@c4a/context-cli 0.6.1-beta.1 → 0.6.1-beta.2

package/plugins/codex/skills/init/SKILL.md

@@ -13,22 +13,30 @@ Public Context entry for agents that expose skills instead of slash commands.
 - Public entry: `init`
 - Host command names are installation-specific; use the command or skill surfaced by the current host instead of deriving a filesystem path from an example name.
 - CLI primitive prefix: `context ...`
-- Internal procedures live under `references/internal-procedures/`; read each referenced file in full before following that step.
 
 ---
 
 ## Workflow
 
-Initialize a Context workspace with the global CLI, then continue only through
-safe mechanical setup steps until the first human decision gate.
+Initialize a Context workspace with the global CLI, complete the returned setup
+step, then hand control to the current workflow route.
 
 Language policy: explain, ask, confirm, and summarize in the user's current
 conversation language. Keep CLI commands, flags, file paths, package names,
 enum values, payload keys, and copied CLI output tokens unchanged.
 
-Use the procedure in `references/internal-procedures/skill-init-workspace.md` end to end. It owns
-the `context init` invocation, dependency install follow-up, generated
-`AGENTS.md` handoff, status handoff, and stop conditions.
+Run `context init [project-dir] [--name <name>]` with only the arguments the
+user supplied. Execute the setup command returned by init, enter the project
+root, and read its generated `AGENTS.md`. Use `--dev` only when the user
+explicitly asked to test a locally linked Context SDK.
+
+Then run `context status --format json`, or `context status --managed --format
+json` only when the user explicitly requested fully managed operation in this
+conversation. While that request remains active, use `--managed` for every
+status evaluation; never persist it into another conversation. Treat
+`workflow.current` as the current-step authority: read every required resource,
+execute only its exact commands, stop before any unresolved command marked
+`after-human-confirmation`, and rerun status after each action.
 
 Do not add extra project-local agent setup. Do not infer repo sources or
 extraction scope from the surrounding monorepo after setup.

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

@@ -1,7 +1,7 @@
 {
   "name": "context",
   "displayName": "C4A Context",
-  "version": "0.6.1-beta.1",
+  "version": "0.6.1-beta.2",
   "description": "Maintain a project-local knowledge workspace through init and next-step agent guidance.",
   "author": {
     "name": "Context4AI",
@@ -24,6 +24,5 @@
     "agent-skills",
     "citations"
   ],
-  "commands": "./commands/",
-  "skills": "./skills/"
+  "commands": "./commands/"
 }

package/plugins/cursor/README.md

@@ -6,8 +6,8 @@ Edit `packages/context-cli/plugin/` and rerun the build instead.
 
 Install shape:
 
-- Marketplace/GitHub plugin shape: this directory is a plugin root with `.cursor-plugin/plugin.json`, `commands/`, and `skills/`.
+- Marketplace/GitHub plugin shape: this directory is a plugin root with `.cursor-plugin/plugin.json` and `commands/`.
 - User entries are under `commands/`; Cursor command files are prefixed as `context-*` to avoid global slash-command collisions.
 - Local plugin fallback: symlink or copy this directory to `~/.cursor/plugins/local/context/` only when Marketplace import is unavailable.
 
-Do not copy these files into `.cursor/skills/` as the main install path. Cursor Marketplace installs this plugin root directly.
+Cursor Marketplace installs this plugin root directly.

package/plugins/cursor/commands/context-continue.md

@@ -10,27 +10,44 @@ Continue the Context workflow from the current workspace state.
 
 ## Workflow
 
-Use this as the conversational entry for an existing Context workspace. There is
-no `context continue` CLI primitive; the command runs lower-level `context ...`
-commands only when the workspace state requires them.
+Use this as the conversational entry for an existing Context workspace. There
+is no `context continue` CLI primitive. Start with:
+
+```bash
+context status --format json
+```
+
+Use `context status --managed --format json` only when the user explicitly
+requested fully managed operation in this conversation. Never persist or reuse
+that authority in another conversation. While the request remains active, use
+`--managed` for every status evaluation; stop using it when the conversation
+ends or the user revokes it.
 
 If the user is starting a new workspace or a new batch from a raw repository
 root, do not run `context status` first. Use the public Context init entry or
 `context init` to create the workspace, complete the init setup command, then
 return here from the initialized workspace.
 
