@c4a/context-cli 0.7.1 → 0.7.5

package/plugins/skills/context-markdown-indexer/references/indexer.md

@@ -1,6 +1,6 @@
 # Markdown Indexer authoring contract
 
-Classify and author at the source-backed Section level. A document profile describes reader intent; it is not an output directory. Mixed documents may contain Sections with different reader goals, but every Section must retain one stable subject, owner, source authority, and projection intent.
+Classify and author at the source-backed Section level using only the current Authorized Workset View. A document profile describes reader intent; it is not an output directory. Mixed documents may contain Sections with different reader goals, but every Section must retain one stable subject, owner, source authority, and projection intent.
 
 Use `classification.md` as the semantic source for `document_kind`, `reader_goal`, and current `artifact_kind` selection. Use `structure-and-artifacts.md` for mixed-document routing, Section-versus-Artifact promotion, density, duplicate/conflict handling, and target candidate resolution. The CLI-supplied profile contract remains the only authority for collection and path projection.
 
@@ -14,10 +14,39 @@ Use `editorial-policy.md` for scenario editorial signals, recommended outcomes,
 
 Preserve exact commands, identifiers, links, attachments, tables, and code blocks when they are evidence-bearing. Separate deterministic catalogs from explanation. Do not publish unsupported claims, conversion annotations, placeholders, or unresolved requests as knowledge.
 
-When current source material cannot answer a required canonical question, return the exact material-question disposition for the supplied target. Answers may use only authorized evidence kinds and spans. Context owns review, layout, collection mapping, material-gap persistence, quality thresholds, and final close.
+When a captured document already contains coherent reader-facing guidance, preserve and organize that supported content instead of replacing it with a heading inventory, directory summary, or a sentence that points the reader back to the source. Summarize only repetition or navigation scaffolding. A shorter Artifact is acceptable only when it still answers the selected reader questions and retains the source's useful contracts, examples, conditions, compatibility notes, and uncertainty.
 
-Follow the operation in the supplied run request. For `main-index`, return only the current `IndexerResult`/`ArtifactResult` contract; Context derives the exact source-span, selected-fact, logical-unit, Artifact, and negative group-input dependencies from that result. For `material-answer`, return only `context.indexer.material-answer-result/v1`. Each binding must echo one eligible `question_key`, its exact `question_revision_digest`, and canonical evidence claims containing only `kind`, authorized `source_ref`, normalized `source_spans`, and the current content `evidence_digest`. Do not return reader prose, an answer body, source-origin/input identities, an `EvidenceItemRef`, a future Artifact/Section identity, or an actualization. Context canonicalizes evidence, performs the limited Review, derives a body-free planned answer from the approved binding, and maps its supplied answer landing after layout.
+For each reader Artifact, start the first actual Section with exactly one
+level-one heading that names the reader subject. Keep the heading concise and
+source-backed. It is a display title for outline and final Candidate Review,
+not a SubjectKey, ownership signal, or identity fallback. Later Sections in the
+same Artifact must not add another level-one heading.
 
-Never create a legacy `MarkdownCollectionSlice` or invoke the independent `alignProse` phase. Never mix `main-index` and `material-answer` output.
+When current source material cannot answer a required canonical question, return the exact material-question disposition for the supplied target. A later run may consume newly captured Markdown as ordinary source and update the same knowledge candidate. Context owns layout, collection mapping, runtime material-gap state, quality thresholds, the single final content Review, and close.
+
+Return only the current `main-index` `IndexerResult`/`ArtifactResult` contract. Context derives the source dependencies needed for stale detection and recovery from that result. Do not emit a separate answer body, answer-only result, future Artifact/Section landing, or post-layout actualization.
+
+Return all knowledge through the current Indexer result; do not create an independent authoring pipeline.
+
+## Quality guidance and production checks
+
+Context blocks only conditions it can derive from current inputs: the complete
+source inventory needs dispositions, the selected reader-question set needs a
+complete plan, answered questions must satisfy their evidence contracts, and
+references, layout and currentness must remain valid.
+
+Profile metrics are writing guidance rather than a separate pass decision.
+They point out duplicated facts, enumeration where explanation was expected,
+repeated template scaffolding, oversized quoted bodies, traversal-ordered
+Partitions, reference-only targets and unsupported optional Artifacts. Treat a
+finding as a prompt to reread the Section. Do not adjust wording, headings,
+sentence counts or Partitions merely to move a counter.
+
+Natural-language statements are not mechanically checked sentence by sentence.
+Use only behavior stated by the supplied material, record a material gap when
+the source does not establish a needed conclusion, and rely on final Review to
+reject unsupported interpretation. When shape guidance conflicts with source
+coverage, preserve the source-backed content and improve its presentation
+rather than deleting it.
 
