fix(agent): bound Antigravity ingestion flow

skills/kb-ingest/SKILL.md

@@ -6,11 +6,11 @@ description: Process explicitly selected sources for a GEWU project into evidenc
 
 Read the pack's [evidence](../../protocols/EVIDENCE.md), [scope](../../protocols/SCOPE.md) and [contribution](../../protocols/CONTRIBUTIONS.md) protocols, then use the [ingestion pipeline](../../pipelines/ingest.md).
 
-Inputs are the selected source(s), explicit project and the user's research objective. Use `get_project_context` for the project's north star, key questions, watch list, taxonomy extensions, research lenses and saved ingest guidance. Every project defaults to four research lenses: technical, conceptual, cultural-historical and financial-market. Treat these as coverage prompts, not quotas. Confirm required tools and arguments from MCP discovery and `diagnostics`; use the schema attached to each discovered tool. For Antigravity, do not open generated MCP cache JSON files or read future tool schemas in advance. Create the service run after diagnostics and project context; use `run_pins` from `.agents/gewu-install.json` as defined in CONTRIBUTIONS.md. If a required tool is absent or a call produces a concrete schema mismatch, inspect only that tool's pinned contract entry and report unresolved drift before mutation. Use the connector for local byte transfer; it returns a typed source metadata candidate without exposing the selected path or bytes. Selected `.vtt` and `.srt` files produce timestamped transcript cues; cite exact cue start/end times and the quote span. A declared NotebookLM export label is metadata only and is not export verification. For text explicitly pasted by the user, use `source_capture_text` with a stable capture ID and source key; it accepts UTF-8 plain text or Markdown up to 1 MB, archives and extracts it, and returns a typed candidate marked `capture_method=pasted-text`. Retry uncertain calls with the same capture ID and identical inputs; changed input under that ID conflicts. It does not register the candidate. `source_capture_url` fetches only operator-allowlisted public hosts and stages supported text, Markdown, HTML or PDF bytes; it also returns a source metadata candidate but does not register it. Add each new source's exact candidate as `register_source` in the proposal that cites it, or verify the source was already registered and readable. Use the candidate's `revision_id` and capture's `extraction_id`; never invent or substitute these IDs. Submit candidates with the normal typed proposal flow, and use `capture-failed` candidates only as bookmarks, never as factual evidence. URL source IDs follow the sanitized URL; local source IDs follow the connector's configured file ID; pasted-text source IDs are derived from the supplied stable key and revision IDs include the content digest. PDF extraction currently requires Linux bubblewrap, Poppler and prlimit. Unsupported formats and unavailable parsers must be reported without inventing an extraction. If the service is unavailable, report the blocked stage and only prepare an unaccepted local draft when that work was requested.
+Inputs are the selected source(s), explicit project and the user's research objective. Use `get_project_context` for the project's north star, key questions, watch list, taxonomy extensions, research lenses and saved ingest guidance. Every project defaults to four research lenses: technical, conceptual, cultural-historical and financial-market. Treat these as coverage prompts, not quotas. Confirm required tools and arguments from MCP discovery and `diagnostics`; use the schema attached to each discovered tool and the Antigravity argument reminders in CONTRIBUTIONS.md. For Antigravity, do not use shell tools or inspect the host MCP cache. On a schema mismatch, use only the relevant pinned entry in `contracts/service-v1.json` and correct once. Use GEWU tools only; Jev runs inside the backend through `ingest_review_create`, not a standalone Jev MCP server. In Antigravity, call `diagnostics`, `get_project_context` and `run_create` once each in order; after a successful call, reuse its returned state rather than repeating it. Do not call `get_source` for a staged candidate: use its exact returned candidate in the proposal's `register_source` operation and read the source's citation through its staged extraction. Create the durable service run with `run_create` after diagnostics and project context; pass its `request_json` envelope using current `run_pins` from `.agents/gewu-install.json`. Do not look for a local `Runs/<run_id>` file before creation; run state is service-owned. Never reuse a run ID after changing the pack or create payload. Use the connector for local byte transfer; `upload_selected_file` requires both the configured `file_id` and the authorized `project_id`. It returns a typed source metadata candidate without exposing the selected path or bytes. Selected `.vtt` and `.srt` files produce timestamped transcript cues; cite exact cue start/end times and the quote span. A declared NotebookLM export label is metadata only and is not export verification. For text explicitly pasted by the user, use `source_capture_text` with a stable capture ID and source key; it accepts UTF-8 plain text or Markdown up to 1 MB, archives and extracts it, and returns a typed candidate marked `capture_method=pasted-text`. Retry uncertain calls with the same capture ID and identical inputs; changed input under that ID conflicts. It does not register the candidate. `source_capture_url` fetches only operator-allowlisted public hosts and stages supported text, Markdown, HTML or PDF bytes; it also returns a source metadata candidate but does not register it. Add each new source's exact candidate as `register_source` in the proposal that cites it, or verify the source was already registered and readable. Use the candidate's `revision_id` and capture's `extraction_id`; never invent or substitute these IDs. Submit candidates with the normal typed proposal flow, and use `capture-failed` candidates only as bookmarks, never as factual evidence. URL source IDs follow the sanitized URL; local source IDs follow the connector's configured file ID; pasted-text source IDs are derived from the supplied stable key and revision IDs include the content digest. PDF extraction currently requires Linux bubblewrap, Poppler and prlimit. Unsupported formats and unavailable parsers must be reported without inventing an extraction. If the service is unavailable, report the blocked stage and only prepare an unaccepted local draft when that work was requested.
 
