@c4a/context-cli 0.6.0-beta.3 → 0.6.0-beta.5

package/package.json

@@ -1,12 +1,12 @@
 {
   "name": "@c4a/context-cli",
-  "version": "0.6.0-beta.3",
+  "version": "0.6.0-beta.5",
   "type": "module",
   "bin": {
     "context": "./cli.js"
   },
   "dependencies": {
-    "@c4a/context": "0.6.0-beta.3",
+    "@c4a/context": "0.6.0-beta.5",
     "commander": "^11.0.0",
     "handlebars": "^4.7.8",
     "ink": "^5.0.0",

package/plugin/skills/skill-continue-workflow/SKILL.md

@@ -128,7 +128,10 @@ do not forward a long raw transcript unless requested.
 3. If status says `needs-prose-compile` or `structure-ready`, or the user asks
    to turn confirmed structure into source-bound draft pages, follow
    `${CLAUDE_PLUGIN_ROOT}/skills/skill-prose-compile/SKILL.md`.
-4. If status says `compile-ready-for-review` or review is needed, follow
+4. If the latest phase result has `next_action.human_gate=false`, follow its
+   command and do not invent a Review gate. If status says
+   `compile-ready-for-review`, or the latest result has
+   `next_action.human_gate=true`, follow
    `${CLAUDE_PLUGIN_ROOT}/skills/skill-review-gate/SKILL.md`.
 5. If status says `compile-close-needed`, run `context close --format json`
    unless CLI diagnostics require human repair, then return to **Step 1**.

package/plugin/skills/skill-review-gate/SKILL.md

@@ -16,6 +16,9 @@ Run the human review gate. The user decides approval or rejection.
 ## TL;DR
 
 - The agent never approves or rejects candidates on the user's behalf.
+- Enter this skill only when the preceding command returns
+  `next_action.human_gate=true`. A no-delta codegraph run returns false and does
+  not need Review.
 - Use `context review html <collection> --open` for visual review.
 - `<collection>` is an internal production collection such as `architecture`,
   `sop`, `decision`, or `standards`; it is not an OKF package root such as
@@ -29,6 +32,9 @@ Run the human review gate. The user decides approval or rejection.
   `context review approve <candidate-id> --collection <collection>` /
   `context review reject <candidate-id> --collection <collection>` or `--all`;
   these commands still enforce the current scoped candidate-id gate.
+- `context run <extract-phase-id> --auto-promote` is a separate, explicit
+  codegraph-only CI/CD policy. It may apply code add/update/remove deltas and
+  verify them without this gate; it never applies to semantic knowledge.
 
 <procedures>
 

package/plugin/skills/skill-source-scope/SKILL.md

@@ -41,6 +41,16 @@ Choose and validate what may become draft knowledge.
   source.
 - `extractTs.include` filters files inside the selected source; it is not a
   package/module selector.
+- Do not ask users to add `exports`, `main`, `bin`, or a new entry file to the
+  source repository solely for extraction. Standard package entries are
+  auto-detected; non-standard API roots belong in Context-owned
+  `extractTs.entries`. When the confirmed scope is all declarations in matched
+  files, use `mode: "scan"` instead of inventing an entry.
+- Empty or undetected entries must return `NO_ENTRY_DETECTED`; never treat an
+  empty extraction as success. Configure `entries`, or choose scan mode only
+  when every matched file is the intended scope.
+- TypeScript extraction follows tsconfig/jsconfig `extends`, `baseUrl`, and
+  `paths`. Aliases such as `@/` do not require changes to the source repository.
 - Use `context source inspect <source-name> --format json` for module choices.
 - Before first real extraction, generate a no-write preview and show module
   counts plus `knowledgeTree` / `knowledgePathExamples` to the user. Use
@@ -364,8 +374,16 @@ show counts plus the planned `knowledge/` tree.
 Only after the user confirms this product-level scope, declare the chosen date
 source with `source("YYYYMMDD")`, add the TypeScript extraction phase, and add
 the human review phase. Use `include` only for a file-level filter within the
-chosen source boundary. Mention the internal API names only in code-change
-summaries, or when the user asks for implementation details.
+chosen source boundary. If the package has no standard detected entry, keep the
+source repository unchanged and ask whether its intended knowledge surface is:
+
+- a public API graph rooted at specific files — configure source-relative
+  `entries` that are also matched by `include`; or
+- all declarations in the matched files — configure `mode: "scan"`, which uses
+  no entries and includes internal symbols by default.
+
+Mention the internal API names only in code-change summaries, or when the user
+asks for implementation details.
 