 Do not return output paths, collection names, arbitrary question text, new authority, or pass/fail claims.

package/plugins/skills/context-markdown-indexer/references/semantic-planning.md

@@ -1,15 +1,31 @@
-# Evidence, subject, and claim planning
-
-Use these rules while producing the operation selected by the current run
-request. For the current `main-index` `ArtifactResult`, apply every rule below. For
-`material-answer`, produce only evidence claims for eligible questions; the
-question identity, landing, canonical evidence items, planned-answer projection
-and post-layout actualization remain Context-owned. These rules preserve the
-useful semantic judgments from the former classification and align path without
-restoring `context.structure.v1`, collection selection, or a second write
-workflow. Context remains the authority for schemas, SubjectKey normalization,
-identities, paths, collisions, stale state, layout changes, Review, and
-publication.
+# Source, subject, and claim planning
+
+Use these rules while producing the current `main-index` `ArtifactResult`.
+Captured Markdown is ordinary source material: it may create or enrich the same
+knowledge candidates as code-derived input. If required material is still
+missing, return a material-gap disposition and let a later main-index run consume
+the newly captured source. Do not create an answer-only result, landing, or
+second review workflow. Context remains the authority for schemas, SubjectKey
+normalization, identities, paths, collisions, stale state, layout changes,
+Review, and publication.
+
+## `reader-subject` partition strategy
+
+For a partition workset, group captured document members by durable reader
+subject rather than by file, heading, route, or temporary capture batch. Use
+the complete authorized document text together with maintained title,
+`source_path`, route, audience, and reader-task evidence. These fields are
+evidence for the decision; none is sufficient by itself.
+
+One group may contain multiple documents when they jointly explain the same
+reader subject. Split platform or runtime variants only when their supported
+contract, behavior, lifecycle, or reader task is materially different. Keep
+navigation-only indexes, generated duplicates, empty placeholders, and
+superseded pages out of authored groups with an explicit inventory
+disposition. Every current inventory member must still receive exactly one
+partition disposition. If durable subject boundaries cannot be established,
+fail this semantic strategy so Context can use its existing catalog fallback;
+do not silently return one group per file under `reader-subject`.
 
 ## Evidence and authority
 
@@ -18,8 +34,8 @@ making a source-wide decision. A file name, URL, title, heading, navigation
 label, polished wording, profile id, or example is a navigation signal, not
 proof of subject identity, authority, or reader intent.
 
-Use only current source roles, evidence bindings, target-resolution views, and
-question targets supplied with the workset. Supporting or context-only material
+Use only current source roles, authorized source views, target-resolution views,
+and question targets supplied with the workset. Supporting or context-only material
 may guide investigation but cannot become a cited Section or structured claim
 unless the current authority makes it eligible. Preserve exact identifiers,
 commands, links, numbers, conditions, code, and source-authored uncertainty.

package/plugins/skills/context-markdown-indexer/references/structure-and-artifacts.md

@@ -32,6 +32,12 @@ or a long table. Do not create thin Artifacts to improve counts. If material has
 an independent subject rather than merely a separate reader page, use the
 workset's target-resolution choices; never invent a Node identity from a title.
 
