docs(ingest): Enhance guidance for naming and context awareness

skills/ingest/SKILL.md

@@ -39,9 +39,17 @@ which matters on a small local model.
 5. On a real contradiction with an existing claim, follow `AGENTS.md` §Conflict: create
    `wiki/queries/conflict-<concept>-<YYYY-MM-DD>.md`. Never overwrite the existing page.
 
-Name files in kebab-case and pick stable names. Read `wiki/index.md` (and the specific
-pages it points to) to decide create-vs-update and to spot contradictions. Do not scan
-whole directories.
+**Naming — you are the sole author of these names; nothing renames your files.** Use
+minimal kebab-case: lowercase letters, digits and hyphens only — no spaces, no underscores,
+no capitals. Pick stable names so the same entity is never created twice (always `acme`,
+never also `acme-corp`). The path you write a file to MUST be byte-for-byte the path you
+list in the manifest.
+
+**Deciding create-vs-update and spotting contradictions — mind the context budget.** Use
+`wiki/index.md` to locate existing pages, then read **only** the handful that _this source
+actually names_ — the entities and concepts in the source's title and opening paragraphs —
+not everything the index lists. When in doubt, read fewer: a missed cross-link is far
+cheaper than a saturated context. Never scan whole directories.
 
 ## Finish: write the manifest, then STOP
 
@@ -52,7 +60,6 @@ append to the log/index, or open anything.
 ```json
 {
   "raw_source": "raw/articles/foo.md",
-  "model": "<the model you are running as>",
   "reasoning": "One sentence for the log: what changed and why.",
   "pr_summary": "One or two sentences describing this ingest for the PR.",
   "contradictions": "None   (or: 1 conflict file created — <concept>)",
@@ -66,7 +73,6 @@ append to the log/index, or open anything.
     {
       "path": "wiki/entities/acme.md",
       "summary": "Acme — vendor.",
-      "maturity": "draft",
       "status": "modified"
     }
   ]
@@ -78,6 +84,10 @@ Manifest rules:
 - List every page you created or modified, with `status` `created` or `modified`.
 - `summary` is the one-line index description (≈12 words max). For conflict pages the
   summary is ignored — the index lists conflicts by slug only.
+- `maturity` is required only on `created` pages (it seeds the new index entry). It is
+  ignored for `modified` pages, so omit it there.
+- Do NOT add a `model` field — the orchestrator records which model produced this run; you
+  cannot know your own model name reliably, so do not guess one.
 - Do not invent a `run_id`, branch, commit, or PR — those belong to the post-processor.
 
 One source per session. After writing the manifest, stop.

skills/ingest/scripts/run-ingest.sh

@@ -27,7 +27,9 @@ command -v python3 >/dev/null 2>&1 || fail "deps" "python3 missing (needed by in
 
 # --- read manifest scalars ---
 raw_source="$(jq -r '.raw_source'             "$manifest")"
-model="$(jq -r '.model // "unknown"'          "$manifest")"
+# model name comes from the orchestrator/wrapper (INGEST_MODEL); the agent cannot know its
+# own tag, so we do not trust a self-reported manifest field. Fall back only if unset.
+model="${INGEST_MODEL:-$(jq -r '.model // "unknown"' "$manifest")}"
 reasoning="$(jq -r '.reasoning // "Ingest."'  "$manifest")"
 pr_summary="$(jq -r '.pr_summary // "Ingest."' "$manifest")"
 contradictions="$(jq -r '.contradictions // "None"' "$manifest")"

tests/run-ingest.bats

@@ -91,3 +91,44 @@ EOF
   # listed by slug under the Conflicts section
   grep -q 'queries/conflict-pricing-2026-06-03' wiki/index.md
 }
+
+@test "run-ingest: records INGEST_MODEL in the log (manifest carries no model field)" {
+  command -v jq >/dev/null 2>&1 || skip "jq not installed"
+
+  G="$(make_fixture_genome)"; cd "$G"
+
+  cat > wiki/sources/test-source.md <<'EOF'
+---
+title: "Test Source"
+type: source
+domain: genome-test
+tags: [t]
+maturity: draft
+last_updated: 2026-06-04
+private: false
+---
+body
+EOF
+
+  # New contract: NO "model" field — the orchestrator supplies it via INGEST_MODEL.
+  cat > .ingest-manifest.json <<'EOF'
+{
+  "raw_source": "raw/articles/test.md",
+  "reasoning": "Ingested the test source.",
+  "pr_summary": "Ingest of test: 1 source page.",
+  "contradictions": "None",
+  "pages": [
+    {"path": "wiki/sources/test-source.md", "summary": "A smoke-test source.", "maturity": "draft", "status": "created"}
+  ]
+}
+EOF
+
+  export KG_LIB_DIR="$LIB_DIR"
+  export FORGEJO_URL="http://forgejo.local" FORGEJO_USER="u" FORGEJO_TOKEN="t" DRY_RUN=1
+  export INGEST_MODEL="qwen-test-tag"
+
+  run bash "$SKILL_SCRIPTS/run-ingest.sh" genome-test
+  [ "$status" -eq 0 ]
+  [[ "$output" == *'"status":"ok"'* ]]
+  grep -q 'qwen-test-tag' wiki/log.md
+}