feat: statusline v2, agentic orchestration hardening, and TUI polish

.claude/hooks/check-changelog.sh

@@ -54,11 +54,16 @@ done <<< "$changed"
 [ "$touched" -eq 0 ] && exit 0
 
 # Pass if ## Unreleased has at least one non-blank line.
+# Checked inside awk (no pipe): `| grep -q` exits at the first match, and
+# under pipefail the resulting SIGPIPE to awk reads as failure once the
+# block outgrows the pipe buffer — denying exactly when the changelog is
+# at its fullest.
 if awk '
   /^## Unreleased[[:space:]]*$/ { inblk=1; next }
   inblk && /^## /               { inblk=0 }
-  inblk                         { print }
-' CHANGELOG.md 2>/dev/null | grep -q '[^[:space:]]'; then
+  inblk && /[^[:space:]]/       { found=1; exit }
+  END                           { exit !found }
+' CHANGELOG.md 2>/dev/null; then
   exit 0
 fi
 

.coderabbit.yaml

@@ -51,6 +51,10 @@ reviews:
     - "!graphify-out/**"
     - "!**/*.pyc"
     - "!**/__pycache__/**"
+    # Prose and working-notes paths: keeps bot reviews focused on shipped
+    # code and large branches under the per-PR reviewed-file limit.
+    - "!docs/**"
+    - "!tasks/**"
 
   path_instructions:
     - path: "**/*.py"

.github/workflows/release-pythinker-cli.yml

@@ -571,6 +571,40 @@ jobs:
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
+  register-bugsink-release:
+    name: Register release in Bugsink
+    needs: [validate, release]
+    # Registering the release at cut time (instead of waiting for the first
+    # event from that version) makes Bugsink's "resolved in next release"
+    # semantics flip exactly when the release ships. Telemetry must never
+    # gate a release: failures here are warnings, not job failures.
+    if: always() && needs.release.result == 'success'
+    runs-on: ubuntu-latest
+    steps:
+      - name: POST release to Bugsink
+        env:
+          VERSION: ${{ needs.validate.outputs.version }}
+          BUGSINK_TOKEN: ${{ secrets.BUGSINK_RELEASES_TOKEN }}
+        run: |
+          set -uo pipefail
+          if [[ -z "$BUGSINK_TOKEN" ]]; then
+            echo "::warning title=Bugsink::BUGSINK_RELEASES_TOKEN not set; skipping release registration"
+            exit 0
+          fi
+          body=$(jq -n --arg v "pythinker-code@${VERSION}" '{project: 1, version: $v}')
+          status=$(curl -sS -o /tmp/resp.json -w "%{http_code}" -m 30 \
+            -X POST "https://errors.pythinker.com/api/canonical/0/releases/" \
+            -H "Authorization: Bearer ${BUGSINK_TOKEN}" \
+            -H "Content-Type: application/json" \
+            -d "$body" || echo "000")
+          if [[ "$status" == "201" || "$status" == "200" ]]; then
+            echo "Registered pythinker-code@${VERSION} in Bugsink"
+          elif [[ "$status" == "400" ]] && grep -q "already exists" /tmp/resp.json; then
+            echo "Release pythinker-code@${VERSION} already registered (idempotent re-run)"
+          else
+            echo "::warning title=Bugsink::release registration failed (HTTP ${status}): $(cat /tmp/resp.json 2>/dev/null | head -c 200)"
+          fi
+
   publish-python-testpypi:
     name: Publish Python package to TestPyPI
     needs: validate

docs/.vitepress/config.ts

@@ -109,6 +109,12 @@ export default withMermaid(defineConfig({
     ],
   },
 
+  transformHead({ pageData }) {
+    if (pageData.relativePath === 'index.md') {
+      return [['meta', { 'http-equiv': 'refresh', content: `0; url=${base}en/` }]]
+    }
+  },
+
   vite: {
     plugins: [llmstxt()],
   },