 ### Step 5 — Show The Pre-extraction Preview
 
@@ -378,7 +396,8 @@ context run <extract-phase-id> --dry-run --format json
 Show the user:
 
 - resolved source and module/package list;
-- file, symbol, and candidate estimate counts;
+- discovered, AST-analyzed, skipped, symbol, relation, and candidate estimate
+  counts, including each skipped reason;
 - `knowledgeTree`;
 - several `knowledgePathExamples`.
 
@@ -412,6 +431,22 @@ matches it, run:
 context run <extract-phase-id>
 ```
 
+Read the structured result before routing. For codegraph, the first run returns
+all code candidates with `next_action.human_gate=true`; later runs return only
+added/updated/removed symbols, while unchanged approved symbols stay approved.
+If `next_action.human_gate=false`, do not open Review and continue with status.
+
+Only when the user explicitly requests a non-interactive CI/CD codegraph sync,
+run:
+
+```bash
+context run <extract-phase-id> --auto-promote --format json
+```
+
+This applies deterministic codegraph deltas and verifies them. A nonzero exit or
+verification issue is a pipeline failure. Never use `--auto-promote` for prose
+or semantic collections.
+
 If the preview reports modules outside the confirmed source boundary, do not
 run extraction. Ask the user to choose the corrected source boundary.
 

package/plugins/VERSION

@@ -1 +1 @@
-0.6.0-beta.3
+0.6.0-beta.5

package/plugins/claude/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "context",
   "description": "Maintain a project-local knowledge workspace through init and next-step agent guidance.",
-  "version": "0.6.0-beta.3",
+  "version": "0.6.0-beta.5",
   "author": {
     "name": "c4a"
   },

package/plugins/claude/skills/skill-continue-workflow/SKILL.md

@@ -128,7 +128,10 @@ do not forward a long raw transcript unless requested.
 3. If status says `needs-prose-compile` or `structure-ready`, or the user asks
    to turn confirmed structure into source-bound draft pages, follow
    `${CLAUDE_PLUGIN_ROOT}/skills/skill-prose-compile/SKILL.md`.
-4. If status says `compile-ready-for-review` or review is needed, follow
+4. If the latest phase result has `next_action.human_gate=false`, follow its
+   command and do not invent a Review gate. If status says
+   `compile-ready-for-review`, or the latest result has
+   `next_action.human_gate=true`, follow
    `${CLAUDE_PLUGIN_ROOT}/skills/skill-review-gate/SKILL.md`.
 5. If status says `compile-close-needed`, run `context close --format json`
    unless CLI diagnostics require human repair, then return to **Step 1**.

package/plugins/claude/skills/skill-review-gate/SKILL.md

@@ -16,6 +16,9 @@ Run the human review gate. The user decides approval or rejection.
 ## TL;DR
 
 - The agent never approves or rejects candidates on the user's behalf.
+- Enter this skill only when the preceding command returns
+  `next_action.human_gate=true`. A no-delta codegraph run returns false and does
+  not need Review.
 - Use `context review html <collection> --open` for visual review.
 - `<collection>` is an internal production collection such as `architecture`,
   `sop`, `decision`, or `standards`; it is not an OKF package root such as
@@ -29,6 +32,9 @@ Run the human review gate. The user decides approval or rejection.
   `context review approve <candidate-id> --collection <collection>` /
   `context review reject <candidate-id> --collection <collection>` or `--all`;
   these commands still enforce the current scoped candidate-id gate.
+- `context run <extract-phase-id> --auto-promote` is a separate, explicit
+  codegraph-only CI/CD policy. It may apply code add/update/remove deltas and
+  verify them without this gate; it never applies to semantic knowledge.
 
 <procedures>
 

package/plugins/claude/skills/skill-source-scope/SKILL.md

@@ -41,6 +41,16 @@ Choose and validate what may become draft knowledge.
   source.
 - `extractTs.include` filters files inside the selected source; it is not a
   package/module selector.
+- Do not ask users to add `exports`, `main`, `bin`, or a new entry file to the
+  source repository solely for extraction. Standard package entries are
+  auto-detected; non-standard API roots belong in Context-owned
+  `extractTs.entries`. When the confirmed scope is all declarations in matched
+  files, use `mode: "scan"` instead of inventing an entry.
+- Empty or undetected entries must return `NO_ENTRY_DETECTED`; never treat an
+  empty extraction as success. Configure `entries`, or choose scan mode only
+  when every matched file is the intended scope.
+- TypeScript extraction follows tsconfig/jsconfig `extends`, `baseUrl`, and
+  `paths`. Aliases such as `@/` do not require changes to the source repository.
 - Use `context source inspect <source-name> --format json` for module choices.
 - Before first real extraction, generate a no-write preview and show module
   counts plus `knowledgeTree` / `knowledgePathExamples` to the user. Use
@@ -364,8 +374,16 @@ show counts plus the planned `knowledge/` tree.
 Only after the user confirms this product-level scope, declare the chosen date
 source with `source("YYYYMMDD")`, add the TypeScript extraction phase, and add
 the human review phase. Use `include` only for a file-level filter within the
-chosen source boundary. Mention the internal API names only in code-change
-summaries, or when the user asks for implementation details.
+chosen source boundary. If the package has no standard detected entry, keep the
+source repository unchanged and ask whether its intended knowledge surface is:
+
+- a public API graph rooted at specific files — configure source-relative
+  `entries` that are also matched by `include`; or
+- all declarations in the matched files — configure `mode: "scan"`, which uses
+  no entries and includes internal symbols by default.
+
+Mention the internal API names only in code-change summaries, or when the user
+asks for implementation details.
 
 ### Step 5 — Show The Pre-extraction Preview
 
@@ -378,7 +396,8 @@ context run <extract-phase-id> --dry-run --format json
 Show the user:
 
 - resolved source and module/package list;
-- file, symbol, and candidate estimate counts;
+- discovered, AST-analyzed, skipped, symbol, relation, and candidate estimate
+  counts, including each skipped reason;
 - `knowledgeTree`;
 - several `knowledgePathExamples`.
 
@@ -412,6 +431,22 @@ matches it, run:
 context run <extract-phase-id>
 ```
 
