Merge pull request #114 from OEvortex/new-providers

New providers

Author: OEvortex

.github/workflows/deploy-docs.yml

@@ -0,0 +1,96 @@
+name: Deploy Documentation to GitHub Pages
+
+on:
+  push:
+    branches:
+      - main
+      - new-providers
+    paths:
+      - 'docs/**'
+      - 'mkdocs.yml'
+      - '.github/workflows/deploy-docs.yml'
+  pull_request:
+    branches:
+      - main
+    paths:
+      - 'docs/**'
+      - 'mkdocs.yml'
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+concurrency:
+  group: "pages"
+  cancel-in-progress: false
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.11'
+          cache: 'pip'
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install mkdocs mkdocs-material pymdown-extensions
+
+      - name: Build documentation
+        run: mkdocs build
+
+      - name: Upload artifact
+        uses: actions/upload-pages-artifact@v2
+        with:
+          path: 'site'
+
+  deploy:
+    if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+    needs: build
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    runs-on: ubuntu-latest
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v2
+
+  test-pr:
+    if: github.event_name == 'pull_request'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.11'
+          cache: 'pip'
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install mkdocs mkdocs-material pymdown-extensions
+
+      - name: Build documentation (test)
+        run: mkdocs build
+
+      - name: Check for build errors
+        run: |
+          if [ ! -d "site" ]; then
+            echo "❌ Documentation build failed!"
+            exit 1
+          fi
+          echo "✅ Documentation built successfully!"

.gitignore

@@ -170,4 +170,5 @@ blackbox_private_key.pem
 _plans/*
 !_plans/.gitkeep
 .zenflow/
-.blackboxrules
+.blackboxrules
+.claude

AGENTS.md

@@ -8,6 +8,9 @@
       If the subagent tool is available, the main Copilot agent acts strictly as an orchestrator.
       All research, planning, and heavy reasoning MUST be delegated to specialized subagents.
       Note: There may be other subagents available beyond those listed below.
+      Always call multiple subagents in parallel.
+      Firstly break down task into subtasks.
+      Then, for each subtask, call the appropriate subagent or custom agent.
     </Overview>
 
     <AvailableSubagents>
@@ -29,26 +32,6 @@
           <Item>Plan multi-file refactors</Item>
         </MustNot>
       </Subagent>
-
-      <Subagent>
-        <Name>Docstring</Name>
-        <Role>Professional Docstring Generator Agent</Role>
-        <Responsibilities>
-          <Item>Read existing Python code</Item>
-          <Item>Generate accurate, professional docstrings</Item>
-          <Item>Insert docstrings without changing logic</Item>
-        </Responsibilities>
-        <WhenToCall>
-          <Condition>User requests documentation or docstring generation</Condition>
-          <Condition>Code lacks or has poor-quality docstrings</Condition>
-          <Condition>Preparing code for release or public use</Condition>
-        </WhenToCall>
-        <MustNot>
-          <Item>Change executable behavior</Item>
-          <Item>Invent undocumented functionality</Item>
-        </MustNot>
-      </Subagent>
-
       <Subagent>
         <Name>Plan</Name>
         <Role>Planning & Task Decomposition Agent</Role>
@@ -144,7 +127,7 @@
         <Description>AI provider implementations</Description>
         <Variants>
           <Variant>
-            <Path>OPENAI/</Path>
+            <Path>Openai_comp/</Path>
             <Description>OpenAI-compatible wrappers</Description>
           </Variant>
           <Variant>
@@ -271,6 +254,15 @@ class MyProvider(OpenAICompatibleProvider):
     <Rule>Add tests for new behavior</Rule>
     <Rule>Validate provider discovery and model registration</Rule>
     <Rule>Use pytest under tests/</Rule>
+    <Structure>
+      <Rule>Place unit tests in tests/providers/ for provider implementations</Rule>
+      <Rule>Use unittest.TestCase for unit tests with setUp() methods</Rule>
+      <Rule>Mock external dependencies using FakeResp or similar patterns</Rule>
+      <Rule>Test parsing, validation, and error handling</Rule>
+      <Rule>Name test files as test_&lt;provider_name&gt;.py</Rule>
+      <Rule>Interactive/stress tests use pytestmark = pytest.mark.skip() to avoid running in CI</Rule>
+      <Rule>All test files must pass: uvx ruff check . and uvx ty check .</Rule>
+    </Structure>
   </TestingGuidelines>
 
   <DocsToUpdate>

Prompts/ReverseEngineering.md

@@ -90,9 +90,10 @@ These providers are only available in the standard implementation format.
 | 16 | **QwenLM** | `webscout/Provider/QwenLM.py` |
 | 17 | **SearchChat** | `webscout/Provider/searchchat.py` |
 | 18 | **TurboSeek** | `webscout/Provider/turboseek.py` |
-| 19 | **WrDoChat** | `webscout/Provider/WrDoChat.py` |
+| 19 | **Upstage** | `webscout/Provider/Upstage.py` |
+| 20 | **WrDoChat** | `webscout/Provider/WrDoChat.py` |
 
-**Total: 19 providers with only normal implementation**
+**Total: 20 providers with only normal implementation**
 
 ---
 
@@ -130,7 +131,7 @@ These providers are only available in the OpenAI-compatible format and have no s
 
 ### Implementation Coverage
 
-- **Total Normal Implementations**: 57 (37 hybrid + 20 normal-only)
+- **Total Normal Implementations**: 58 (37 hybrid + 21 normal-only)
 - **Total OpenAI Implementations**: 42 (37 hybrid + 5 OpenAI-only)
 - **Providers with Multiple Options**: 37 (59% of all providers)
 
@@ -230,7 +231,7 @@ provider = Groq()
 response = provider.chat("Hello, how are you?")
 
 # OpenAI-Compatible Provider
-from webscout.Provider.OPENAI import groq
+from webscout.Provider.Openai_comp import groq
 client = groq.GroqProvider()
 response = client.chat.completions.create(
     model="mixtral-8x7b",