docs: clarify local file upload connector flow
CI / quality (push) Canceled after 0s

This commit is contained in:
vasily committed 2026-10-17 13:20:57 +08:00
1 parent c492124fe1
commit e7d9b13821
4 files changed
+18 -6

No files matched your search

+1 -1
View File
@@ -58,7 +58,7 @@ The [modularity protocol](../development/MODULARITY_PROTOCOL.md) applies to all
| `kb-curate` | Scoped audit -> inspect candidates -> propose corrections/relations -> receipts | Traceable changes or a report, preserving disagreements and old revisions. |
| `kb-synthesize` | Accepted inputs -> dependency inventory -> compare/compose -> evidence audit -> optional proposal | Labeled local synthesis draft, or accepted synthesis after a real receipt. |
The four skills are instruction artifacts, and the service has authenticated Streamable HTTP reads and contribution tools. The `gewu-connector` stdio program bridges explicitly selected local files to that service without exposing file bytes or credentials in model-visible tool responses. It is launched with one or more stable file IDs and paths, plus a service URL; the operator supplies `GEWU_TOKEN` through the host's protected environment rather than a command-line argument. The connector requires HTTPS for non-loopback services and stores resumable upload checkpoints in a private state file. The pack manifest is bound to generated wire schemas and now has a reversible workspace installer, but host MCP configuration, native client workflows and remote deployment remain unqualified. The authenticated `source_capture_url` MCP operation is enabled only when the operator configures the exact public-host allowlist in `GEWU_FETCH_ALLOWED_HOSTS`; URL and selected-file intake support UTF-8 text, Markdown, HTML visible-text extraction and PDF. Linux PDF extraction runs inside bubblewrap; scanned PDFs return an explicit no-text result, and Windows/macOS parsing remain unqualified.
The four skills are instruction artifacts, and the service has authenticated Streamable HTTP reads and contribution tools. Local-file ingestion uses two MCP server entries: the Streamable HTTP service endpoint provides workflow tools, while the `gewu-connector` stdio process runs on the machine with the selected files, reads only its explicit allowlist, and streams the bytes without exposing file bytes or credentials in model-visible tool responses. The service endpoint cannot read a path on the agent machine. It is launched with one or more stable file IDs and paths, plus a service URL; the operator supplies `GEWU_TOKEN` through the host's protected environment rather than a command-line argument. The connector requires HTTPS for non-loopback services and stores resumable upload checkpoints in a private state file. The pack manifest is bound to generated wire schemas and now has a reversible workspace installer, but host MCP configuration, native client workflows and remote deployment remain unqualified. The authenticated `source_capture_url` MCP operation is enabled only when the operator configures the exact public-host allowlist in `GEWU_FETCH_ALLOWED_HOSTS`; URL and selected-file intake support UTF-8 text, Markdown, HTML visible-text extraction and PDF. Linux PDF extraction runs inside bubblewrap; scanned PDFs return an explicit no-text result, and Windows/macOS parsing remain unqualified.
## Run and resume contract