+Do not collapse a substantial captured document into a page that only lists its
+headings or says the source should be consulted. Preserve supported procedures,
+API tables, examples, constraints, compatibility notes, and decisions inside
+the selected reader Artifact; remove only navigation chrome, conversion noise,
+duplicates, and content with an explicit omission disposition.
+
 Within one Artifact, every Section must use that Artifact's `artifact_kind`.
 Start by grouping only Sections with the same exact
 `document_kind + reader_goal + artifact_kind` intent. Different intents may be

package/plugins/skills/context-markdown-indexer/tests/fixtures/anonymous.json

@@ -18,7 +18,7 @@
       "artifact_kind": "content",
       "purpose": "required",
       "reader_question_refs": [
-        "question:source-authority"
+        "question:reader-structure"
       ],
       "evidence_refs": [
         "evidence:anonymous-guide-source"

package/plugins/skills/context-markdown-indexer/tests/fixtures/profiles.json

@@ -9,7 +9,7 @@
     "logical_unit_ref": "node:anonymous-domain-reference",
     "canonical_facts": { "target": { "eligible": true } },
     "artifact_policy_variant": "standard",
-    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:source-authority"], "evidence_refs": ["evidence:anonymous-domain-reference-source"] }],
+    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:reader-purpose"], "evidence_refs": ["evidence:anonymous-domain-reference-source"] }],
     "evidence_refs": ["evidence:anonymous-domain-reference-source"]
   },
   {
@@ -22,7 +22,7 @@
     "logical_unit_ref": "node:anonymous-product-requirements",
     "canonical_facts": { "target": { "eligible": true } },
     "artifact_policy_variant": "standard",
-    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:source-authority"], "evidence_refs": ["evidence:anonymous-product-requirements-source"] }],
+    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:reader-purpose"], "evidence_refs": ["evidence:anonymous-product-requirements-source"] }],
     "evidence_refs": ["evidence:anonymous-product-requirements-source"]
   },
   {
@@ -35,7 +35,7 @@
     "logical_unit_ref": "node:anonymous-technical-guide",
     "canonical_facts": { "target": { "eligible": true } },
     "artifact_policy_variant": "standard",
-    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:source-authority"], "evidence_refs": ["evidence:anonymous-technical-guide-source"] }],
+    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:reader-structure"], "evidence_refs": ["evidence:anonymous-technical-guide-source"] }],
     "evidence_refs": ["evidence:anonymous-technical-guide-source"]
   },
   {
@@ -48,7 +48,7 @@
     "logical_unit_ref": "node:anonymous-user-and-developer-guide",
     "canonical_facts": { "target": { "eligible": true } },
     "artifact_policy_variant": "standard",
-    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:source-authority"], "evidence_refs": ["evidence:anonymous-user-and-developer-guide-source"] }],
+    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:reader-operation"], "evidence_refs": ["evidence:anonymous-user-and-developer-guide-source"] }],
     "evidence_refs": ["evidence:anonymous-user-and-developer-guide-source"]
   },
   {
@@ -61,7 +61,7 @@
     "logical_unit_ref": "node:anonymous-public-api-reference",
     "canonical_facts": { "target": { "eligible": true } },
     "artifact_policy_variant": "standard",
-    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:source-authority"], "evidence_refs": ["evidence:anonymous-public-api-reference-source"] }],
+    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:reader-contract"], "evidence_refs": ["evidence:anonymous-public-api-reference-source"] }],
     "evidence_refs": ["evidence:anonymous-public-api-reference-source"]
   },
   {
@@ -74,7 +74,7 @@
     "logical_unit_ref": "node:anonymous-runbook",
     "canonical_facts": { "target": { "eligible": true } },
     "artifact_policy_variant": "standard",
-    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:source-authority"], "evidence_refs": ["evidence:anonymous-runbook-source"] }],