+Read the structured result before routing. For codegraph, the first run returns
+all code candidates with `next_action.human_gate=true`; later runs return only
+added/updated/removed symbols, while unchanged approved symbols stay approved.
+If `next_action.human_gate=false`, do not open Review and continue with status.
+
+Only when the user explicitly requests a non-interactive CI/CD codegraph sync,
+run:
+
+```bash
+context run <extract-phase-id> --auto-promote --format json
+```
+
+This applies deterministic codegraph deltas and verifies them. A nonzero exit or
+verification issue is a pipeline failure. Never use `--auto-promote` for prose
+or semantic collections.
+
 If the preview reports modules outside the confirmed source boundary, do not
 run extraction. Ask the user to choose the corrected source boundary.
 

package/plugins/codex/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "context",
-  "version": "0.6.0-beta.3",
+  "version": "0.6.0-beta.5",
   "description": "Maintain a project-local knowledge workspace through init and next-step agent guidance.",
   "author": {
     "name": "c4a"
@@ -18,7 +18,7 @@
   "skills": "./skills/",
   "interface": {
     "displayName": "C4A Context",
-    "shortDescription": "Initialize and advance a local, source-linked project knowledge workspace.\nv0.6.0-beta.3",
+    "shortDescription": "Initialize and advance a local, source-linked project knowledge workspace.\nv0.6.0-beta.5",
     "longDescription": "Create a Context workspace and use agent-guided next steps to register sources, run extraction, review candidates, build package outputs, and verify health without silently mutating source repositories.",
     "developerName": "c4a",
     "category": "Productivity",

package/plugins/codex/skills/continue/references/internal-procedures/skill-continue-workflow.md

@@ -128,7 +128,10 @@ do not forward a long raw transcript unless requested.
 3. If status says `needs-prose-compile` or `structure-ready`, or the user asks
    to turn confirmed structure into source-bound draft pages, follow
    `skill-prose-compile.md`.
-4. If status says `compile-ready-for-review` or review is needed, follow
+4. If the latest phase result has `next_action.human_gate=false`, follow its
+   command and do not invent a Review gate. If status says
+   `compile-ready-for-review`, or the latest result has
+   `next_action.human_gate=true`, follow
    `skill-review-gate.md`.
 5. If status says `compile-close-needed`, run `context close --format json`
    unless CLI diagnostics require human repair, then return to **Step 1**.

package/plugins/codex/skills/continue/references/internal-procedures/skill-review-gate.md

@@ -16,6 +16,9 @@ Run the human review gate. The user decides approval or rejection.
 ## TL;DR
 
 - The agent never approves or rejects candidates on the user's behalf.
+- Enter this skill only when the preceding command returns
+  `next_action.human_gate=true`. A no-delta codegraph run returns false and does
+  not need Review.
 - Use `context review html <collection> --open` for visual review.
 - `<collection>` is an internal production collection such as `architecture`,
   `sop`, `decision`, or `standards`; it is not an OKF package root such as
@@ -29,6 +32,9 @@ Run the human review gate. The user decides approval or rejection.
   `context review approve <candidate-id> --collection <collection>` /
   `context review reject <candidate-id> --collection <collection>` or `--all`;
   these commands still enforce the current scoped candidate-id gate.
+- `context run <extract-phase-id> --auto-promote` is a separate, explicit
+  codegraph-only CI/CD policy. It may apply code add/update/remove deltas and
+  verify them without this gate; it never applies to semantic knowledge.
 
 <procedures>
 

package/plugins/codex/skills/continue/references/internal-procedures/skill-source-scope.md

@@ -41,6 +41,16 @@ Choose and validate what may become draft knowledge.
   source.
 - `extractTs.include` filters files inside the selected source; it is not a
   package/module selector.
+- Do not ask users to add `exports`, `main`, `bin`, or a new entry file to the
+  source repository solely for extraction. Standard package entries are
+  auto-detected; non-standard API roots belong in Context-owned
+  `extractTs.entries`. When the confirmed scope is all declarations in matched
+  files, use `mode: "scan"` instead of inventing an entry.
+- Empty or undetected entries must return `NO_ENTRY_DETECTED`; never treat an
+  empty extraction as success. Configure `entries`, or choose scan mode only
+  when every matched file is the intended scope.
+- TypeScript extraction follows tsconfig/jsconfig `extends`, `baseUrl`, and
+  `paths`. Aliases such as `@/` do not require changes to the source repository.
 - Use `context source inspect <source-name> --format json` for module choices.
 - Before first real extraction, generate a no-write preview and show module
   counts plus `knowledgeTree` / `knowledgePathExamples` to the user. Use
@@ -364,8 +374,16 @@ show counts plus the planned `knowledge/` tree.
 Only after the user confirms this product-level scope, declare the chosen date
 source with `source("YYYYMMDD")`, add the TypeScript extraction phase, and add
 the human review phase. Use `include` only for a file-level filter within the
-chosen source boundary. Mention the internal API names only in code-change
-summaries, or when the user asks for implementation details.
+chosen source boundary. If the package has no standard detected entry, keep the
+source repository unchanged and ask whether its intended knowledge surface is:
+
+- a public API graph rooted at specific files — configure source-relative
+  `entries` that are also matched by `include`; or
+- all declarations in the matched files — configure `mode: "scan"`, which uses
+  no entries and includes internal symbols by default.
+
+Mention the internal API names only in code-change summaries, or when the user
+asks for implementation details.
 
 ### Step 5 — Show The Pre-extraction Preview
 
@@ -378,7 +396,8 @@ context run <extract-phase-id> --dry-run --format json
 Show the user:
 
 - resolved source and module/package list;
-- file, symbol, and candidate estimate counts;
+- discovered, AST-analyzed, skipped, symbol, relation, and candidate estimate
+  counts, including each skipped reason;
 - `knowledgeTree`;
 - several `knowledgePathExamples`.
 