-If `context status` reports `workspace-not-found` and points at a configured
-`context.workspaceDir`, do not keep working from the host repository root. Enter
-that workspace when it exists, or initialize it through the init workflow after
-confirming with the user.
-
 Language policy: explain, ask, confirm, and summarize in the user's current
 conversation language. Keep CLI commands, flags, paths, ids, status enum values,
 JSONL payload keys, `source_ref` values, and copied CLI output tokens unchanged.
 
-Use the procedure in `../skills/skill-continue-workflow/SKILL.md` end to end. It owns the
-status loop, safe mechanical next steps, source/scope gate, review gate, package
-gate, and final report rules.
+Treat `workflow.current` as the current-step authority:
+
+1. Read every `resources.required` item. Read a `path` directly; for a resource
+   with `command`, execute that command and read the returned file.
+2. At a Gate, keep conditional context phase-local. An `inspection_action`
+   Skill or Schema is read only when performing that pre-decision inspection;
+   a `resolution_action` Skill or Schema is read only after the user confirms
+   the Gate. Neither replaces ordinary `resources.required`.
+3. Execute only `commands` returned by the Route, preserving revision and
+   authority flags exactly. A command marked `after-human-confirmation` must
+   wait for the current Gate decision.
+4. If `configuration` is present, edit only the named project file using the
+   selected resources as its contract.
+5. After every action or configuration change, run status again. A phase-local
+   `next_action` can continue that operation but never replaces the workspace
+   Route.
 
 Do not infer repo sources, extraction scope, review decisions, or package output
 choices from surrounding files. Do not call source-repo operations such as

package/plugins/cursor/commands/context-init.md

@@ -10,16 +10,25 @@ Initialize a Context knowledge workspace.
 
 ## Workflow
 
-Initialize a Context workspace with the global CLI, then continue only through
-safe mechanical setup steps until the first human decision gate.
+Initialize a Context workspace with the global CLI, complete the returned setup
+step, then hand control to the current workflow route.
 
 Language policy: explain, ask, confirm, and summarize in the user's current
 conversation language. Keep CLI commands, flags, file paths, package names,
 enum values, payload keys, and copied CLI output tokens unchanged.
 
-Use the procedure in `../skills/skill-init-workspace/SKILL.md` end to end. It owns
-the `context init` invocation, dependency install follow-up, generated
-`AGENTS.md` handoff, status handoff, and stop conditions.
+Run `context init [project-dir] [--name <name>]` with only the arguments the
+user supplied. Execute the setup command returned by init, enter the project
+root, and read its generated `AGENTS.md`. Use `--dev` only when the user
+explicitly asked to test a locally linked Context SDK.
+
+Then run `context status --format json`, or `context status --managed --format
+json` only when the user explicitly requested fully managed operation in this
+conversation. While that request remains active, use `--managed` for every
+status evaluation; never persist it into another conversation. Treat
+`workflow.current` as the current-step authority: read every required resource,
+execute only its exact commands, stop before any unresolved command marked
+`after-human-confirmation`, and rerun status after each action.
 
 Do not add extra project-local agent setup. Do not infer repo sources or
 extraction scope from the surrounding monorepo after setup.

package/plugins/skills/context-continue/SKILL.md

@@ -13,33 +13,49 @@ Public Context entry for agents that expose skills instead of slash commands.
 - Public entry: `context-continue`
 - Host command names are installation-specific; use the command or skill surfaced by the current host instead of deriving a filesystem path from an example name.
 - CLI primitive prefix: `context ...`
-- Internal procedures live under `references/internal-procedures/`; read each referenced file in full before following that step.
 
 ---
 
 ## Workflow
 
-Use this as the conversational entry for an existing Context workspace. There is
-no `context continue` CLI primitive; the command runs lower-level `context ...`
-commands only when the workspace state requires them.
+Use this as the conversational entry for an existing Context workspace. There
+is no `context continue` CLI primitive. Start with:
+
+```bash
+context status --format json
+```
+
+Use `context status --managed --format json` only when the user explicitly
+requested fully managed operation in this conversation. Never persist or reuse
+that authority in another conversation. While the request remains active, use
+`--managed` for every status evaluation; stop using it when the conversation
+ends or the user revokes it.
 
 If the user is starting a new workspace or a new batch from a raw repository
 root, do not run `context status` first. Use the public Context init entry or
 `context init` to create the workspace, complete the init setup command, then
 return here from the initialized workspace.
 