+    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:reader-operation"], "evidence_refs": ["evidence:anonymous-runbook-source"] }],
     "evidence_refs": ["evidence:anonymous-runbook-source"]
   },
   {
@@ -87,7 +87,7 @@
     "logical_unit_ref": "node:anonymous-faq-support",
     "canonical_facts": { "target": { "eligible": true } },
     "artifact_policy_variant": "standard",
-    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:source-authority"], "evidence_refs": ["evidence:anonymous-faq-support-source"] }],
+    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:reader-purpose"], "evidence_refs": ["evidence:anonymous-faq-support-source"] }],
     "evidence_refs": ["evidence:anonymous-faq-support-source"]
   },
   {
@@ -100,7 +100,7 @@
     "logical_unit_ref": "node:anonymous-standard-policy",
     "canonical_facts": { "target": { "eligible": true } },
     "artifact_policy_variant": "standard",
-    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:source-authority"], "evidence_refs": ["evidence:anonymous-standard-policy-source"] }],
+    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:reader-contract"], "evidence_refs": ["evidence:anonymous-standard-policy-source"] }],
     "evidence_refs": ["evidence:anonymous-standard-policy-source"]
   },
   {
@@ -113,7 +113,7 @@
     "logical_unit_ref": "node:anonymous-decision-record",
     "canonical_facts": { "target": { "eligible": true } },
     "artifact_policy_variant": "standard",
-    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:source-authority"], "evidence_refs": ["evidence:anonymous-decision-record-source"] }],
+    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:reader-purpose"], "evidence_refs": ["evidence:anonymous-decision-record-source"] }],
     "evidence_refs": ["evidence:anonymous-decision-record-source"]
   },
   {
@@ -126,7 +126,7 @@
     "logical_unit_ref": "node:anonymous-incident-review",
     "canonical_facts": { "target": { "eligible": true } },
     "artifact_policy_variant": "standard",
-    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:source-authority"], "evidence_refs": ["evidence:anonymous-incident-review-source"] }],
+    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:reader-operation"], "evidence_refs": ["evidence:anonymous-incident-review-source"] }],
     "evidence_refs": ["evidence:anonymous-incident-review-source"]
   },
   {
@@ -139,7 +139,7 @@
     "logical_unit_ref": "node:anonymous-test-validation",
     "canonical_facts": { "target": { "eligible": true } },
     "artifact_policy_variant": "standard",
-    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:source-authority"], "evidence_refs": ["evidence:anonymous-test-validation-source"] }],
+    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:reader-operation"], "evidence_refs": ["evidence:anonymous-test-validation-source"] }],
     "evidence_refs": ["evidence:anonymous-test-validation-source"]
   },
   {
@@ -152,7 +152,7 @@
     "logical_unit_ref": "node:anonymous-release-migration-guide",
     "canonical_facts": { "target": { "eligible": true } },
     "artifact_policy_variant": "standard",
-    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:source-authority"], "evidence_refs": ["evidence:anonymous-release-migration-guide-source"] }],
+    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:reader-operation"], "evidence_refs": ["evidence:anonymous-release-migration-guide-source"] }],
     "evidence_refs": ["evidence:anonymous-release-migration-guide-source"]
   },
   {
@@ -165,7 +165,7 @@
     "logical_unit_ref": "node:anonymous-documentation-site",
     "canonical_facts": { "target": { "eligible": true } },
     "artifact_policy_variant": "standard",
-    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:source-authority"], "evidence_refs": ["evidence:anonymous-documentation-site-source"] }],
+    "artifacts": [{ "artifact_id": "content", "artifact_kind": "content", "purpose": "required", "reader_question_refs": ["question:reader-purpose"], "evidence_refs": ["evidence:anonymous-documentation-site-source"] }],
     "evidence_refs": ["evidence:anonymous-documentation-site-source"]
   }
 ]

