openclacky 0.9.18 → 0.9.20

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 538f6014a8386fcddf69dbf69efd162a00ad594d776b812eba5ac04f98953995
-  data.tar.gz: 4d9952dbbf2e20d1a598b136a0f01e821a1e53391240c197afe60e3570d4bfce
+  metadata.gz: 803023a686f9005d8bbed56fa2604d6cb4a426ba2ff1c24ddf6e297242c7faed
+  data.tar.gz: ee8738600a36146e4f56b8605a917066746b31e370a41c3e245066ec4e4e961c
 SHA512:
-  metadata.gz: 8ed52fb94f805bc83c8ab996c9a1f01635665b054750900623002edc29a0197c9ab99be08d192e2f1f1040c8665451e155d9878fec5a71c213d7c3130fbbb956
-  data.tar.gz: 248569c522a59c37c3bda8342141be750609ca4fca996a8d563fcb953e6dcb1446fbc379082691b5503679d26d9168aa8e2503f7b169b3b4daeafa9428b7cf5b
+  metadata.gz: b5b27887365a698d193fee92d0672315c48963a9748509cae8a6b5426d0169f16b9fad709afa2232d80542999fc931ee48e09f2cee35100b39273b33c324b558
+  data.tar.gz: 5c5572d8a7b34af4eb03220dbf0e566ed0d2ab7b7278a89d8801f0c9ca58b100c90dd27fd17d1548016b21c20e1e458889a97a54983309c409479b863fc8b6ca

data/.clacky/skills/oss-upload/SKILL.md

@@ -0,0 +1,47 @@
+---
+name: oss-upload
+description: Upload local files to Tencent COS (oss.1024code.com CDN) using coscli. Use when user wants to upload a file to CDN/OSS, or deploy static assets.
+---
+
+# OSS Upload Skill
+
+Upload files to Tencent COS bucket `clackyai-1258723534`, served via `https://oss.1024code.com`.
+
+## Tool
+`coscli` — config at `~/.cos.yaml`
+
+## Bucket Info
+- Bucket: `clackyai-1258723534`
+- Region: `ap-guangzhou`
+- Endpoint: `cos.ap-guangzhou.myqcloud.com`
+- Public CDN: `https://oss.1024code.com/<path>`
+
+## Upload Command
+
+```bash
+coscli cp <local-file> cos://clackyai-1258723534/<remote-path>
+```
+
+### Examples
+
+```bash
+# Upload a single file to bucket root
+coscli cp /tmp/wsl.2.6.3.0.arm64.msi cos://clackyai-1258723534/wsl.2.6.3.0.arm64.msi
+
+# Upload to a subdirectory
+coscli cp /tmp/install.ps1 cos://clackyai-1258723534/clacky-ai/openclacky/main/scripts/install.ps1
+
+# Upload entire directory recursively
+coscli cp /tmp/dist/ cos://clackyai-1258723534/dist/ -r
+```
+
+## Public URL
+After upload, the file is accessible at:
+```
+https://oss.1024code.com/<remote-path>
+```
+
+## Steps
+1. Confirm local file exists
+2. Run `coscli cp <local> cos://clackyai-1258723534/<path>`
+3. Return the public URL: `https://oss.1024code.com/<path>`