 Extract useful atomic assertions, problems, techniques or cases with their conditions across all four lenses where the source contains relevant material. Consider cultural history, philosophical context and market/financial evidence as project data when they explain the project's origins, concepts, adoption, audience, costs or viability; they are not automatically peripheral. First try to connect uncertain material to the north star, a key question, a saved rule or one of the lenses. Exclude only clearly unrelated material, unavailable evidence, or material the user explicitly excluded. Do not defer a section merely because its relevance is indirect, non-technical or historical. Continue normal evidence-backed proposal evaluation/submission for all plausible useful findings. When human relevance/categorization feedback or explicit Jev label normalization is needed, call `ingest_review_create` with a single `review_json` string, the complete `IngestReviewCreate` fields, and the exact extraction excerpt/locator. The required rationale field is `relevance_rationale`, not `reason`; include `review_id` and `extraction_id`. This persists a non-blocking notification and never blocks the evidence-backed proposal flow.
 
-Before building each proposal, use the principal ID assigned to the configured agent credential for `proposer_id`, node `agent_id` and assessment `assessor_id`; do not use the model or harness name. If the operator has not provided that principal ID, stop before preparing or evaluating a proposal; diagnostics intentionally omits it. The proposal envelope requires `schema_version`, `proposal_id`, `revision`, `initiating_project_id`, `scope`, `base_commit`, `payload_digest`, `proposer_id`, `run_id` and `operations`. Use the current canonical revision from diagnostics as `base_commit`; do not add unsupported envelope fields. Finalize claim text, evidence and locators, then call `proposal_prepare` with the complete draft. It fills dependent digests but does not invent metadata or correct an invalid citation locator. For PDF evidence use `locator.kind="pdf_page_span"` with the extraction block's page; `text_span` cannot include a page. Proceed only when the tool returns `status="prepared"`, and pass its returned `proposal_json` unchanged to evaluation. If it returns `status="invalid"`, correct only the named issue and retry once. Do not probe it with an empty or incomplete proposal. If the tool is unavailable or rejects a corrected proposal, stop and report the concrete error.
+Before building each proposal, use the principal ID assigned to the configured agent credential for `proposer_id`, node `agent_id` and assessment `assessor_id`; do not use the model or harness name. If the operator has not provided that principal ID, stop before preparing or evaluating a proposal; diagnostics intentionally omits it. The proposal envelope requires `schema_version`, `proposal_id`, `revision`, `initiating_project_id`, `scope`, `base_commit`, `payload_digest`, `proposer_id`, `run_id` and `operations`. Use the current canonical revision from diagnostics as `base_commit`; do not add unsupported envelope fields. Finalize claim text, evidence and locators, then call `proposal_prepare` with the complete draft. It fills dependent digests but does not invent metadata or correct an invalid citation locator. For PDF evidence use `locator.kind="pdf_page_span"` with the extraction block's page; `text_span` cannot include a page. Proceed only when the tool returns `status="prepared"`, and pass its returned `proposal_json` unchanged to evaluation. Do not retype, reconstruct or edit that serialized string between tools; keep proposal content limited to the claims and evidence needed for one learning unit. The service can repair exactly one missing final outer `}` if the result passes the full contract; when this occurs the evaluation or submission response includes `input_repaired: true`. Other malformed JSON stays invalid. If evaluation returns `PROPOSAL_JSON_INVALID`, do not submit; rebuild and prepare the draft once, then stop if it remains invalid. A valid `needs-review` result (including `AUTO_ACCEPT_UNSPECIFIED`) is a policy hold for an owner decision, not a transport failure or automatic-acceptance candidate; do not submit it as eligible. If a tool is unavailable or rejects a corrected proposal, stop and report the concrete error.
 
 Use the input schema advertised for each MCP tool. If a call rejects its arguments, inspect only that tool's advertised/pinned schema, correct the arguments and retry once; do not probe unrelated tools or read the entire schema directory. Do not test proposal tools with invented IDs, placeholder identities, zero digests or incomplete payloads. Evaluate only the complete proposal for this learning unit; use `proposal_status` only for its real proposal ID and revision.