-If `context status` reports `workspace-not-found` and points at a configured
-`context.workspaceDir`, do not keep working from the host repository root. Enter
-that workspace when it exists, or initialize it through the init workflow after
-confirming with the user.
-
 Language policy: explain, ask, confirm, and summarize in the user's current
 conversation language. Keep CLI commands, flags, paths, ids, status enum values,
 JSONL payload keys, `source_ref` values, and copied CLI output tokens unchanged.
 
-Use the procedure in `references/internal-procedures/skill-continue-workflow.md` end to end. It owns the
-status loop, safe mechanical next steps, source/scope gate, review gate, package
-gate, and final report rules.
+Treat `workflow.current` as the current-step authority:
+
+1. Read every `resources.required` item. Read a `path` directly; for a resource
+   with `command`, execute that command and read the returned file.
+2. At a Gate, keep conditional context phase-local. An `inspection_action`
+   Skill or Schema is read only when performing that pre-decision inspection;
+   a `resolution_action` Skill or Schema is read only after the user confirms
+   the Gate. Neither replaces ordinary `resources.required`.
+3. Execute only `commands` returned by the Route, preserving revision and
+   authority flags exactly. A command marked `after-human-confirmation` must
+   wait for the current Gate decision.
+4. If `configuration` is present, edit only the named project file using the
+   selected resources as its contract.
+5. After every action or configuration change, run status again. A phase-local
+   `next_action` can continue that operation but never replaces the workspace
+   Route.
 
 Do not infer repo sources, extraction scope, review decisions, or package output
 choices from surrounding files. Do not call source-repo operations such as

package/plugins/skills/context-init/SKILL.md

@@ -13,22 +13,30 @@ Public Context entry for agents that expose skills instead of slash commands.
 - Public entry: `context-init`
 - Host command names are installation-specific; use the command or skill surfaced by the current host instead of deriving a filesystem path from an example name.
 - CLI primitive prefix: `context ...`
-- Internal procedures live under `references/internal-procedures/`; read each referenced file in full before following that step.
 
 ---
 
 ## Workflow
 
-Initialize a Context workspace with the global CLI, then continue only through
-safe mechanical setup steps until the first human decision gate.
+Initialize a Context workspace with the global CLI, complete the returned setup
+step, then hand control to the current workflow route.
 
 Language policy: explain, ask, confirm, and summarize in the user's current
 conversation language. Keep CLI commands, flags, file paths, package names,
 enum values, payload keys, and copied CLI output tokens unchanged.
 
-Use the procedure in `references/internal-procedures/skill-init-workspace.md` end to end. It owns
-the `context init` invocation, dependency install follow-up, generated
-`AGENTS.md` handoff, status handoff, and stop conditions.
+Run `context init [project-dir] [--name <name>]` with only the arguments the
+user supplied. Execute the setup command returned by init, enter the project
+root, and read its generated `AGENTS.md`. Use `--dev` only when the user
+explicitly asked to test a locally linked Context SDK.
+
+Then run `context status --format json`, or `context status --managed --format
+json` only when the user explicitly requested fully managed operation in this
+conversation. While that request remains active, use `--managed` for every
+status evaluation; never persist it into another conversation. Treat
+`workflow.current` as the current-step authority: read every required resource,
+execute only its exact commands, stop before any unresolved command marked
+`after-human-confirmation`, and rerun status after each action.
 
 Do not add extra project-local agent setup. Do not infer repo sources or
 extraction scope from the surrounding monorepo after setup.

package/providers/context/actions/align-next.yaml

@@ -0,0 +1,6 @@
+schema: agent-graph.action.v1
+id: align-next
+runner: host
+effect: write
+handler: context.align.next
+

package/providers/context/actions/apply-managed-review.yaml

@@ -0,0 +1,6 @@
+schema: agent-graph.action.v1
+id: apply-managed-review
+runner: host
+effect: write
+handler: context.review.approve-current
+

package/providers/context/actions/apply-structure-confirmation.yaml

@@ -0,0 +1,6 @@
+schema: agent-graph.action.v1
+id: apply-structure-confirmation
+runner: host
+effect: write
+handler: context.structure.confirm
+

package/providers/context/actions/build-next.yaml

@@ -0,0 +1,5 @@
+schema: agent-graph.action.v1
+id: build-next
+runner: command
+effect: write
+command: context build --format json

package/providers/context/actions/capture-next.yaml

@@ -0,0 +1,6 @@
+schema: agent-graph.action.v1
+id: capture-next
+runner: host
+effect: external
+handler: context.capture.next
+