data/CHANGELOG.md

@@ -7,6 +7,40 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.9.20] - 2026-03-30
+
+### Added
+- **SSL error retry**: LLM API calls now automatically retry on SSL errors (same as other network failures — up to 10 retries with 5s delay)
+
+### Fixed
+- **Brand wrapper not found under root**: the install script now places the brand command wrapper in the same directory as the `openclacky` binary, so it is always on PATH regardless of whether running as root or a normal user
+
+### Improved
+- **Cron task management refactored to API**: cron task CRUD operations now go through the HTTP API instead of running ad-hoc Ruby scripts, making the scheduler more reliable and easier to maintain
+- **UTF-8 encoding fix for browser tool on Windows**: browser command output with non-ASCII characters no longer causes encoding errors
+
+### More
+- Installer no longer adds `~/.local/bin` to PATH (wrapper now colocated with gem binary, making the extra PATH entry unnecessary)
+- Brand install tips in Windows PowerShell installer
+
+## [0.9.19] - 2026-03-29
+
+### Added
+- **Bing search engine support**: the web search tool now supports Bing in addition to DuckDuckGo and Baidu — improves search coverage and fallback reliability
+- **WSL1 fallback for Windows installer**: the PowerShell installer now automatically falls back to WSL1 when WSL2/Hyper-V is unavailable, ensuring installation succeeds on older or constrained Windows machines
+- **Upgrade via OSS (CN mirror)**: the upgrade flow now downloads new gem versions from Tencent OSS, making upgrades faster and more reliable for users in China
+
+### Fixed
+- **WeChat (Weixin) context token refresh**: the WeChat channel adapter now correctly refreshes the access token when it expires, preventing message delivery failures
+- **DOCX parser UTF-8 encoding bug**: parsing `.docx` files with non-ASCII content no longer causes encoding errors
+- **WSL version detection broadened**: installer now correctly handles old inbox `wsl.exe` (exit code -1) in addition to "feature not enabled" (exit code 1)
+- **Ctrl+C handling in UI**: Ctrl+C now correctly interrupts the current operation without leaving the UI in a broken state
+- **Layout scrollback double-render**: fixed a UI rendering issue that caused the scrollback buffer to render twice
+
+### More
+- Support custom brand name in Windows PowerShell installer
+- Redesigned Windows registration flow; removed Win10 MSI dependency
+
 ## [0.9.18] - 2026-03-28
 
 ### Fixed

data/docs/c-end-user-positioning.md

@@ -0,0 +1,64 @@
+# C-End User Positioning
+
+> Date: 2026-03-30
+
+---
+
+## Market Context
+
+The "OpenClaw ecosystem" has exploded in 2026. Key players:
+
+- **OpenClaw** — open-source, self-hosted, community Skills. Designed for technical users who configure everything themselves.
+- **QClaw** — Tencent's fork. Bundled Kimi model, WeChat binding. Mass-market but Tencent-ecosystem only.
+- **Others** (Wukong, etc.) — same lane.
+
+OpenClaw has 5,700+ Skills, but almost all are open-source, free, and easily copied. The ecosystem lacks **expertise-backed, production-grade Skills worth paying for**.
+
+---
+
+## Who openclacky Is For
+
+**Ordinary users, not technical geeks.**
+
+The target user knows OpenClaw exists, has heard about "raising a lobster", but can't or doesn't want to:
+- configure Docker / environment / webhooks
+- manage their own API keys without knowing what they'll spend
+- troubleshoot when a long task breaks halfway
+
+They want to use a lobster built by an expert (a lawyer, a trader, an SEO specialist) — not build one themselves.
+
+> Core insight: **OpenClaw is built for people who create Skills. openclacky is built for people who use them.**
+
+---
+
+## Why openclacky Over OpenClaw: 3 Core Reasons
+
+### 1. Zero-friction IM setup — the strongest differentiator
+
+OpenClaw requires users to manually configure webhooks, tokens, and config files to connect WeChat / Feishu / WeCom. High technical barrier, most ordinary users give up.
+
+openclacky uses **AI-automated channel setup**: one sentence, and the AI configures the IM connection for you — no plugins, no docs, no engineering knowledge required. This is a genuine technical moat.
+
+### 2. Built for China, natively
+
+- No VPN required, no overseas credit card
+- WeChat / Feishu / WeCom are the primary daily tools for Chinese users — openclacky treats them as first-class citizens
+- Supports domestic models (DeepSeek, Kimi, etc.) out of the box
+- QClaw is domestic too, but locked to Tencent's ecosystem and model choices
+
+### 3. Cost transparency and long-task reliability
+
+- Real-time token cost tracking — users always know what they're spending
+- Automatic compression (up to 90% savings via Insert-then-Compress + Prompt Caching)
+- Long tasks don't break: sub-agent isolation + Time Machine architecture keeps context intact
+
+---
+
+## The User Progression
+
+```
+Can use it  →  Dare to use it  →  Keep using it
+(zero setup)   (cost clarity)     (tasks don't break)
+```
+
+Each of the 3 reasons maps directly to one stage of this progression.

