`, `used_wiki`, `data_freshness`, `warnings`, and `confidence` so agents can parse the response without scraping raw logs. A normal `wiki-query` log entry is allowed. The generated prompt instructs the agent to avoid ingest/update/rebuild workflows, writes, sync/config/timer operations, and arbitrary shell execution.
Clean old MCP runtime staging data with the default 30-day retention window: