@c4a/context-cli 0.6.1-beta.2 → 0.6.1-beta.3

package/docs/quickstart.md

@@ -68,6 +68,12 @@ The CLI performs mechanical work such as source registration, capture,
 validation, review application, verify, close, and build. The agent performs
 semantic judgment only when the workflow asks for it.
 
+When the user explicitly requests fully managed operation, the Agent may use
+`context run --managed --until blocked-or-complete --format json` to collapse
+consecutive deterministic routes. The CLI re-evaluates every revision and
+stops before semantic reads, configuration, missing authority, diagnostics, or
+multiple commands.
+
 ## 4. Manual Orientation
 
 When operating without an agent plugin, start with:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@c4a/context-cli",
-  "version": "0.6.1-beta.2",
+  "version": "0.6.1-beta.3",
   "type": "module",
   "description": "Local CLI for capturing, compiling, and governing knowledge workspaces",
   "license": "MIT",
@@ -21,7 +21,7 @@
   },
   "dependencies": {
     "@c4a/agent-graph": "0.2.2",
-    "@c4a/context": "0.6.1-beta.2",
+    "@c4a/context": "0.6.1-beta.3",
     "commander": "^11.0.0",
     "handlebars": "^4.7.8",
     "ink": "^5.0.0",

package/plugins/README.md

@@ -68,6 +68,17 @@ That session authority is not stored. It cannot choose source boundaries,
 authorize unread external content, perform external repository operations, or
 bypass validation and verification.
 
+After the initial managed status, consecutive deterministic routes can be
+collapsed with:
+
+```bash
+context run --managed --until blocked-or-complete --format json
+```
+
+The loop stops before any route that needs Agent interpretation, configuration,
+additional authority, or diagnostic repair, and returns the current workflow
+route for normal progressive loading.
+
 ## Workspace and SDK
 
 Run the plugin from the initialized Context project root. Project declarations

package/plugins/README_CN.md

@@ -62,6 +62,15 @@ context status --managed --format json
 该会话权限不会持久化，也不能选择来源边界、授权尚未允许读取的外部内容、执行
 外部仓库操作，或绕过校验与验证。
 
+首次读取托管状态后，可用下面的命令合并连续的确定性步骤：
+
+```bash
+context run --managed --until blocked-or-complete --format json
+```
+
+遇到需要 Agent 判断、配置修改、额外权限、诊断修复或多条命令的路线时，循环会
+立即停止，并返回当前 `workflow.current` 供 Agent 按需加载上下文。
+
 ## 工作区与 SDK
 
 Plugin 应在初始化后的 Context 项目根目录运行。`src/index.ts` 保存项目声明；

package/plugins/VERSION

@@ -1 +1 @@
-0.6.1-beta.2
+0.6.1-beta.3

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": "0.6.1-beta.2",
+  "version": "0.6.1-beta.3",
   "author": {
     "name": "c4a"
   },

package/plugins/claude/commands/continue.md

@@ -24,6 +24,20 @@ 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.
 
+For an explicitly managed conversation, the CLI can collapse consecutive
+mechanical routes:
+
+```bash
+context run --managed --until blocked-or-complete --format json
+```
+
+Pass an additional `--authority` only when the user explicitly granted that
+non-managed authority in this conversation. This loop executes only one
+revision-bound command at a time and re-evaluates after every receipt. It stops
+before read-only interpretation, project configuration, unresolved authority,
+diagnostics, or a non-unique command plan. On stop, resume from the returned
+`workflow.current`; do not derive a command from earlier steps.
+
 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.
@@ -41,7 +55,8 @@ Treat `workflow.current` as the current-step authority:
    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
+5. After every action or configuration change, run status again. The managed
+   `--until` loop performs this re-evaluation internally. A phase-local
    `next_action` can continue that operation but never replaces the workspace
    Route.
 

package/plugins/claude/commands/init.md

@@ -9,22 +9,23 @@ allowed-tools: Bash(context:*), Bash(bun:*), Bash(cd *)
 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 user's language for conversation. Keep command and payload tokens
+unchanged.
 
 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.
+user supplied. Never substitute `.` when `project-dir` was omitted; the default
+is `context/`. Use `--dev` only for an explicitly requested local-link test.
 