@@ -412,6 +431,22 @@ matches it, run:
 context run <extract-phase-id>
 ```
 
+Read the structured result before routing. For codegraph, the first run returns
+all code candidates with `next_action.human_gate=true`; later runs return only
+added/updated/removed symbols, while unchanged approved symbols stay approved.
+If `next_action.human_gate=false`, do not open Review and continue with status.
+
+Only when the user explicitly requests a non-interactive CI/CD codegraph sync,
+run:
+
+```bash
+context run <extract-phase-id> --auto-promote --format json
+```
+
+This applies deterministic codegraph deltas and verifies them. A nonzero exit or
+verification issue is a pipeline failure. Never use `--auto-promote` for prose
+or semantic collections.
+
 If the preview reports modules outside the confirmed source boundary, do not
 run extraction. Ask the user to choose the corrected source boundary.
 

package/plugins/codex/skills/init/references/internal-procedures/skill-continue-workflow.md

@@ -128,7 +128,10 @@ do not forward a long raw transcript unless requested.
 3. If status says `needs-prose-compile` or `structure-ready`, or the user asks
    to turn confirmed structure into source-bound draft pages, follow
    `skill-prose-compile.md`.
-4. If status says `compile-ready-for-review` or review is needed, follow
+4. If the latest phase result has `next_action.human_gate=false`, follow its
+   command and do not invent a Review gate. If status says
+   `compile-ready-for-review`, or the latest result has
+   `next_action.human_gate=true`, follow
    `skill-review-gate.md`.
 5. If status says `compile-close-needed`, run `context close --format json`
    unless CLI diagnostics require human repair, then return to **Step 1**.

package/plugins/codex/skills/init/references/internal-procedures/skill-review-gate.md

@@ -16,6 +16,9 @@ Run the human review gate. The user decides approval or rejection.
 ## TL;DR
 
 - The agent never approves or rejects candidates on the user's behalf.
+- Enter this skill only when the preceding command returns
+  `next_action.human_gate=true`. A no-delta codegraph run returns false and does
+  not need Review.
 - Use `context review html <collection> --open` for visual review.
 - `<collection>` is an internal production collection such as `architecture`,
   `sop`, `decision`, or `standards`; it is not an OKF package root such as
@@ -29,6 +32,9 @@ Run the human review gate. The user decides approval or rejection.
   `context review approve <candidate-id> --collection <collection>` /
   `context review reject <candidate-id> --collection <collection>` or `--all`;
   these commands still enforce the current scoped candidate-id gate.
+- `context run <extract-phase-id> --auto-promote` is a separate, explicit
+  codegraph-only CI/CD policy. It may apply code add/update/remove deltas and
+  verify them without this gate; it never applies to semantic knowledge.
 
 <procedures>
 

package/plugins/codex/skills/init/references/internal-procedures/skill-source-scope.md

@@ -41,6 +41,16 @@ Choose and validate what may become draft knowledge.
   source.
 - `extractTs.include` filters files inside the selected source; it is not a
   package/module selector.
+- Do not ask users to add `exports`, `main`, `bin`, or a new entry file to the
+  source repository solely for extraction. Standard package entries are
+  auto-detected; non-standard API roots belong in Context-owned
+  `extractTs.entries`. When the confirmed scope is all declarations in matched
+  files, use `mode: "scan"` instead of inventing an entry.
+- Empty or undetected entries must return `NO_ENTRY_DETECTED`; never treat an
+  empty extraction as success. Configure `entries`, or choose scan mode only
+  when every matched file is the intended scope.
+- TypeScript extraction follows tsconfig/jsconfig `extends`, `baseUrl`, and
+  `paths`. Aliases such as `@/` do not require changes to the source repository.
 - Use `context source inspect <source-name> --format json` for module choices.
 - Before first real extraction, generate a no-write preview and show module
   counts plus `knowledgeTree` / `knowledgePathExamples` to the user. Use
@@ -364,8 +374,16 @@ show counts plus the planned `knowledge/` tree.
 Only after the user confirms this product-level scope, declare the chosen date
 source with `source("YYYYMMDD")`, add the TypeScript extraction phase, and add
 the human review phase. Use `include` only for a file-level filter within the
-chosen source boundary. Mention the internal API names only in code-change
-summaries, or when the user asks for implementation details.
+chosen source boundary. If the package has no standard detected entry, keep the
+source repository unchanged and ask whether its intended knowledge surface is:
+
+- a public API graph rooted at specific files — configure source-relative
+  `entries` that are also matched by `include`; or
+- all declarations in the matched files — configure `mode: "scan"`, which uses
+  no entries and includes internal symbols by default.
+
+Mention the internal API names only in code-change summaries, or when the user
+asks for implementation details.
 
 ### Step 5 — Show The Pre-extraction Preview
 
@@ -378,7 +396,8 @@ context run <extract-phase-id> --dry-run --format json
 Show the user:
 
 - resolved source and module/package list;
-- file, symbol, and candidate estimate counts;
+- discovered, AST-analyzed, skipped, symbol, relation, and candidate estimate
+  counts, including each skipped reason;
 - `knowledgeTree`;
 - several `knowledgePathExamples`.
 
@@ -412,6 +431,22 @@ matches it, run:
 context run <extract-phase-id>
 ```
 