package/plugins/skills/context-markdown-indexer/tests/fixtures/routing.json

@@ -146,6 +146,128 @@
           ]
         }
       ]
+    },
+    {
+      "id": "anonymous-product-intent",
+      "profile": "product-requirements",
+      "source_role": "authoritative-document",
+      "density_mode": "meso",
+      "candidate_signal": "coherent-product-outcome",
+      "candidate_resolution": "dismiss-with-rationale",
+      "artifacts": [{
+        "artifact_id": "product-intent",
+        "artifact_kind": "content",
+        "boundary_decision": "retain-section-group",
+        "sections": [{ "section_key": "outcome", "owner_indexer_id": "anonymous-markdown-indexer", "document_kind": "product-requirements", "reader_goal": "understand-product-intent", "artifact_kind": "content" }]
+      }]
+    },
+    {
+      "id": "anonymous-public-api-contract",
+      "profile": "public-api-reference",
+      "source_role": "authoritative-document",
+      "density_mode": "meso",
+      "candidate_signal": "contract-and-policy-boundaries",
+      "candidate_resolution": "accept-correction",
+      "artifacts": [
+        { "artifact_id": "api-reference", "artifact_kind": "content", "boundary_decision": "promote-reader-artifact", "sections": [{ "section_key": "operations", "owner_indexer_id": "anonymous-markdown-indexer", "document_kind": "public-api-reference", "reader_goal": "look-up-public-contract", "artifact_kind": "content" }] },
+        { "artifact_id": "contract-policy", "artifact_kind": "content", "boundary_decision": "promote-reader-artifact", "sections": [{ "section_key": "compatibility", "owner_indexer_id": "anonymous-markdown-indexer", "document_kind": "public-contract-policy", "reader_goal": "follow-public-contract-policy", "artifact_kind": "content" }] }
+      ]
+    },
+    {
+      "id": "anonymous-operational-runbook",
+      "profile": "runbook",
+      "source_role": "operational-document",
+      "density_mode": "micro",
+      "candidate_signal": "ordered-recovery-task",
+      "candidate_resolution": "keep-unresolved",
+      "artifacts": [{
+        "artifact_id": "recovery-procedure",
+        "artifact_kind": "content",
+        "boundary_decision": "retain-section-group",
+        "sections": [{ "section_key": "recover", "owner_indexer_id": "anonymous-markdown-indexer", "document_kind": "runbook", "reader_goal": "operate-or-recover-system", "artifact_kind": "content" }]
+      }]
+    },
+    {
+      "id": "anonymous-support-answers",
+      "profile": "faq-support",
+      "source_role": "supporting-document",
+      "density_mode": "micro",
+      "candidate_signal": "independent-reader-question",
+      "candidate_resolution": "accept-correction",
+      "artifacts": [{
+        "artifact_id": "support-answer",
+        "artifact_kind": "content",
+        "boundary_decision": "promote-reader-artifact",
+        "sections": [{ "section_key": "answer", "owner_indexer_id": "anonymous-markdown-indexer", "document_kind": "faq-support", "reader_goal": "resolve-reader-question", "artifact_kind": "content" }]
+      }]
+    },
+    {
+      "id": "anonymous-standard-policy",
+      "profile": "standard-policy",
+      "source_role": "authoritative-document",
+      "density_mode": "single-pass",
+      "candidate_signal": "single-normative-scope",
+      "candidate_resolution": "dismiss-with-rationale",
+      "artifacts": [{
+        "artifact_id": "policy",
+        "artifact_kind": "content",
+        "boundary_decision": "retain-section-group",
+        "sections": [{ "section_key": "requirements", "owner_indexer_id": "anonymous-markdown-indexer", "document_kind": "standard-policy", "reader_goal": "follow-standard-or-policy", "artifact_kind": "content" }]
+      }]
+    },
+    {
+      "id": "anonymous-architecture-decision",
+      "profile": "decision-record",
+      "source_role": "decision-record",
+      "density_mode": "single-pass",
+      "candidate_signal": "decision-with-tradeoffs",
+      "candidate_resolution": "dismiss-with-rationale",
+      "artifacts": [{
+        "artifact_id": "decision",
+        "artifact_kind": "content",
+        "boundary_decision": "retain-section-group",
+        "sections": [{ "section_key": "tradeoffs", "owner_indexer_id": "anonymous-markdown-indexer", "document_kind": "decision-record", "reader_goal": "understand-decision-and-tradeoffs", "artifact_kind": "content" }]
+      }]
+    },
+    {
+      "id": "anonymous-incident-learning",
+      "profile": "incident-review",
+      "source_role": "operational-document",
+      "density_mode": "macro",
+      "candidate_signal": "timeline-and-remediation",
+      "candidate_resolution": "accept-correction",
+      "artifacts": [{
+        "artifact_id": "incident-review",
+        "artifact_kind": "content",
+        "boundary_decision": "retain-section-group",
+        "sections": [{ "section_key": "learning", "owner_indexer_id": "anonymous-markdown-indexer", "document_kind": "incident-review", "reader_goal": "learn-from-incident", "artifact_kind": "content" }]
+      }]
+    },
+    {
+      "id": "anonymous-validation-record",
+      "profile": "test-validation",
+      "source_role": "supporting-document",
+      "density_mode": "meso",
+      "candidate_signal": "acceptance-result",
+      "candidate_resolution": "keep-unresolved",
+      "artifacts": [{
+        "artifact_id": "validation",
+        "artifact_kind": "content",
+        "boundary_decision": "retain-section-group",
+        "sections": [{ "section_key": "result", "owner_indexer_id": "anonymous-markdown-indexer", "document_kind": "test-validation", "reader_goal": "verify-behavior-or-acceptance", "artifact_kind": "content" }]
+      }]
+    },
+    {
+      "id": "anonymous-release-migration",
+      "profile": "release-migration-guide",
+      "source_role": "authoritative-document",
+      "density_mode": "macro",
+      "candidate_signal": "release-and-migration-tasks",
+      "candidate_resolution": "accept-correction",
+      "artifacts": [
+        { "artifact_id": "release-change", "artifact_kind": "content", "boundary_decision": "promote-reader-artifact", "sections": [{ "section_key": "change", "owner_indexer_id": "anonymous-markdown-indexer", "document_kind": "release-guide", "reader_goal": "understand-release-change", "artifact_kind": "content" }] },
+        { "artifact_id": "migration-task", "artifact_kind": "content", "boundary_decision": "promote-reader-artifact", "sections": [{ "section_key": "steps", "owner_indexer_id": "anonymous-markdown-indexer", "document_kind": "migration-guide", "reader_goal": "complete-migration", "artifact_kind": "content" }] }
+      ]
     }
   ]
 }