-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.
+If init reports `init-target-nonempty`, explain that existing files would share
+the workspace root. Run the returned `--allow-nonempty` command only after
+explicit confirmation.
 
-Do not add extra project-local agent setup. Do not infer repo sources or
-extraction scope from the surrounding monorepo after setup.
+Execute the returned setup command, enter the project root, and read its
+generated `AGENTS.md`. Then run `context status --format json`, adding
+`--managed` only for fully managed operation explicitly authorized in this
+conversation. Treat `workflow.current` as authoritative: read its required
+resources, execute only exact commands, honor unresolved human gates, and
+reevaluate status after each action.
+
+Do not add extra project-local agent setup or infer sources from the surrounding
+monorepo.

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

@@ -1,6 +1,6 @@
 {
   "name": "context",
-  "version": "0.6.1-beta.2",
+  "version": "0.6.1-beta.3",
   "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.\nv0.6.1-beta.2",
+    "shortDescription": "Initialize and advance a local, source-linked project knowledge workspace.\nv0.6.1-beta.3",
     "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/SKILL.md

@@ -36,6 +36,20 @@ 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.
 
+For an explicitly managed conversation, the CLI can collapse consecutive
+mechanical routes:
+
+```bash
+context run --managed --until blocked-or-complete --format json
+```
+
+Pass an additional `--authority` only when the user explicitly granted that
+non-managed authority in this conversation. This loop executes only one
+revision-bound command at a time and re-evaluates after every receipt. It stops
+before read-only interpretation, project configuration, unresolved authority,
+diagnostics, or a non-unique command plan. On stop, resume from the returned
+`workflow.current`; do not derive a command from earlier steps.
+
 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.
@@ -53,7 +67,8 @@ Treat `workflow.current` as the current-step authority:
    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
+5. After every action or configuration change, run status again. The managed
+   `--until` loop performs this re-evaluation internally. A phase-local
    `next_action` can continue that operation but never replaces the workspace
    Route.
 

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

@@ -21,22 +21,23 @@ Public Context entry for agents that expose skills instead of slash commands.
 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 user's language for conversation. Keep command and payload tokens
+unchanged.
 
 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.
+user supplied. Never substitute `.` when `project-dir` was omitted; the default
+is `context/`. Use `--dev` only for an explicitly requested local-link test.
+
+If init reports `init-target-nonempty`, explain that existing files would share
+the workspace root. Run the returned `--allow-nonempty` command only after
+explicit confirmation.
+
+Execute the returned setup command, enter the project root, and read its
+generated `AGENTS.md`. Then run `context status --format json`, adding
+`--managed` only for fully managed operation explicitly authorized in this
+conversation. Treat `workflow.current` as authoritative: read its required
+resources, execute only exact commands, honor unresolved human gates, and
+reevaluate status after each action.
+
+Do not add extra project-local agent setup or infer sources from the surrounding
+monorepo.

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

@@ -1,7 +1,7 @@
 {
   "name": "context",
   "displayName": "C4A Context",
-  "version": "0.6.1-beta.2",
+  "version": "0.6.1-beta.3",
   "description": "Maintain a project-local knowledge workspace through init and next-step agent guidance.",
   "author": {
     "name": "Context4AI",

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

@@ -28,6 +28,20 @@ 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.
 
+For an explicitly managed conversation, the CLI can collapse consecutive
+mechanical routes:
+
+```bash
+context run --managed --until blocked-or-complete --format json
+```
+
+Pass an additional `--authority` only when the user explicitly granted that
+non-managed authority in this conversation. This loop executes only one
+revision-bound command at a time and re-evaluates after every receipt. It stops
+before read-only interpretation, project configuration, unresolved authority,
+diagnostics, or a non-unique command plan. On stop, resume from the returned
+`workflow.current`; do not derive a command from earlier steps.
+
 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.
@@ -45,7 +59,8 @@ Treat `workflow.current` as the current-step authority:
    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
+5. After every action or configuration change, run status again. The managed
+   `--until` loop performs this re-evaluation internally. A phase-local
    `next_action` can continue that operation but never replaces the workspace
    Route.
 

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

@@ -13,22 +13,23 @@ Initialize a Context knowledge workspace.
 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 user's language for conversation. Keep command and payload tokens
+unchanged.
 