+Read the structured result before routing. For codegraph, the first run returns
+all code candidates with `next_action.human_gate=true`; later runs return only
+added/updated/removed symbols, while unchanged approved symbols stay approved.
+If `next_action.human_gate=false`, do not open Review and continue with status.
+
+Only when the user explicitly requests a non-interactive CI/CD codegraph sync,
+run:
+
+```bash
+context run <extract-phase-id> --auto-promote --format json
+```
+
+This applies deterministic codegraph deltas and verifies them. A nonzero exit or
+verification issue is a pipeline failure. Never use `--auto-promote` for prose
+or semantic collections.
+
 If the preview reports modules outside the confirmed source boundary, do not
 run extraction. Ask the user to choose the corrected source boundary.
 

package/plugins/cursor/.cursor-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "context",
   "displayName": "C4A Context",
-  "version": "0.6.0-beta.3",
+  "version": "0.6.0-beta.5",
   "description": "Maintain a project-local knowledge workspace through init and next-step agent guidance.",
   "author": {
     "name": "Context4AI",

package/plugins/cursor/skills/skill-continue-workflow/SKILL.md

@@ -128,7 +128,10 @@ do not forward a long raw transcript unless requested.
 3. If status says `needs-prose-compile` or `structure-ready`, or the user asks
    to turn confirmed structure into source-bound draft pages, follow
    `../skill-prose-compile/SKILL.md`.
-4. If status says `compile-ready-for-review` or review is needed, follow
+4. If the latest phase result has `next_action.human_gate=false`, follow its
+   command and do not invent a Review gate. If status says
+   `compile-ready-for-review`, or the latest result has
+   `next_action.human_gate=true`, follow
    `../skill-review-gate/SKILL.md`.
 5. If status says `compile-close-needed`, run `context close --format json`
    unless CLI diagnostics require human repair, then return to **Step 1**.

package/plugins/cursor/skills/skill-review-gate/SKILL.md

@@ -16,6 +16,9 @@ Run the human review gate. The user decides approval or rejection.
 ## TL;DR
 
 - The agent never approves or rejects candidates on the user's behalf.
+- Enter this skill only when the preceding command returns
+  `next_action.human_gate=true`. A no-delta codegraph run returns false and does
+  not need Review.
 - Use `context review html <collection> --open` for visual review.
 - `<collection>` is an internal production collection such as `architecture`,
   `sop`, `decision`, or `standards`; it is not an OKF package root such as
@@ -29,6 +32,9 @@ Run the human review gate. The user decides approval or rejection.
   `context review approve <candidate-id> --collection <collection>` /
   `context review reject <candidate-id> --collection <collection>` or `--all`;
   these commands still enforce the current scoped candidate-id gate.
+- `context run <extract-phase-id> --auto-promote` is a separate, explicit
+  codegraph-only CI/CD policy. It may apply code add/update/remove deltas and
+  verify them without this gate; it never applies to semantic knowledge.
 
