gitea-admin/obsidian-wiki
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(mcp): add verified ingest job phases

Browse Source 
Expose authoritative ingest phases and supervisor-backed process liveness without semantic activity inference. Require deterministic registry, manifest, archive, file-index, and declared-output verification before an agent-successful job can finish succeeded.\n\nPreserve legacy state values, derive defaults for older job records, keep verification outside the manager lock, and retain partial outputs on verification failure.\n\nValidated with the full unittest suite (205 tests).
This commit is contained in:
Codex
2026-07-16 14:26:58 +00:00
parent a2b4bc393b
commit 2183404966
8 changed files with 888 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+5 -1
View File
@@ -497,7 +497,11 @@ The endpoint accepts optional `body_text`, `body_title`, `bundle_id`, `source_ty
Run `check_ingest_opencode_readiness` before the first remote upload. Use `run_smoke_test: true` when you want OpenCode itself to prove it can load the project `wiki-ingest` skill; otherwise the static preflight is also run automatically before every `start_ingest_job`.
Uploads and text notes land under `.runtime/mcp-ingest/uploads/`, outside the Obsidian vault, and are treated only as temporary source staging. Job state and logs live under `.runtime/mcp-ingest/jobs/`. Remote upload and job responses expose upload/job ids, hashes, states, and bounded result text, but omit local runtime file paths; the internal job record still keeps paths so the fixed local OpenCode prompt can ingest only the uploaded files. Completion is accepted only from the final JSON text event containing `MCP_INGEST_OK`; `MCP_INGEST_FAILED`, a missing marker, a nonzero exit, timeout, or cancellation marks the job failed/cancelled. `get_mcp_capabilities` includes `server_version`, `schema_version`/`capabilities_schema_version`, `tools_version`, file-index freshness, ingest queue state, and known limitations so remote agents can detect stale client instructions. Its `recommended_first_steps` only names currently enabled tool groups. The MCP server refuses to enable ingest if `OBSIDIAN_MCP_INGEST_RUNTIME_ROOT` points inside the vault; let `wiki-ingest` decide how to archive sources into `_sources/archive/`, update registries, and rebuild the file index.
Uploads and text notes land under `.runtime/mcp-ingest/uploads/`, outside the Obsidian vault, and are treated only as temporary source staging. Job state and logs live under `.runtime/mcp-ingest/jobs/`. Remote upload and job responses expose upload/job ids, hashes, states, and bounded result text, but omit local runtime file paths; the internal job record still keeps paths so the fixed local OpenCode prompt can ingest only the uploaded files.
Ingest status has authoritative `phase` values: `queued`, `preflight`, `agent_running`, `verifying`, and `complete`. `phase_started_at` marks the current phase boundary, while `process_alive` is true only when the process supervisor still owns a live process in `agent_running`; the server does not infer vague activity from logs or elapsed time. The final JSON text event must contain `MCP_INGEST_OK` before verification begins. The server then strictly verifies each source against `_meta/source-registry.jsonl`, `.manifest.json`, `_meta/file-assets.sqlite`, the archive when `WIKI_ARCHIVE_SOURCES=true`, and every declared related/catalog/created/updated path. Only a passed verification produces `state=succeeded`; failed verification produces `state=failed` even when the agent reported success. Agent output and any partial vault writes are preserved for diagnosis and are not rolled back automatically. `MCP_INGEST_FAILED`, a missing marker, a nonzero exit, timeout, cancellation, readiness failure, or protocol failure skips verification and finishes with `verification.status=not_run`.
`get_mcp_capabilities` includes `server_version`, `schema_version`/`capabilities_schema_version`, `tools_version`, file-index freshness, ingest queue state, authoritative phase support, strict post-run verification, and known limitations so remote agents can detect stale client instructions. Its `recommended_first_steps` only names currently enabled tool groups. The MCP server refuses to enable ingest if `OBSIDIAN_MCP_INGEST_RUNTIME_ROOT` points inside the vault; let `wiki-ingest` decide how to archive sources into `_sources/archive/`, update registries, and rebuild the file index.
Ingest and query launch OpenCode with a fixed prompt and `--auto`, but the MCP service does not enforce a shell sandbox and prompt restrictions are not a security boundary. There is no direct arbitrary-prompt or arbitrary-shell MCP tool, yet a client able to influence vault/upload content must still be trusted. Keep these tool groups behind a trusted network boundary and rotate the token if it has been shared too broadly.