 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.
+user supplied. Never substitute `.` when `project-dir` was omitted; the default
+is `context/`. Use `--dev` only for an explicitly requested local-link test.
+
+If init reports `init-target-nonempty`, explain that existing files would share
+the workspace root. Run the returned `--allow-nonempty` command only after
+explicit confirmation.
+
+Execute the returned setup command, enter the project root, and read its
+generated `AGENTS.md`. Then run `context status --format json`, adding
+`--managed` only for fully managed operation explicitly authorized in this
+conversation. Treat `workflow.current` as authoritative: read its required
+resources, execute only exact commands, honor unresolved human gates, and
+reevaluate status after each action.
+
+Do not add extra project-local agent setup or infer sources from the surrounding
+monorepo.

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

@@ -36,6 +36,20 @@ 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.
 
+For an explicitly managed conversation, the CLI can collapse consecutive
+mechanical routes:
+
+```bash
+context run --managed --until blocked-or-complete --format json
+```
+
+Pass an additional `--authority` only when the user explicitly granted that
+non-managed authority in this conversation. This loop executes only one
+revision-bound command at a time and re-evaluates after every receipt. It stops
+before read-only interpretation, project configuration, unresolved authority,
+diagnostics, or a non-unique command plan. On stop, resume from the returned
+`workflow.current`; do not derive a command from earlier steps.
+
 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.
@@ -53,7 +67,8 @@ Treat `workflow.current` as the current-step authority:
    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
+5. After every action or configuration change, run status again. The managed
+   `--until` loop performs this re-evaluation internally. A phase-local
    `next_action` can continue that operation but never replaces the workspace
    Route.
 

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

@@ -21,22 +21,23 @@ Public Context entry for agents that expose skills instead of slash commands.
 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 user's language for conversation. Keep command and payload tokens
+unchanged.
 
 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.
+user supplied. Never substitute `.` when `project-dir` was omitted; the default
+is `context/`. Use `--dev` only for an explicitly requested local-link test.
+
+If init reports `init-target-nonempty`, explain that existing files would share
+the workspace root. Run the returned `--allow-nonempty` command only after
+explicit confirmation.
+
+Execute the returned setup command, enter the project root, and read its
+generated `AGENTS.md`. Then run `context status --format json`, adding
+`--managed` only for fully managed operation explicitly authorized in this
+conversation. Treat `workflow.current` as authoritative: read its required
+resources, execute only exact commands, honor unresolved human gates, and
+reevaluate status after each action.
+
+Do not add extra project-local agent setup or infer sources from the surrounding
+monorepo.

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

@@ -3,4 +3,3 @@ id: align-next
 runner: host
 effect: write
 handler: context.align.next
-

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

@@ -3,4 +3,3 @@ id: apply-managed-review
 runner: host
 effect: write
 handler: context.review.approve-current
-

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

@@ -3,4 +3,3 @@ id: apply-structure-confirmation
 runner: host
 effect: write
 handler: context.structure.confirm
-

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

@@ -3,4 +3,3 @@ id: capture-next
 runner: host
 effect: external
 handler: context.capture.next
-

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

@@ -3,4 +3,3 @@ id: compile-next
 runner: host
 effect: write
 handler: context.compile.next
-

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

@@ -3,4 +3,3 @@ id: configure-code-extraction
 runner: host
 effect: write
 handler: context.project.configure-extraction
-

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

@@ -3,4 +3,3 @@ id: configure-document-capture
 runner: host
 effect: write
 handler: context.project.configure-capture
-

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

@@ -3,4 +3,3 @@ id: configure-package-output
 runner: host
 effect: write
 handler: context.project.configure-package
-

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

@@ -3,4 +3,3 @@ id: configure-prose-lifecycle
 runner: host
 effect: write
 handler: context.project.configure-prose
-

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

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

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

@@ -3,4 +3,3 @@ id: extract-next
 runner: host
 effect: write
 handler: context.extract.next
-

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

@@ -3,4 +3,3 @@ id: repair-project-entry
 runner: host
 effect: write
 handler: context.project.repair-entry
-

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

@@ -3,4 +3,3 @@ id: repair-workspace-state
 runner: host
 effect: read
 handler: context.workspace.inspect-diagnostics
-