package/providers/context/actions/advance-current-indexer-lifecycle.yaml

@@ -0,0 +1,6 @@
+schema: agent-graph.action.v1
+id: advance-current-indexer-lifecycle
+description: Advance deterministic Indexer setup, fallback, recovery, and finalization to the next semantic step or Gate.
+runner: command
+effect: write
+command: context run --format json

package/providers/context/actions/authorize-current-indexer-provider-program.yaml

@@ -0,0 +1,6 @@
+schema: agent-graph.action.v1
+id: authorize-current-indexer-provider-program
+runner: agent
+effect: external
+skill: skills/authorize-current-indexer-provider-program/SKILL.md
+outputSchema: schemas/indexer-agent-step-result.schema.json

package/providers/context/actions/configure-indexer-providers.yaml

@@ -3,4 +3,4 @@ id: configure-indexer-providers
 runner: agent
 effect: write
 skill: skills/configure-indexer-providers/SKILL.md
-outputSchema: schemas/indexer-provider-route-input.schema.json
+outputSchema: schemas/indexer-agent-step-result.schema.json

package/providers/context/actions/finalize-current-indexer-provider-selection.yaml

@@ -0,0 +1,5 @@
+schema: agent-graph.action.v1
+id: finalize-current-indexer-provider-selection
+runner: command
+effect: write
+command: context run --format json

package/providers/context/actions/materialize-indexer-workset-view.yaml

@@ -0,0 +1,7 @@
+schema: agent-graph.action.v1
+id: materialize-indexer-workset-view
+runner: host
+effect: read
+handler: context.materialize-indexer-workset-view/v1
+inputSchema: schemas/indexer-workset-view-materialization-request.schema.json
+outputSchema: schemas/indexer-authorized-workset-view.schema.json

package/providers/context/actions/resolve-current-indexer-gate.yaml

@@ -0,0 +1,6 @@
+schema: agent-graph.action.v1
+id: resolve-current-indexer-gate
+runner: agent
+effect: write
+skill: skills/resolve-current-indexer-gate/SKILL.md
+outputSchema: schemas/indexer-agent-step-result.schema.json

package/providers/context/actions/resolve-current-indexer-provider.yaml

@@ -0,0 +1,6 @@
+schema: agent-graph.action.v1
+id: resolve-current-indexer-provider
+runner: agent
+effect: external
+skill: skills/resolve-current-indexer-provider/SKILL.md
+outputSchema: schemas/indexer-agent-step-result.schema.json

package/providers/context/actions/run-indexer-lifecycle.yaml

@@ -4,4 +4,3 @@ description: Continue the unique registry-and-Provider Indexer lifecycle until c
 runner: agent
 effect: write
 skill: skills/run-indexer-lifecycle/SKILL.md
-outputSchema: schemas/indexer-lifecycle-continuation.schema.json