package/providers/context/actions/close-approved-knowledge.yaml

@@ -0,0 +1,5 @@
+schema: agent-graph.action.v1
+id: close-approved-knowledge
+runner: command
+effect: write
+command: context close --format json

package/providers/context/actions/compile-next.yaml

@@ -0,0 +1,6 @@
+schema: agent-graph.action.v1
+id: compile-next
+runner: host
+effect: write
+handler: context.compile.next
+

package/providers/context/actions/configure-code-extraction.yaml

@@ -0,0 +1,6 @@
+schema: agent-graph.action.v1
+id: configure-code-extraction
+runner: host
+effect: write
+handler: context.project.configure-extraction
+

package/providers/context/actions/configure-document-capture.yaml

@@ -0,0 +1,6 @@
+schema: agent-graph.action.v1
+id: configure-document-capture
+runner: host
+effect: write
+handler: context.project.configure-capture
+

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

@@ -0,0 +1,6 @@
+schema: agent-graph.action.v1
+id: configure-package-output
+runner: host
+effect: write
+handler: context.project.configure-package
+

package/providers/context/actions/configure-prose-lifecycle.yaml

@@ -0,0 +1,6 @@
+schema: agent-graph.action.v1
+id: configure-prose-lifecycle
+runner: host
+effect: write
+handler: context.project.configure-prose
+

package/providers/context/actions/ensure-repository-sources.yaml

@@ -0,0 +1,5 @@
+schema: agent-graph.action.v1
+id: ensure-repository-sources
+runner: command
+effect: write
+command: context source ensure --format json

package/providers/context/actions/extract-next.yaml

@@ -0,0 +1,6 @@
+schema: agent-graph.action.v1
+id: extract-next
+runner: host
+effect: write
+handler: context.extract.next
+

package/providers/context/actions/inspect-document-classification.yaml

@@ -0,0 +1,5 @@
+schema: agent-graph.action.v1
+id: inspect-document-classification
+runner: host
+effect: read
+handler: context.document.inspect-classification

package/providers/context/actions/inspect-review.yaml

@@ -0,0 +1,5 @@
+schema: agent-graph.action.v1
+id: inspect-review
+runner: host
+effect: read
+handler: context.review.inspect-current

package/providers/context/actions/inspect-structure.yaml

@@ -0,0 +1,5 @@
+schema: agent-graph.action.v1
+id: inspect-structure
+runner: host
+effect: read
+handler: context.structure.inspect

package/providers/context/actions/maintain-evidence.yaml

@@ -0,0 +1,6 @@
+schema: agent-graph.action.v1
+id: maintain-evidence
+runner: command
+effect: write
+command: context review maintain --input - --format json
+inputSchema: schemas/evidence-maintenance-input.schema.json

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

@@ -0,0 +1,8 @@
+schema: agent-graph.action.v1
+id: materialize-context-view
+description: Emit a Context-owned, revision-bound Markdown view supplied by the host adapter.
+runner: script
+effect: read
+entry: scripts/render-context-view.mjs
+runtime: node
+cwd: workspace

package/providers/context/actions/register-source-batch.yaml

@@ -0,0 +1,7 @@
+schema: agent-graph.action.v1
+id: register-source-batch
+description: Register the source batch explicitly confirmed in the current conversation.
+runner: command
+effect: write
+command: context source add batch --input - --format json
+inputSchema: schemas/source-batch-input.schema.json

package/providers/context/actions/repair-project-entry.yaml

@@ -0,0 +1,6 @@
+schema: agent-graph.action.v1
+id: repair-project-entry
+runner: host
+effect: write
+handler: context.project.repair-entry
+

package/providers/context/actions/repair-verification.yaml

@@ -0,0 +1,5 @@
+schema: agent-graph.action.v1
+id: repair-verification
+runner: command
+effect: read
+command: context verify --format json

package/providers/context/actions/repair-workspace-state.yaml

@@ -0,0 +1,6 @@
+schema: agent-graph.action.v1
+id: repair-workspace-state
+runner: host
+effect: read
+handler: context.workspace.inspect-diagnostics
+