docs/en/configuration/config-files.md

@@ -30,7 +30,7 @@ The configuration file contains the following top-level configuration items:
 | `skip_auto_prompt_injection` | `boolean` | Whether to suppress the auto-mode system reminder (defaults to `false`) |
 | `default_plan_mode` | `boolean` | Whether to start new sessions in plan mode by default (defaults to `false`); resumed sessions preserve their existing state |
 | `default_editor` | `string` | Default external editor command (e.g. `"vim"`, `"code --wait"`), auto-detects when empty |
-| `theme` | `string` | Terminal color theme, either `"dark"` or `"light"` (defaults to `"dark"`) |
+| `theme` | `string` | Terminal color theme: `"dark"`, `"light"`, or `"auto"` (detects the terminal background at startup, falling back to dark); defaults to `"dark"` |
 | `show_thinking_stream` | `boolean` | Whether to stream the raw reasoning text in the live area as a 6-line scrolling preview and commit the full reasoning markdown to history when the block ends (defaults to `true`; set to `false` to show only the compact `Thinking ...` indicator and a one-line trace summary) |
 | `prevent_idle_sleep` | `boolean` | Whether to prevent the computer from idle-sleeping while an agent turn is running (defaults to `false`; supported on macOS, Linux, and Windows) |
 | `merge_all_available_skills` | `boolean` | Whether to merge skills from all brand directories (defaults to `true`); see [Skills configuration](../customization/skills.md) |
@@ -41,6 +41,7 @@ The configuration file contains the following top-level configuration items:
 | `compact_prompt` | `string \| null` | Override the built-in compaction summarization prompt; `null`/unset keeps the default handoff-structured prompt (a `/compact` focus argument is still appended on top) |
 | `background` | `table` | Background task runtime parameters |
 | `services` | `table` | External service configuration (search, fetch) |
+| `web` | `table` | Shared web fetch/search policy (e.g. `allowed_domains`) |
 | `mcp` | `table` | MCP client configuration |
 
 ### Complete configuration example

docs/en/configuration/env-vars.md

@@ -140,8 +140,8 @@ export OPENAI_ADMIN_KEY="sk-admin-xxx"
 | --- | --- |
 | `PYTHINKER_SHARE_DIR` | Customize the share directory path (default: `~/.pythinker`) |
 | `PYTHINKER_CLI_NO_AUTO_UPDATE` | Disable proactive update checks and startup update notices |
-| `PYTHINKER_CLI_PASTE_CHAR_THRESHOLD` | Character threshold for folding pasted text (default: `1000`) |
-| `PYTHINKER_CLI_PASTE_LINE_THRESHOLD` | Line threshold for folding pasted text (default: `15`) |
+| `PYTHINKER_CLI_PASTE_CHAR_THRESHOLD` | Character threshold for folding pasted text (default: `200`) |
+| `PYTHINKER_CLI_PASTE_LINE_THRESHOLD` | Line threshold for folding pasted text (default: `5`) |
 
 ### `PYTHINKER_SHARE_DIR`
 
@@ -171,18 +171,18 @@ If you installed Pythinker Code via Nix or other package managers, this environm
 
 ### `PYTHINKER_CLI_PASTE_CHAR_THRESHOLD`
 
-In Agent mode, when pasted text exceeds this character count, it is folded into a placeholder (e.g., `[Pasted text #1 +10 lines]`) and expanded to full content on submit. Default: `1000`.
+In Agent mode, when pasted text exceeds this character count, it is folded into a placeholder (e.g., `[Pasted text #1 +10 lines]`) and expanded to full content on submit. Default: `200`.
 
 ```sh
-export PYTHINKER_CLI_PASTE_CHAR_THRESHOLD="1000"
+export PYTHINKER_CLI_PASTE_CHAR_THRESHOLD="200"
 ```
 
 ### `PYTHINKER_CLI_PASTE_LINE_THRESHOLD`
 
-In Agent mode, when pasted text reaches this line count, it is folded into a placeholder. Default: `15`.
+In Agent mode, when pasted text reaches this line count, it is folded into a placeholder. Default: `5`.
 
 ```sh
-export PYTHINKER_CLI_PASTE_LINE_THRESHOLD="15"
+export PYTHINKER_CLI_PASTE_LINE_THRESHOLD="5"
 ```
 
 ::: tip

docs/en/configuration/overrides.md

@@ -54,7 +54,7 @@ Environment variables can override provider and model settings without modifying
 Environment variables take effect based on the current provider type:
 
 - `pythinker` type providers: Use `PYTHINKER_*` environment variables
-- `openai_legacy` or `openai_responses` type providers: Use `OPENAI_*` environment variables
+- `openai_legacy`, `openai_responses`, or `openai_codex` type providers: Use `OPENAI_*` environment variables
 - Other provider types: Environment variable overrides not supported
 
 See [Environment Variables](./env-vars.md) for the complete list.

docs/en/configuration/providers.md

@@ -17,8 +17,12 @@ After configuration, Pythinker Code will automatically save settings to `~/.pyth
 | Platform | Description |
 | --- | --- |
 | Pythinker | Pythinker platform, supports search and fetch services |
+| OpenAI API | Official OpenAI API |
+| OpenAI ChatGPT Codex | OpenAI managed account login |
 | Pythinker AI Open Platform (pythinker-ai.cn) | China region API endpoint |
 | Pythinker AI Open Platform (pythinker-ai.ai) | Global region API endpoint |
+| LM Studio | Local models served via LM Studio |
+| Ollama | Local models served via Ollama |
 
 For other platforms, please manually edit the configuration file.
 