package/providers/context/actions/run-indexer-post-author-composer.yaml

@@ -3,5 +3,5 @@ id: run-indexer-post-author-composer
 runner: agent
 effect: write
 skill: skills/run-indexer-post-author-composer/SKILL.md
-inputSchema: schemas/indexer-post-author-fragment-request.schema.json
-outputSchema: schemas/indexer-post-author-fragment-result.schema.json
+inputSchema: schemas/indexer-agent-step-input.schema.json
+outputSchema: schemas/indexer-agent-step-result.schema.json

package/providers/context/codes.yaml

@@ -18,19 +18,23 @@ codes:
   - { code: route.capture.configuration-required, kind: route-reason, summary: Registered document sources are missing capture declarations., document: resources/procedures/project-configuration.md }
   - { code: route.capture.permission-required, kind: route-reason, summary: External document capture requires source-read permission., document: resources/procedures/document-capture.md }
   - { code: route.capture.pending-target, kind: route-reason, summary: Capture the next declared document target., document: resources/procedures/document-capture.md }
-  - { code: route.review.identity-conflict, kind: route-reason, summary: Preserve approved ViewRef and path identity before Review., document: resources/procedures/knowledge-review.md }
   - { code: route.review.decision-required, kind: route-reason, summary: The complete current candidate batch needs one review decision set., document: resources/procedures/knowledge-review.md }
   - { code: route.review.apply-managed, kind: route-reason, summary: Apply the current candidate batch under explicit session-managed authority., document: resources/procedures/knowledge-review.md }
   - { code: route.close.projection-stale, kind: route-reason, summary: Rebuild the deterministic approved structure projection., document: resources/procedures/close-and-build.md }
   - { code: route.package.output-required, kind: route-reason, summary: Approved knowledge has no confirmed package output., document: resources/procedures/package-output.md }
   - { code: route.package.configuration-required, kind: route-reason, summary: Declare the confirmed package output in the Context project., document: resources/procedures/package-output.md }
   - { code: route.package.template-review-required, kind: route-reason, summary: "Replace or edit package templates, or explicitly accept the generic defaults.", document: resources/procedures/package-output.md }
-  - { code: route.document-revision.requested, kind: route-reason, summary: Apply and validate the user's requested correction on one approved knowledge page., document: resources/procedures/document-revision.md }
   - { code: route.build.package-stale, kind: route-reason, summary: Build the declared package outputs from current approved knowledge., document: resources/procedures/close-and-build.md }
   - { code: route.logs.delivery-pending, kind: route-reason, summary: Send locally queued runtime logs through the configured generic sink., document: resources/procedures/close-and-build.md }
   - { code: route.indexer.lifecycle-required, kind: route-reason, summary: Continue the sole registry-and-Provider indexing lifecycle until current Candidates exist. }
+  - { code: route.indexer.lifecycle-advance, kind: route-reason, summary: Advance deterministic Indexer lifecycle state to the next Agent step or user Gate. }
+  - { code: route.indexer.semantic-structure-review, kind: route-reason, summary: Review the complete semantic structure and create-or-enrich targets before Author work starts. }
+  - { code: route.indexer.recovery-required, kind: route-reason, summary: "Resolve a persisted source, material, or execution failure before retrying the Indexer lifecycle." }
+  - { code: route.indexer.layout-confirmation-required, kind: route-reason, summary: Confirm the proposed knowledge layout change or reject it with revision feedback. }
   - { code: route.indexer.agent-step, kind: route-reason, summary: Run one digest-bound Indexer workset with the static Context Agent Action. }
   - { code: route.indexer.provider-configuration, kind: route-reason, summary: Configure an exact path-free Provider selection from currently visible Indexer Skills. }
+  - { code: route.indexer.provider-host-resolution-required, kind: route-reason, summary: Resolve the exact current Indexer Provider through its declared Host Action. }
+  - { code: route.indexer.provider-finalization-required, kind: route-reason, summary: Deterministically validate and apply the fully resolved current Indexer Provider selection. }
   - { code: route.indexer.markdown-capture-validation, kind: route-reason, summary: Require exact current document capture before discovering a semantic Markdown Provider. }
   - { code: route.indexer.markdown-provider-discovery, kind: route-reason, summary: Report visible Markdown Indexer Skills and build one capture-bound Provider route input. }
