@c4a/context-cli 0.7.9 → 0.7.10-alpha.2

package/indexers/bundles/context-note-indexer/references/indexer.md

@@ -32,7 +32,7 @@ note itself states the boundary, use it and proceed within authorization.
 
 ## Diagrams
 
-Use the materialized [diagram guidance](diagrams.md) when a diagram clarifies the reader task. This also applies to older templates, source diagrams and Composer summaries. Preserve source strength, version and external boundaries; diagram presence is not a completion requirement.
+Use the materialized [diagram guidance](diagrams.md) when a diagram clarifies the reader task. This also applies to source diagrams and combined articles. Preserve source strength, version and external boundaries; diagram presence is not a completion requirement.
 
 ## Existing source images and tables
 
@@ -40,4 +40,8 @@ For authorized visual material, follow [source visual processing](visual-source-
 
 ## Reading selected article material
 
-Use the current task's combined writing brief: it includes selected article guidance, examples when supplied, and section/variable slots. Profile bindings can share one article Markdown source; do not open every binding or regenerate every listed article. Keep short collaboration notes and examples beside the relevant guidance instead of requesting separate files. Read extra source or full technical contracts only when this task needs them. The CLI applies executable contracts and evidence bindings; the Agent decides applicability, substance and useful diagrams. Reuse an already-read unchanged shared resource while it remains in context.
+Read the current task's brief and source navigation; choose relevant examples
+and source passages rather than enumerating profile bindings. For a revision,
+use the supplied base article and references. Reuse unchanged shared material
+already in context. The CLI checks source authorization, regional references
+and safe writes; the Agent decides the topic, meaning and useful diagrams.

package/indexers/bundles/context-note-indexer/references/updates-and-composition.md

@@ -1,37 +1,31 @@
 # Updates and composition
 
-First inspect the authorized existing knowledge and requested outcome. Saving
-input alone does not authorize a new indexing target. If a paragraph corrects
-an existing explanation, revise that approved page. Retain its useful steps,
-examples, images, limitations and confirmed contributions. If the material
-supports a new reader task, propose that topic through normal structure review
-before Author; never write directly to approved knowledge. If it adds nothing
-new, retain the source without producing a duplicate page.
+Start with existing article titles, descriptions and references. Read relevant
+article bodies or source passages when that navigation is insufficient. A
+correction belongs in the affected article; do not create a page merely to
+announce an improvement. A new reader question may justify a new target.
+Several authorized sources and skills may contribute to the same article.
+There is no primary-skill ownership or extension-profile binding to retain.
 
-Use one primary Provider per target. For an independent note/session topic this
-Provider may be primary with one of its declared document profiles. For an
-existing Code or Markdown page, retain that page's primary Provider. When this
-Provider's specialized interpretation is needed, select it as an extension
-layer and bind its prefixed extension profile to the active base profile, e.g.
-`note/component-library` extends `component-library`. `profile.additional`
-uses `kind: extension`, not `supporting`: supporting profiles belong to the
-same primary layer. Read actual manifests; do not invent a profile name for a
-business Provider.
+Use the current stage's plan submission to propose targets or append revision
+tasks. Preserve accepted articles; do not overwrite a successful task by
+resubmitting different content. Once a revision is issued, use its supplied
+base Markdown and reference table to edit only the necessary sections through
+the current submission schema. Keep useful unaffected examples and limitations.
 
-This is an instruction-only extension. Its selected references guide source
-interpretation in the primary task; it has no separate inspector/program and
-does not claim to emit machine fact fragments. It supplies source-backed
-distinctions, relevant reasons, conflicts and limits to the same writing task. It does not become a second author,
-replace the primary API table, or create a standalone session page merely
-because a source exists. Extend only the target's explicit evidence/read scope;
-a commit or URL in metadata does not authorize fetching it. If no extension is
-selected, the main Provider can still read authorized supporting material under
-its own guidance; do not silently enable an unavailable skill.
+Write drafts and submission files in the designated Agent temporary directory.
+Submit their paths through the current CLI action, not long shell arguments.
+The coordinator may submit a finished subset. Child Agents work only when the
+current host supports them and the issued directory permits that scheduling;
+they do not concurrently mutate shared production state.
 