 <procedures>
 

package/plugins/cursor/skills/skill-source-scope/SKILL.md

@@ -41,6 +41,16 @@ Choose and validate what may become draft knowledge.
   source.
 - `extractTs.include` filters files inside the selected source; it is not a
   package/module selector.
+- Do not ask users to add `exports`, `main`, `bin`, or a new entry file to the
+  source repository solely for extraction. Standard package entries are
+  auto-detected; non-standard API roots belong in Context-owned
+  `extractTs.entries`. When the confirmed scope is all declarations in matched
+  files, use `mode: "scan"` instead of inventing an entry.
+- Empty or undetected entries must return `NO_ENTRY_DETECTED`; never treat an
+  empty extraction as success. Configure `entries`, or choose scan mode only
+  when every matched file is the intended scope.
+- TypeScript extraction follows tsconfig/jsconfig `extends`, `baseUrl`, and
+  `paths`. Aliases such as `@/` do not require changes to the source repository.
 - Use `context source inspect <source-name> --format json` for module choices.
 - Before first real extraction, generate a no-write preview and show module
   counts plus `knowledgeTree` / `knowledgePathExamples` to the user. Use
@@ -364,8 +374,16 @@ show counts plus the planned `knowledge/` tree.
 Only after the user confirms this product-level scope, declare the chosen date
 source with `source("YYYYMMDD")`, add the TypeScript extraction phase, and add
 the human review phase. Use `include` only for a file-level filter within the
-chosen source boundary. Mention the internal API names only in code-change
-summaries, or when the user asks for implementation details.
+chosen source boundary. If the package has no standard detected entry, keep the
+source repository unchanged and ask whether its intended knowledge surface is:
+
+- a public API graph rooted at specific files — configure source-relative
+  `entries` that are also matched by `include`; or
+- all declarations in the matched files — configure `mode: "scan"`, which uses
+  no entries and includes internal symbols by default.
+
+Mention the internal API names only in code-change summaries, or when the user
+asks for implementation details.
 
 ### Step 5 — Show The Pre-extraction Preview
 
@@ -378,7 +396,8 @@ context run <extract-phase-id> --dry-run --format json
 Show the user:
 
 - resolved source and module/package list;
-- file, symbol, and candidate estimate counts;
+- discovered, AST-analyzed, skipped, symbol, relation, and candidate estimate
+  counts, including each skipped reason;
 - `knowledgeTree`;
 - several `knowledgePathExamples`.
 
@@ -412,6 +431,22 @@ matches it, run:
 context run <extract-phase-id>
 ```
 
+Read the structured result before routing. For codegraph, the first run returns
+all code candidates with `next_action.human_gate=true`; later runs return only
+added/updated/removed symbols, while unchanged approved symbols stay approved.
+If `next_action.human_gate=false`, do not open Review and continue with status.
+
+Only when the user explicitly requests a non-interactive CI/CD codegraph sync,
+run:
+
+```bash
+context run <extract-phase-id> --auto-promote --format json
+```
+
+This applies deterministic codegraph deltas and verifies them. A nonzero exit or
+verification issue is a pipeline failure. Never use `--auto-promote` for prose
+or semantic collections.
+
 If the preview reports modules outside the confirmed source boundary, do not
 run extraction. Ask the user to choose the corrected source boundary.
 

package/plugins/skills/context-continue/references/internal-procedures/skill-continue-workflow.md

@@ -128,7 +128,10 @@ do not forward a long raw transcript unless requested.
 3. If status says `needs-prose-compile` or `structure-ready`, or the user asks
    to turn confirmed structure into source-bound draft pages, follow
    `skill-prose-compile.md`.
-4. If status says `compile-ready-for-review` or review is needed, follow
+4. If the latest phase result has `next_action.human_gate=false`, follow its
+   command and do not invent a Review gate. If status says
+   `compile-ready-for-review`, or the latest result has
+   `next_action.human_gate=true`, follow
    `skill-review-gate.md`.
 5. If status says `compile-close-needed`, run `context close --format json`
    unless CLI diagnostics require human repair, then return to **Step 1**.

package/plugins/skills/context-continue/references/internal-procedures/skill-review-gate.md

@@ -16,6 +16,9 @@ Run the human review gate. The user decides approval or rejection.
 ## TL;DR
 
 - The agent never approves or rejects candidates on the user's behalf.
+- Enter this skill only when the preceding command returns
+  `next_action.human_gate=true`. A no-delta codegraph run returns false and does
+  not need Review.
 - Use `context review html <collection> --open` for visual review.
 - `<collection>` is an internal production collection such as `architecture`,
   `sop`, `decision`, or `standards`; it is not an OKF package root such as
@@ -29,6 +32,9 @@ Run the human review gate. The user decides approval or rejection.
   `context review approve <candidate-id> --collection <collection>` /
   `context review reject <candidate-id> --collection <collection>` or `--all`;
   these commands still enforce the current scoped candidate-id gate.
+- `context run <extract-phase-id> --auto-promote` is a separate, explicit
+  codegraph-only CI/CD policy. It may apply code add/update/remove deltas and
+  verify them without this gate; it never applies to semantic knowledge.
 
 <procedures>