   - { code: route.indexer.markdown-provider-validation, kind: route-reason, summary: Revalidate the capture-bound selection and resolve it through the exact CLI or Host boundary. }
@@ -75,25 +79,7 @@ codes:
   - { code: route.indexer.post-author-observation, kind: route-reason, summary: Join current composer worksets with their ledger and publish independent completion Facts. }
   - { code: route.indexer.post-author-composition, kind: route-reason, summary: Compose the current result envelope after every selected composer is accepted. }
   - { code: route.indexer.result-reconciliation, kind: route-reason, summary: Recompute per-domain completion and emit exact capability or material gaps before reporting success. }
-  - { code: route.indexer.material-question-workset, kind: route-reason, summary: Build immutable question-target pairs and derive exact answer eligibility from current registry authority. }
-  - { code: route.indexer.material-answer-run-preparation, kind: route-reason, summary: Recover content-addressed material-answer runs and accepted empty or non-empty Results. }
-  - { code: route.indexer.material-answer-observation, kind: route-reason, summary: "Publish material-answer counts, next refs, candidates, and unresolved question keys." }
-  - { code: route.indexer.material-answer-run-start, kind: route-reason, summary: Persist one exact pending or stale material-answer run before dispatch. }
-  - { code: route.indexer.material-answer-agent-step, kind: route-reason, summary: Run one semantic-operation-gated material-answer request without rerunning main extraction. }
-  - { code: route.indexer.material-answer-run-acceptance, kind: route-reason, summary: Validate current source-span read receipts and atomically accept one material-answer Result. }
-  - { code: route.indexer.material-answer-run-failure, kind: route-reason, summary: Persist one exact material-answer failure without accepting partial evidence. }
-  - { code: route.indexer.material-answer-review, kind: route-reason, summary: Approve or reject only one exact material-answer evidence binding; final reader content remains unapproved. }
-  - { code: route.indexer.material-gap-audit, kind: route-reason, summary: Read-only recompute the expected retained material-gap ledger and route pre-Review drift to checkpoint or post-Review closure to close. }
-  - { code: route.indexer.material-gap-checkpoint, kind: route-reason, summary: Recompute and durably checkpoint the retained material-gap ledger before any blocking outcome. }
-  - { code: route.indexer.material-answer-review-checkpoint, kind: route-reason, summary: Persist one exact answer-approved successor under retained ledger CAS. }
-  - { code: route.indexer.candidate-review-readiness, kind: route-reason, summary: Prove exact precompile and postcompile mechanical audits are current for the effective candidate revision. }
   - { code: route.indexer.candidate-compile, kind: route-reason, summary: Compile Candidate Artifacts from the exact accepted author IndexerResult set and authorized layout. }
   - { code: route.indexer.incremental-impact, kind: route-reason, summary: "Report exact logical-unit, Artifact, and Section impact from complete current Merkle dependency views." }
-  - { code: route.indexer.profile-revision, kind: route-reason, summary: Revise one exact candidate set against the recorded runtime profile failure without changing baseline authority. }
-  - { code: route.indexer.profile-revision-record, kind: route-reason, summary: Record one distinct result revision under the stable problem lineage and three-attempt ledger CAS. }
-  - { code: route.indexer.profile-failure-report, kind: route-reason, summary: "Persist the complete module, artifact, metric, attempt, missing-input, and capability-loss report after three failures." }
-  - { code: route.indexer.profile-override, kind: route-reason, summary: Require the user to force approve one exact current runtime profile risk through a non-delegable Gate. }
-  - { code: route.indexer.candidate-review, kind: route-reason, summary: Review the exact current candidate set only after the mechanical audit readiness proof passes. }
-  - { code: route.indexer.material-gap-evaluation, kind: route-reason, summary: Derive layout and main Review admission from the current retained ledger. }
-  - { code: route.indexer.material-answer-actualization, kind: route-reason, summary: Map answer-approved landings to current Artifact or Section identities and checkpoint the result. }
-  - { code: route.indexer.approved-knowledge-close, kind: route-reason, summary: Atomically close approved Indexer structure with exact resolved material-answer provenance. }
+  - { code: route.indexer.candidate-review, kind: route-reason, summary: Review the exact current candidate set only after current mechanical validation passes. }
+  - { code: route.indexer.approved-knowledge-close, kind: route-reason, summary: Atomically close approved Indexer structure after required material gaps are resolved. }