-An incorrect source summary needs explicit correction by the host import flow,
-with current base_digest and task adjustment for pinned inputs. An accurate
-source but misleading page needs only approved-page revision. This Provider
-must not rewrite the original source to make a new page seem supported.
-A rejected revision leaves source material and approved content available for
-repair. Knowledge approval never changes upstream code, approves an MR, or
-turns a proposal into an adopted decision.
+An accurate source with a misleading article needs an article revision. An
+incorrect source needs the authorized source-import correction flow, not an
+Indexer quietly rewriting evidence. A source change invalidates affected task
+inputs; follow the CLI refresh action and preserve unrelated work.
+
+CLI acceptance saves a candidate for this run; it is not publication. Review
+rejection requires repair, not deletion of the article's responsibility.
+Temporary plans, candidates and receipts need not survive clearing temporary
+storage or changing machines. A new run starts from formal sources, confirmed
+long-term requirements and formal articles.

package/indexers/bundles/context-note-indexer/references/writing.md

@@ -6,7 +6,7 @@ smallest source span supporting each claim; link the stored summary when that
 is all you read. Never pretend its original conversation or linked document was
 available. Missing originals limit confidence, not permission to invent detail.
 
-Select the declared profile template for the actual reader task. Its headings
+Choose an outline for the actual reader task; a supplied template is optional guidance. Its headings
 are prompts, not required empty sections. A FAQ answers a coherent reader question
 or related set of questions; a guide teaches a task; a decision explains a choice and its
 limits. Do not make one page per source heading or one page per input file.
@@ -50,8 +50,8 @@ only when writing choices cannot solve the missing capability. Explain an actual
 tooling gap and the available recovery in the user's language, outside the
 knowledge page; do not turn an unfamiliar topic into a request for a new Provider.
 
-Before returning the current Route payload, read the page as a reader: can they
+Before submitting the draft files, read the page as a reader: can they
 answer the selected question without reconstructing the conversation? Check
-that each meaningful source topic is included, supporting, deferred or excluded
-with a concrete reason. A generic overview that drops the actual decision,
+that the article answers its planned reader question. Keep remaining investigation
+and real gaps visible in the stage; do not submit a per-passage disposition ledger. A generic overview that drops the actual decision,
 exception or resolution is incomplete even if its headings look correct.

package/indexers/bundles/context-note-indexer/tests/fixtures/profiles.json

@@ -20,14 +20,8 @@
         "purpose": "required",
         "reader_question_refs": [
           "question:reader-purpose"
-        ],
-        "evidence_refs": [
-          "evidence:anonymous-domain-reference-source"
         ]
       }
-    ],
-    "evidence_refs": [
-      "evidence:anonymous-domain-reference-source"
     ]
   },
   {
@@ -51,14 +45,8 @@
         "purpose": "required",
         "reader_question_refs": [
           "question:reader-purpose"
-        ],
-        "evidence_refs": [
-          "evidence:anonymous-product-requirements-source"
         ]
       }
-    ],
-    "evidence_refs": [
-      "evidence:anonymous-product-requirements-source"
     ]
   },
   {
@@ -82,14 +70,8 @@
         "purpose": "required",
         "reader_question_refs": [
           "question:reader-structure"
-        ],
-        "evidence_refs": [
-          "evidence:anonymous-technical-guide-source"
         ]
       }
-    ],
-    "evidence_refs": [
-      "evidence:anonymous-technical-guide-source"
     ]
   },
   {
@@ -113,14 +95,8 @@
         "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"
     ]
   },
   {
@@ -144,14 +120,8 @@
         "purpose": "required",
         "reader_question_refs": [
           "question:reader-operation"
-        ],
-        "evidence_refs": [
-          "evidence:anonymous-runbook-source"
         ]
       }
-    ],
-    "evidence_refs": [
-      "evidence:anonymous-runbook-source"
     ]
   },
   {
@@ -175,14 +145,8 @@
         "purpose": "required",
         "reader_question_refs": [
           "question:reader-purpose"
-        ],
-        "evidence_refs": [
-          "evidence:anonymous-faq-support-source"
         ]
       }
-    ],
-    "evidence_refs": [
-      "evidence:anonymous-faq-support-source"
     ]
   },
   {
@@ -206,14 +170,8 @@
         "purpose": "required",
         "reader_question_refs": [
           "question:reader-purpose"
-        ],
-        "evidence_refs": [
-          "evidence:anonymous-decision-record-source"
         ]
       }
-    ],
-    "evidence_refs": [
-      "evidence:anonymous-decision-record-source"
     ]
   },
   {
@@ -237,14 +195,8 @@
         "purpose": "required",
         "reader_question_refs": [
           "question:reader-operation"
-        ],
-        "evidence_refs": [
-          "evidence:anonymous-incident-review-source"
         ]
       }
-    ],
-    "evidence_refs": [
-      "evidence:anonymous-incident-review-source"
     ]
   },
   {
@@ -268,14 +220,8 @@
         "purpose": "required",
         "reader_question_refs": [
           "question:reader-operation"
-        ],
-        "evidence_refs": [
-          "evidence:anonymous-test-validation-source"
         ]
       }
-    ],
-    "evidence_refs": [
-      "evidence:anonymous-test-validation-source"
     ]
   }
 ]