@@ -31,6 +35,7 @@ The `type` field in `providers` configuration specifies the API provider type. D
 | `pythinker` | Pythinker API |
 | `openai_legacy` | OpenAI Chat Completions API |
 | `openai_responses` | OpenAI Responses API |
+| `openai_codex` | OpenAI Responses API with managed account login (configured via `/login`, not by hand) |
 | `anthropic` | Anthropic Claude API |
 | `gemini` | Google Gemini API |
 | `vertexai` | Google Vertex AI |

docs/en/customization/agent-architecture.md

@@ -217,7 +217,7 @@ The toolset is both a registry and an execution boundary. It hides tools from th
 
 ## Subagent graph
 
-The `Agent` tool lets only the root agent create or resume subagents. Subagents get isolated context and Wire files, but share session-level services such as approval state, notification infrastructure, background task management, and the root Wire hub.
+The `Agent` tool lets only the root agent create or resume a single subagent, and the `RunAgents` tool launches a batch of subagents (up to 8) in one call. Both are root-only. Subagents get isolated context and Wire files, but share session-level services such as approval state, notification infrastructure, background task management, and the root Wire hub.
 
 ```mermaid
 flowchart TB
@@ -306,6 +306,7 @@ Hooks are integrated at both turn and tool boundaries:
 | `PostToolUseFailure` | After a tool raises an exception |
 | `Stop` | After a turn finishes, with one re-trigger guard |
 | `StopFailure` | After an agent step fails |
+| `SessionStart` and `SessionEnd` | When a session is created/resumed and when it closes |
 | `PreCompact` and `PostCompact` | Around context compaction |
 | `Notification` | When pending notifications are delivered into LLM context |
 | `SubagentStart` and `SubagentStop` | Around foreground subagent execution |

docs/en/customization/agents.md

@@ -16,7 +16,7 @@ pythinker --agent okabe
 
 The default agent, suitable for general use. Enabled tools:
 
-`Agent`, `AskUserQuestion`, `SetTodoList`, `Shell`, `ReadFile`, `ReadMediaFile`, `Glob`, `Grep`, `WriteFile`, `StrReplaceFile`, `SearchWeb`, `FetchURL`, `EnterPlanMode`, `ExitPlanMode`, `TaskList`, `TaskOutput`, `TaskStop`
+`Agent`, `RunAgents`, `ReadSkill`, `AskUserQuestion`, `SetTodoList`, `UpdateGoal`, `Progress`, `Suggest`, `Memory`, `Recall`, `Scratchpad`, `Shell`, `TaskList`, `TaskOutput`, `TaskInput`, `TaskHandoff`, `TaskStop`, `ReadFile`, `ReadMediaFile`, `Glob`, `Grep`, `SmartSearch`, `WriteFile`, `StrReplaceFile`, `SearchWeb`, `FetchURL`, `ListMcpResources`, `ReadMcpResource`, `EnterPlanMode`, `ExitPlanMode`
 
 ### `ask`
 
@@ -28,7 +28,7 @@ Primary mode for systematic failure diagnosis. It reproduces or inspects failure
 
 ### `okabe`
 
-An experimental agent for testing new prompts and tools. Adds `SendDMail` on top of `default`.
+An experimental agent for testing new prompts and tools. It inherits from `default` but defines its own tool list, which adds `SendDMail` (D-Mail checkpoint rollback).
 
 ## Repository markdown agents
 
@@ -187,19 +187,21 @@ The default agent configuration includes focused built-in subagent types with di
 |------|---------|----------------|
 | `coder` | General software engineering with judgment: read/write files, run commands, search code | Read/search tools, `Shell`, write tools, web tools |
 | `implementer` | Scoped implementation with minimal edits and quick verification | Read/search tools, `Shell`, write tools, web tools |
-| `explore` | Fast read-only codebase exploration: search, read, summarize | Read/search tools, `Shell`, web tools; no write tools |
+| `explore` | Fast read-only codebase exploration: search, read, summarize | Read/search tools and `Shell`; no write tools |
 | `plan` | Implementation planning and architecture design | Read/search tools and web tools; no write tools |
 | `planner` | Read-only recon planner that decomposes broad work into parallel seeds | Read/search tools and `Shell`; no write tools |
 | `scout` | Read-only external docs, dependency-source, and API freshness researcher | Read/search tools, `Shell`, web tools; no write tools |
-| `review` | Read-only severity-scored code review | Read/search tools, `Shell`, web tools; no write tools |
-| `code-reviewer` | Diff-focused code review for the current branch | Read/search tools, `Shell`, web tools; no write tools |
-| `security-reviewer` | Diff-focused security review with validated findings | Read/search tools, `Shell`, web tools; no write tools |
+| `review` | Read-only severity-scored code review | Read/search tools and `Shell`; no write tools |
+| `code-reviewer` | Diff-focused code review for the current branch | Read/search tools and `Shell`; no write tools |
+| `security-reviewer` | Diff-focused security review with validated findings | Read/search tools and `Shell`; no write tools |
 | `debugger` | Root-cause analysis for failures, logs, and stack traces | Read/search tools and `Shell`; no write tools |