data/lib/clacky/agent/llm_caller.rb

@@ -34,7 +34,7 @@ module Clacky
             max_tokens: @config.max_tokens,
             enable_caching: @config.enable_prompt_caching
           )
-        rescue Faraday::ConnectionFailed, Faraday::TimeoutError, Errno::ECONNREFUSED, Errno::ETIMEDOUT => e
+        rescue Faraday::ConnectionFailed, Faraday::TimeoutError, Faraday::SSLError, Errno::ECONNREFUSED, Errno::ETIMEDOUT => e
           @ui&.clear_progress
           retries += 1
           if retries <= max_retries

data/lib/clacky/agent/message_compressor_helper.rb

@@ -20,6 +20,14 @@ module Clacky
         @ui&.show_idle_status(phase: :start, message: "Idle detected. Compressing conversation to optimize costs...")
         if compression_context.nil?
           @ui&.show_idle_status(phase: :end, message: "Idle skipped.")
+          Clacky::Logger.info(
+            "Idle compression skipped",
+            enable_compression: @config.enable_compression,
+            previous_total_tokens: @previous_total_tokens,
+            history_size: @history.size,
+            idle_threshold: IDLE_COMPRESSION_THRESHOLD,
+            max_recent_messages: MAX_RECENT_MESSAGES
+          )
           return false
         end
 

data/lib/clacky/default_parsers/docx_parser.rb

@@ -1,5 +1,10 @@
 #!/usr/bin/env ruby
 # frozen_string_literal: true
+# encoding: utf-8
+
+Encoding.default_external = Encoding::UTF_8
+Encoding.default_internal = Encoding::UTF_8
+
 #
 # Clacky DOCX Parser — CLI interface
 #
@@ -22,30 +27,43 @@ require "zip"
 require "rexml/document"
 require "stringio"
 
-def read_document_xml(body)
+def safe_utf8(str)
+  # First try force_encoding (lossless, for content that IS valid UTF-8)
+  utf8 = str.dup.force_encoding("UTF-8")
+  return utf8 if utf8.valid_encoding?
+  # Fallback: transcode with replacement for genuinely invalid bytes
+  str.encode("UTF-8", "binary", invalid: :replace, undef: :replace, replace: "")
+end
+
+def read_zip_entry(body, name)
+  xml = nil
   Zip::File.open_buffer(StringIO.new(body)) do |zip|
-    entry = zip.find_entry("word/document.xml")
-    raise "Could not extract content — possibly encrypted or invalid format" unless entry
-    entry.get_input_stream.read
+    entry = zip.find_entry(name)
+    xml = safe_utf8(entry.get_input_stream.read) if entry
   end
+  xml
+end
+
+def read_document_xml(body)
+  xml = read_zip_entry(body, "word/document.xml")
+  raise "Could not extract content — possibly encrypted or invalid format" unless xml
+  xml
 end
 
 def read_numbering(body)
   result = {}
-  Zip::File.open_buffer(StringIO.new(body)) do |zip|
-    entry = zip.find_entry("word/numbering.xml")
-    break unless entry
-    doc = REXML::Document.new(entry.get_input_stream.read)
-    REXML::XPath.each(doc, "//w:abstractNum") do |an|
-      id = an.attributes["w:abstractNumId"]
-      levels = {}
-      REXML::XPath.each(an, "w:lvl") do |lvl|
-        ilvl = lvl.attributes["w:ilvl"].to_i
-        fmt  = REXML::XPath.first(lvl, "w:numFmt")&.attributes&.[]("w:val")
-        levels[ilvl] = { fmt: fmt || "bullet" }
-      end
-      result[id] = levels
+  xml = read_zip_entry(body, "word/numbering.xml")
+  return result unless xml
+  doc = REXML::Document.new(xml)
+  REXML::XPath.each(doc, "//w:abstractNum") do |an|
+    id = an.attributes["w:abstractNumId"]
+    levels = {}
+    REXML::XPath.each(an, "w:lvl") do |lvl|
+      ilvl = lvl.attributes["w:ilvl"].to_i
+      fmt  = REXML::XPath.first(lvl, "w:numFmt")&.attributes&.[]("w:val")
+      levels[ilvl] = { fmt: fmt || "bullet" }
     end
+    result[id] = levels
   end
   result
 rescue
@@ -54,16 +72,14 @@ end
 