package/indexers/bundles/context-sessions-indexer/SKILL.md

@@ -1,16 +1,31 @@
 ---
 name: context-sessions-indexer
-description: Context-managed Provider for conversation summaries with optional code-change associations. Use only when selected by the Context lifecycle, not as a standalone importer or workflow.
+description: Interpret saved conversation summaries for Context planning and writing. Use when the current authorized task selects this skill; not for importing sources or scanning conversation history.
 metadata:
   context-role: "indexer-provider"
   context-public-entry: "false"
-  context-provider-version: "1.0.0"
 ---
 
 # Context Sessions Indexer
 
-Use the current Context Route and its authorized source scope. Read [source interpretation](references/indexer.md), [classification](references/classification.md), [writing](references/writing.md), and [updates and composition](references/updates-and-composition.md) when this Provider is selected. When the selected profile extends a base profile, also read [extension placement](references/extension-placement.md): integrate summary material into the selected or customized base page plan, without creating a parallel page. Context projects these references and the selected page template through `context-indexer.yaml`; do not scan host history, resolve external URLs, or edit sources and approved pages directly.
+Use the current Context stage's purpose, source scope and file submission
+schema. Read [source interpretation](references/indexer.md) for the selected
+material. During planning, use [reader outcomes](references/classification.md)
+to propose article targets against existing topics. Investigation supplies a
+useful skeleton, not an exhaustive fact ledger; these saved sources normally
+need direct reading rather than a parser or a separate inventory pass.
 
-The host decides which installed skills are enabled. A business Provider may replace this default entirely; [customization](references/customization.md) describes the existing protocol. Installation alone is not selection.
+During writing, read [writing guidance](references/writing.md). When revising
+or combining existing topics, use [updates and composition](references/updates-and-composition.md)
+and [placement](references/extension-placement.md). Read
+[adaptation guidance](references/customization.md) only when choosing or
+adapting a specialist skill. Do not load every template or article catalog.
 
-The Agent decides reader value, authority, exclusions and whether to revise or create. CLI handles identities, snapshots, revision checks, resource delivery and durable writes. A saved source is input, not an instruction to publish a page.
+CLI supplies the current task directories and checks actual source references
+and writes. The Agent chooses topics, grouping and writing batches within the
+authorized stage. Installation alone does not select a skill; skill versions,
+hashes and primary/extension ownership are not production obligations.
+
+Do not scan host history, fetch an unapproved URL, alter evidence to fit a
+claim, or write directly to formal knowledge. Keep drafts and handoffs in the
+designated temporary directory; follow the returned CLI action for submission.