 | `verifier` | Read-only validation runner for tests, lint, type checks, and builds | Read/search tools and `Shell`; no write tools |
 | `judge` | Independent final quality gate for answers, reports, and code-change summaries | Read/search tools and `Shell`; no write tools |
 
 All subagent types are prohibited from nesting the `Agent` tool (subagents cannot create their own subagents). The `Agent` tool is only available to the root agent.
 
+Reviewer-class types (`review`, `code-reviewer`, `security-reviewer`, `debugger`, `judge`, `verifier`, `explore`) run offline by design: their permission profiles block network and external doc-lookup tools because the content they analyze is untrusted. Third-party claims they cannot verify from the repository come back under RISKS as `needs verification` items; the parent agent resolves those against live docs — directly or by dispatching `scout`, the online research type (`plan` also keeps web access for planning research).
+
 ## How subagents run
 
 Subagents launched via the `Agent` tool run in an isolated context and return results to the main agent when complete. Each subagent instance maintains its own context history and metadata under `subagents/<agent_id>/` in the session directory, and can be resumed across multiple invocations. Advantages of this approach:
@@ -226,7 +228,31 @@ The following are all built-in tools in Pythinker Code.
 | `model` | string | Optional model override |
 | `resume` | string | Optional agent instance ID to resume an existing instance |
 | `run_in_background` | bool | Whether to run in background, default false |
-| `timeout` | int | Timeout in seconds, range 30–3600. Foreground defaults to no timeout (runs until completion), background defaults to 15 minutes; the task is stopped if the limit is exceeded |
+| `timeout` | int | Timeout in seconds, range 30–3600. Foreground defaults to no timeout (runs until completion), background defaults to the configured limit (1 hour); the task is stopped if the limit is exceeded |
+| `dependencies` | array | Optional background task IDs this task depends on. Metadata only — launch dependent tasks after their prerequisites are ready |
+| `budget_seconds` | int | Optional time budget (seconds) recorded as planning/synthesis metadata |
+| `isolation` | string | `none` (default) or `worktree`. `worktree` records a git-worktree isolation intent for background agents; ignored for foreground runs |
+
+### `RunAgents`
+
+- **Path**: `pythinker_code.tools.agent:RunAgents`
+- **Description**: Launch a batch of subagents (1–8) in one call, sharing a common `base_prompt` and each running its own `prompt`. Foreground batches run the children concurrently and return all results inline; background batches return task IDs immediately, and if a background batch exceeds the available slots only the fitting prefix is launched while the rest are reported as deferred. Like `Agent`, this tool is only available to the root agent.
+
+| Parameter | Type | Description |
+|-----------|------|-------------|
+| `summary` | string | Short summary of the multi-agent run |
+| `base_prompt` | string | Shared context prepended to every child prompt |
+| `agents` | array | Child agents to launch (1–8); each has its own objective |
+| `agents[].name` | string | Stable short name for the child agent |
+| `agents[].prompt` | string | Child-specific task prompt |
+| `agents[].title` | string | Optional 3–5 word display title, defaults to `name` |
+| `agents[].subagent_type` | string | Built-in subagent type for the child, default `coder` |
+| `model` | string | Optional model override applied to every child |
+| `run_in_background` | bool | Whether to run in background, default true |
+| `timeout` | int | Optional per-agent timeout in seconds, range 30–3600 |
+| `isolation` | string | `none` (default) or `worktree` for background children |
+
+To keep parallel children distinguishable in the task list, tree, and notifications, any child whose name is generic (or collides with a sibling) is given a stable `adjective-noun` codename (for example `amber-falcon`), while its subagent type stays visible separately.
 
 ### `AskUserQuestion`
 

docs/en/customization/hooks.md

@@ -36,7 +36,7 @@ Pythinker Code supports 13 lifecycle events:
 | `SubagentStop` | When subagent ends | Agent name | `agent_name`, `response` |
 | `PreCompact` | Before context compaction | Trigger reason | `trigger`, `token_count` |
 | `PostCompact` | After context compaction | Trigger reason | `trigger`, `estimated_token_count` |
-| `Notification` | When notification is delivered | Sink name | `sink`, `notification_type`, `title`, `body`, `severity` |
+| `Notification` | When notification is delivered | Notification type | `sink`, `notification_type`, `title`, `body`, `severity` |
 
 ## Configuring Hooks