 def read_styles(body)
   result = {}
-  Zip::File.open_buffer(StringIO.new(body)) do |zip|
-    entry = zip.find_entry("word/styles.xml")
-    break unless entry
-    doc = REXML::Document.new(entry.get_input_stream.read)
-    REXML::XPath.each(doc, "//w:style") do |s|
-      sid  = s.attributes["w:styleId"]
-      name = REXML::XPath.first(s, "w:name")&.attributes&.[]("w:val").to_s
-      if name =~ /^heading (\d)/i
-        result[sid] = { heading: $1.to_i }
-      end
+  xml = read_zip_entry(body, "word/styles.xml")
+  return result unless xml
+  doc = REXML::Document.new(xml)
+  REXML::XPath.each(doc, "//w:style") do |s|
+    sid  = s.attributes["w:styleId"]
+    name = REXML::XPath.first(s, "w:name")&.attributes&.[]("w:val").to_s
+    if name =~ /^heading (\d)/i
+      result[sid] = { heading: $1.to_i }
     end
   end
   result

data/lib/clacky/default_skills/cron-task-creator/SKILL.md

@@ -17,21 +17,14 @@ Storage:
   ~/.clacky/schedules.yml        # All scheduled plans (YAML list)
   ~/.clacky/logger/clacky-*.log  # Execution logs (daily rotation)
 
-WebUI Task Panel (Clacky Web Interface):
-  - Automatically reads tasks/ + schedules.yml and renders the task list
-  - Each row shows task name, cron expression, and content preview
-  - Action buttons: ▶ Run (execute now), ✎ Edit (edit in session), ✕ (delete)
-  - Run button triggers POST /api/tasks/run → executes task in a new session
-
-API Endpoints (available when clacky server is running):
-  GET    /api/tasks              → list all tasks
-  POST   /api/tasks              → create task {name, content}
-  GET    /api/tasks/:name        → get task content
-  DELETE /api/tasks/:name        → delete task
-  POST   /api/tasks/run          → run immediately {name}
-  GET    /api/schedules          → list all schedules
-  POST   /api/schedules          → create schedule {name, task, cron}
-  DELETE /api/schedules/:name    → delete schedule
+API Base: http://${CLACKY_SERVER_HOST}:${CLACKY_SERVER_PORT}
+
+Cron-Tasks API (unified — manages task file + schedule together):
+  GET    /api/cron-tasks              → list all cron tasks with schedule info
+  POST   /api/cron-tasks              → create task + schedule {name, content, cron, enabled?}
+  PATCH  /api/cron-tasks/:name        → update {content?, cron?, enabled?}
+  DELETE /api/cron-tasks/:name        → delete task file + schedule
+  POST   /api/cron-tasks/:name/run    → execute immediately (creates a new session)
 ```
 
 ## Cron Expression Quick Reference
@@ -54,10 +47,11 @@ Field order: `minute hour day-of-month month day-of-week`
 
 ### 1. LIST — Show all tasks
 
-When user asks "what tasks do I have", "list scheduled tasks", etc.:
+```bash
+curl -s http://${CLACKY_SERVER_HOST}:${CLACKY_SERVER_PORT}/api/cron-tasks
+```
 
-1. Run `ruby ~/.clacky/skills/cron-task-creator/scripts/list_tasks.rb`
-2. Display results: task name, cron schedule, enabled status, last run status
+Display each task: name, cron schedule, enabled status, content preview.
 
 If no tasks exist, inform the user and offer to create one or show templates.
 
@@ -69,15 +63,14 @@ If no tasks exist, inform the user and offer to create one or show templates.
 
 **Step 1: Gather required info** (only ask for what's missing)
 - What should the task DO? (goal, behavior, output format)
-- How often should it run? (or is it manual-only?)
+- How often should it run? (or is it manual-only without a schedule?)
 - Any specific parameters? (URLs, file paths, output location, language)
 
 **Step 2: Generate task name**
 - Rule: only `[a-z0-9_-]`, lowercase, no spaces
 - Examples: `daily_report`, `price_monitor`, `weekly_summary`
 
-**Step 3: Write the task prompt file**
-Path: `~/.clacky/tasks/<name>.md`
+**Step 3: Write the task prompt**
 
 The prompt must be:
 - **Self-contained**: the agent running it has zero prior context — include everything needed
@@ -85,7 +78,7 @@ The prompt must be:
 - **Detailed**: include URLs, file paths, output format, language, expected output location
 
 Good task prompt example:
-```markdown
+```
 You are a price monitoring assistant. Complete the following task:
 
 ## Goal
@@ -100,14 +93,17 @@ Check the current BTC price on CoinGecko, compare with yesterday's price, and lo
 Execute immediately.
 ```
 