package/providers/context/codes.yaml

@@ -0,0 +1,38 @@
+schema: agent-graph.code-catalog.v1
+codes:
+  - { code: diagnostic.project-entry-invalid, kind: diagnostic, severity: error, summary: The Context project entry cannot be loaded., document: resources/diagnostics/workspace-state.md }
+  - { code: diagnostic.workspace-state-invalid, kind: diagnostic, severity: error, summary: Context cannot establish valid lifecycle facts for the workspace., document: resources/diagnostics/workspace-state.md }
+  - { code: diagnostic.structure-snapshot-invalid, kind: diagnostic, severity: error, summary: An active source-bound structure snapshot is invalid., document: resources/diagnostics/workspace-state.md }
+  - { code: diagnostic.phase-source-unresolved, kind: diagnostic, severity: error, summary: A document lifecycle phase cannot resolve its canonical source., document: resources/diagnostics/workspace-state.md }
+  - { code: diagnostic.structure-route-unresolved, kind: diagnostic, severity: error, summary: A staged structure cannot resolve to one source and collection lifecycle., document: resources/diagnostics/workspace-state.md }
+  - { code: diagnostic.compile-route-ambiguous, kind: diagnostic, severity: error, summary: More than one compile lifecycle owns the same source and collection., document: resources/diagnostics/workspace-state.md }
+  - { code: diagnostic.structure-snapshot-missing, kind: diagnostic, severity: error, summary: A compile batch references a missing confirmed structure snapshot., document: resources/diagnostics/workspace-state.md }
+  - { code: diagnostic.verify-failed, kind: diagnostic, severity: error, summary: Verification found one or more blocking findings., document: resources/diagnostics/verification.md }
+  - { code: diagnostic.evidence-degraded, kind: diagnostic, severity: warning, summary: Approved knowledge has evidence that cannot currently be rechecked., document: resources/diagnostics/verification.md }
+  - { code: diagnostic.evidence-stale, kind: diagnostic, severity: warning, summary: Approved knowledge evidence is stale against its registered source., document: resources/diagnostics/verification.md }
+  - { code: diagnostic.evidence-orphaned, kind: diagnostic, severity: warning, summary: Approved knowledge no longer resolves to registered source evidence., document: resources/diagnostics/verification.md }
+  - { code: route.workspace.project-entry-invalid, kind: route-reason, summary: Repair the Context project entry before continuing., document: resources/procedures/project-configuration.md }
+  - { code: route.workspace.state-invalid, kind: route-reason, summary: Inspect and repair the invalid workspace facts., document: resources/diagnostics/workspace-state.md }
+  - { code: route.verify.failed, kind: route-reason, summary: Resolve blocking verification findings before other lifecycle writes., document: resources/procedures/verify-and-repair.md }
+  - { code: route.evidence.decision-required, kind: route-reason, summary: A source-evidence change needs an explicit maintenance decision., document: resources/procedures/evidence-maintenance.md }
+  - { code: route.evidence.maintenance-required, kind: route-reason, summary: Apply the selected evidence-maintenance action., document: resources/procedures/evidence-maintenance.md }
+  - { code: route.source.boundary-required, kind: route-reason, summary: No knowledge source boundary has been registered., document: resources/procedures/source-boundary.md }
+  - { code: route.source.repository-not-ready, kind: route-reason, summary: A registered repository source is not ready locally., document: resources/procedures/source-boundary.md }
+  - { 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.extract.scope-required, kind: route-reason, summary: Code extraction scope has not been confirmed., document: resources/procedures/code-extraction.md }
+  - { code: route.extract.configuration-required, kind: route-reason, summary: Registered repository sources are missing extraction declarations., document: resources/procedures/project-configuration.md }
+  - { code: route.extract.pending-target, kind: route-reason, summary: Extract the next pending code target before another workflow family., document: resources/procedures/code-extraction.md }
+  - { code: route.document.classification-required, kind: route-reason, summary: A captured document needs an evidence-backed collection decision., document: resources/procedures/document-classification.md }
+  - { code: route.prose.configuration-required, kind: route-reason, summary: A document target is missing a complete prose lifecycle declaration., document: resources/procedures/project-configuration.md }
+  - { code: route.structure.pending-target, kind: route-reason, summary: Prepare the next document structure slot from source evidence., document: resources/procedures/prose-align.md }
+  - { code: route.structure.confirmation-required, kind: route-reason, summary: A staged structure is waiting for confirmation., document: resources/procedures/prose-align.md }
+  - { code: route.structure.confirm, kind: route-reason, summary: Persist the confirmed structure slot., document: resources/procedures/prose-align.md }
+  - { code: route.compile.pending-target, kind: route-reason, summary: Compile the next planned source-bound knowledge view., document: resources/procedures/prose-compile.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.build.package-stale, kind: route-reason, summary: Build the declared package outputs from current approved knowledge., document: resources/procedures/close-and-build.md }