fix(mcp): migrate OpenCode defaults to GPT-6.1 Sol
setup / install-leaves-tree-clean (push) Canceled after 0s
setup / install-leaves-tree-clean (push) Canceled after 0s
Replace retired ChatGPT Codex GPT-5.5 defaults with GPT-6.1 Sol. Use low reasoning for queries and retain high reasoning for ingestion. Update config examples, operator guidance, and service default assertions. Validation: 168 MCP tests passed; live OAuth model invocation returned MODEL_OK; restarted service reports the new model and variants.
This commit is contained in:
@@ -473,7 +473,7 @@ This adds write-capable MCP tools to the same `wiki-file-assets` server and bear
|
||||
- `start_ingest_job` — queues a local `opencode run --auto --format json` job with a fixed `/wiki-ingest` prompt for the completed uploads.
|
||||
- `get_ingest_job_status`, `get_ingest_job_result`, `cancel_ingest_job` — inspect or cancel the local job.
|
||||
|
||||
The managed service config sets the OpenCode model server-side. By default ingest uses `OBSIDIAN_MCP_INGEST_OPENCODE_MODEL=openai/gpt-5.5`, `OBSIDIAN_MCP_INGEST_OPENCODE_VARIANT=high`, and an `OBSIDIAN_MCP_INGEST_JOB_TIMEOUT_SECONDS=1800` deadline. It also writes `OBSIDIAN_MCP_PUBLIC_BASE_URL` from the detected remote address so ticket responses can include a complete upload URL; set it manually when the service is behind a tunnel, reverse proxy, or custom DNS name. If the upload endpoint is exposed through a different public URL than `/mcp`, set `OBSIDIAN_MCP_INGEST_PUBLIC_UPLOAD_URL` explicitly and it will override the derived upload URL in capabilities, upload instructions, tickets, and `show-config`. Change these values in `.runtime/obsidian-wiki-mcp.env` on the server if needed; remote MCP clients do not choose the model per call.
|
||||
The managed service config sets the OpenCode model server-side. By default ingest uses `OBSIDIAN_MCP_INGEST_OPENCODE_MODEL=openai/gpt-6.1-sol`, `OBSIDIAN_MCP_INGEST_OPENCODE_VARIANT=high`, and an `OBSIDIAN_MCP_INGEST_JOB_TIMEOUT_SECONDS=1800` deadline. It also writes `OBSIDIAN_MCP_PUBLIC_BASE_URL` from the detected remote address so ticket responses can include a complete upload URL; set it manually when the service is behind a tunnel, reverse proxy, or custom DNS name. If the upload endpoint is exposed through a different public URL than `/mcp`, set `OBSIDIAN_MCP_INGEST_PUBLIC_UPLOAD_URL` explicitly and it will override the derived upload URL in capabilities, upload instructions, tickets, and `show-config`. Change these values in `.runtime/obsidian-wiki-mcp.env` on the server if needed; remote MCP clients do not choose the model per call.
|
||||
|
||||
For short text thoughts, notes, findings, or pasted context, call `ingest_text_note(text, title?, project?, doc_type_hint?, note?, start_job?)`. It uses `doc_type_hint="thought"` and `start_job=false` by default, returning a one-item Bundle and the staged upload; it also returns the queued job when `start_job=true` is explicitly requested.
|
||||
|
||||
@@ -520,7 +520,7 @@ This adds read-oriented OpenCode-backed query tools to the same `wiki-file-asset
|
||||
- `start_wiki_query` — queues a local `opencode run --auto --format json` job with a fixed `/wiki-query` prompt. Parameters: `query`, `mode` (`normal` or `index_only`), `public_only` (default `false`), and optional `note`.
|
||||
- `get_wiki_query_status`, `get_wiki_query_result`, `cancel_wiki_query` — inspect, retrieve, or cancel the local query job.
|
||||
|
||||
The managed service config sets query to `OBSIDIAN_MCP_QUERY_OPENCODE_MODEL=openai/gpt-5.5`, `OBSIDIAN_MCP_QUERY_OPENCODE_VARIANT=minimal`, 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.
|
||||
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; it only permits the `obsidian-wiki business schema/template/sql` read-only commands needed by the wiki-query business facts route, but these prompt restrictions do not replace the trusted-client boundary described above. Hybrid business + wiki questions may run a wiki context track and a business facts track, using parallel subagents only when the host supports them and otherwise running sequentially. When `public_only=true`, business facts remain disabled.
|
||||
|
||||
|
||||
Reference in New Issue
Block a user