-**Step 4: Write file and add schedule**
+**Step 4: Create via API**
 
 ```bash
-# Write task file
-ruby ~/.clacky/skills/cron-task-creator/scripts/manage_task.rb create "<name>" "<content>"
-
-# Add schedule (if applicable)
-ruby ~/.clacky/skills/cron-task-creator/scripts/manage_schedule.rb add "<name>" "<task_name>" "<cron_expr>"
+curl -s -X POST http://${CLACKY_SERVER_HOST}:${CLACKY_SERVER_PORT}/api/cron-tasks \
+  -H "Content-Type: application/json" \
+  -d '{
+    "name": "task_name",
+    "content": "task prompt content...",
+    "cron": "0 9 * * *",
+    "enabled": true
+  }'
 ```
 
 **Step 5: Confirm creation**
@@ -116,7 +112,6 @@ ruby ~/.clacky/skills/cron-task-creator/scripts/manage_schedule.rb add "<name>"
 ✅ Task created successfully!
 
 📋 Task name: daily_standup
-📄 File: ~/.clacky/tasks/daily_standup.md
 ⏰ Schedule: Weekdays at 09:00 (cron: 0 9 * * 1-5)
 
 View and manage this task in the Clacky WebUI → Tasks panel. Click ▶ Run to execute immediately.
@@ -126,24 +121,27 @@ View and manage this task in the Clacky WebUI → Tasks panel. Click ▶ Run to
 
 ### 3. EDIT — Modify an existing task
 
-When the user wants to change task content, cron schedule, or rename:
+**Step 1**: Identify the task (if unclear, LIST first and ask)
 
-**Step 1**: Identify the task to modify (if unclear, LIST first and ask)
+**Step 2**: Show current state via LIST or ask user to confirm
 
-**Step 2**: Show current state (first 10 lines + cron expression)
-
-**Step 3**: Determine what to change
-- Prompt only → rewrite `~/.clacky/tasks/<name>.md`
-- Schedule only → update `cron` field in `schedules.yml`
-- Both → do both
-- Rename → rename .md file + update schedules.yml
+**Step 3**: Update via API
 
 ```bash
-# Update task content
-ruby ~/.clacky/skills/cron-task-creator/scripts/manage_task.rb update "<name>" "<new_content>"
-
-# Update cron schedule
-ruby ~/.clacky/skills/cron-task-creator/scripts/manage_schedule.rb update "<schedule_name>" "<new_cron>"
+# Update content only
+curl -s -X PATCH http://${CLACKY_SERVER_HOST}:${CLACKY_SERVER_PORT}/api/cron-tasks/task_name \
+  -H "Content-Type: application/json" \
+  -d '{"content": "new prompt content..."}'
+
+# Update cron schedule only
+curl -s -X PATCH http://${CLACKY_SERVER_HOST}:${CLACKY_SERVER_PORT}/api/cron-tasks/task_name \
+  -H "Content-Type: application/json" \
+  -d '{"cron": "0 8 * * 1-5"}'
+
+# Update both
+curl -s -X PATCH http://${CLACKY_SERVER_HOST}:${CLACKY_SERVER_PORT}/api/cron-tasks/task_name \
+  -H "Content-Type: application/json" \
+  -d '{"content": "...", "cron": "0 8 * * 1-5"}'
 ```
 
 **Step 4**: Confirm changes
@@ -151,7 +149,6 @@ ruby ~/.clacky/skills/cron-task-creator/scripts/manage_schedule.rb update "<sche
 ```
 ✅ Task updated!
 📋 daily_standup
-  Prompt: updated ✓
   Schedule: 0 9 * * 1-5 → 0 8 * * 1-5 (now weekdays at 08:00)
 ```
 
@@ -160,7 +157,15 @@ ruby ~/.clacky/skills/cron-task-creator/scripts/manage_schedule.rb update "<sche
 ### 4. ENABLE / DISABLE — Toggle a task
 
 ```bash
-ruby ~/.clacky/skills/cron-task-creator/scripts/manage_schedule.rb toggle "<schedule_name>" true|false
+# Disable
+curl -s -X PATCH http://${CLACKY_SERVER_HOST}:${CLACKY_SERVER_PORT}/api/cron-tasks/task_name \
+  -H "Content-Type: application/json" \
+  -d '{"enabled": false}'
+
+# Enable
+curl -s -X PATCH http://${CLACKY_SERVER_HOST}:${CLACKY_SERVER_PORT}/api/cron-tasks/task_name \
+  -H "Content-Type: application/json" \
+  -d '{"enabled": true}'
 ```
 
 Confirm:
@@ -180,15 +185,22 @@ Always confirm before deleting (unless the user has explicitly said to delete):
 ```
 
 ```bash
-ruby ~/.clacky/skills/cron-task-creator/scripts/manage_task.rb delete "<name>"
+curl -s -X DELETE http://${CLACKY_SERVER_HOST}:${CLACKY_SERVER_PORT}/api/cron-tasks/task_name
 ```
 
 ---
 
 ### 6. HISTORY — View run history
 
+Read the daily log files directly:
+
 ```bash
-ruby ~/.clacky/skills/cron-task-creator/scripts/task_history.rb "<task_name>"
+grep "task_name" ~/.clacky/logger/clacky-$(date +%Y-%m-%d).log | tail -20
+```
+
+Or search across recent days:
+```bash
+grep -h "task_name" ~/.clacky/logger/clacky-*.log | tail -30
 ```
 
 Display format:
@@ -198,24 +210,21 @@ Display format:
 Mar 10  19:00  ❌ Failed  — JSON::ParserError: unexpected end of input
 Mar 09  19:00  ✅ Success — took 1m 42s
 Mar 08  19:00  ✅ Success — took 2m 10s
-Mar 07  19:00  ⚠️ Skipped — (task was disabled)
-
-Recent error:
-  JSON::ParserError at line 226
-  Possible cause: API response was truncated or empty
 ```
 
 ---
 
 ### 7. RUN NOW — Execute immediately
 
+```bash
+curl -s -X POST http://${CLACKY_SERVER_HOST}:${CLACKY_SERVER_PORT}/api/cron-tasks/task_name/run
 ```
-▶️ Go to the Clacky WebUI → Tasks panel, find the task, and click ▶ Run.
 
-The task will execute in a new session. You can watch it run in real time via the WebUI.
+This creates a new session. Tell the user:
+```
+▶️ Task started in a new session.
+   View it in the Clacky WebUI → Sessions panel.
 ```
-
-If the user wants to run the task in the current session, read the task file and execute the instructions directly.
 
 ---
 
@@ -243,8 +252,6 @@ Tell me which one interests you, or describe your own use case!
 ## Important Notes
 
 - Task names: only `[a-z0-9_-]`, no spaces, no uppercase
-- When modifying `schedules.yml`: always read → modify → write back the full file (never append directly)
 - Task prompt files must be **self-contained** — the executing agent has no prior memory
 - Clacky server must be running for cron to trigger automatically (checked every minute)
 - The WebUI Task Panel is the preferred interface for managing tasks — always remind the user to check it after changes
-- Path expansion: always use absolute paths, expand `~` to the actual home directory