[Release]: v0.1.1 (#59)

* feature: add templates for PR and issues (#58)

* feature: add _resolve_schema_refs (#57)

* feature: add _resolve_schema_refs

* feature: add anyOf/oneOf in json schema in _resolve_schema_refs

* Update coverage badge for release/v0.1.1

* feature: properties missing finally works

* chore: fix tests, bump version

* Update coverage badge for release/v0.1.1

* chore: bump to beta

* chore: delete print

* Bugfix/fix responses streaming (#60)

* bugfix: fix responses API streaming

* chore: fix tests

* chore: ruff format

* chore: ruff format

* Update coverage badge for release/v0.1.1

* chore: split request_mapper.py to better maintainability

* bugfix: fix tests

* Update coverage badge for release/v0.1.1

* bugfix: responses API streaming function call in openclaw

* chore: bump version

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

Author: krakenalt

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,146 @@
+---
+name: Bug Report
+about: Report a bug to help us improve gpt2giga
+title: "[BUG] "
+labels: bug
+assignees: ''
+---
+
+## Bug Description
+
+<!-- A clear and concise description of the bug -->
+
+## Environment
+
+### gpt2giga Setup
+
+- **gpt2giga version**: <!-- e.g., 0.5.0 -->
+- **Installation method**:
+  - [ ] pip (`pip install gpt2giga`)
+  - [ ] uv (`uv tool install gpt2giga/ uv add gpt2giga`)
+  - [ ] Docker (`docker compose up`)
+  - [ ] From source (`pip install git+...`)
+
+- **Python version**: <!-- e.g., 3.10 -->
+- **OS**: <!-- e.g., Ubuntu 22.04, macOS 14.0, Windows 11 -->
+
+### GigaChat Configuration
+
+- **GigaChat model**: <!-- e.g., GigaChat, GigaChat-2-Max -->
+- **Auth settings**: <!-- e.g., OAuth(scope+creds), Basic(user+password) -->
+
+## How to Reproduce
+
+### Method Used
+
+- [ ] OpenAI Python SDK
+- [ ] curl
+- [ ] Other: <!-- specify -->
+
+### Request Payload
+
+<!--
+Provide the full request you're sending.
+Remove any sensitive data (credentials, tokens, etc.)
+-->
+
+<details>
+<summary>Request</summary>
+
+**For OpenAI SDK:**
+
+```python
+from openai import OpenAI
+
+client = OpenAI(base_url="http://localhost:8090", api_key="your-key")
+
+# Your request here
+completion = client.chat.completions.create(
+    model="gpt-4",
+    messages=[
+        {"role": "user", "content": "Your message"}
+    ],
+    # ... other parameters
+)
+```
+
+**For curl:**
+
+```bash
+curl -X POST http://localhost:8090/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer your-key" \
+  -d '{
+    "model": "gpt-4",
+    "messages": [
+      {"role": "user", "content": "Your message"}
+    ]
+  }'
+```
+
+</details>
+
+### Steps to Reproduce
+
+1. Start gpt2giga with: `...`
+2. Send request: `...`
+3. See error
+
+## Expected Behavior
+
+<!-- What you expected to happen -->
+
+## Actual Behavior
+
+<!-- What actually happened -->
+
+## Error Output
+
+<details>
+<summary>Error message / Traceback</summary>
+
+```
+Paste your error or traceback here
+```
+
+</details>
+
+## Logs
+
+<!--
+Set GPT2GIGA_LOG_LEVEL=DEBUG and provide relevant logs.
+Remove any sensitive information!
+-->
+
+<details>
+<summary>gpt2giga logs (DEBUG level)</summary>
+
+```
+Paste relevant logs here
+```
+
+</details>
+
+## Configuration
+
+<!-- Provide your .env file content (remove sensitive values!) -->
+
+<details>
+<summary>.env configuration</summary>
+
+```dotenv
+GPT2GIGA_HOST=localhost
+GPT2GIGA_PORT=8090
+GPT2GIGA_LOG_LEVEL=DEBUG
+# ... other settings
+```
+
+</details>
+
+## Additional Context
+
+<!-- Add any other context about the problem here -->
+
+## Possible Solution
+
+<!-- Optional: If you have any ideas on how to fix this -->

.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,133 @@
+## Description
+
+<!-- Provide a clear and concise description of what this PR does -->
+
+## Motivation
+
+<!-- Why is this change needed? Link to related issues if applicable -->
+
+Closes #<!-- issue number -->
+
+## Type of Change
+
+<!-- Mark the relevant option with an "x" -->
+
+- [ ] Bug fix (non-breaking change that fixes an issue)
+- [ ] New feature (non-breaking change that adds functionality)
+- [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
+- [ ] Documentation update
+- [ ] Code refactoring (no functional changes)
+- [ ] Performance improvement
+- [ ] Test coverage improvement
+- [ ] CI/CD or tooling change
+
+## Changes Made
+
+<!-- List the main changes made in this PR -->
+
+-
+-
+-
+
+## Testing
+
+<!-- Describe the tests you ran and how to reproduce them -->
+
+### Test Coverage
+
+- [ ] Unit tests added/updated
+- [ ] Integration tests added/updated (if applicable)
+- [ ] All existing tests pass locally
+
+### Manual Testing
+
+<!-- Describe any manual testing performed -->
+
+#### Method Used
+
+- [ ] OpenAI Python SDK
+- [ ] curl
+- [ ] Docker
+- [ ] Other: <!-- specify -->
+
+<details>
+<summary>Test commands / code</summary>
+
+**Example with OpenAI SDK:**
+
+```python
+from openai import OpenAI
+
+client = OpenAI(base_url="http://localhost:8090", api_key="your-key")
+
+completion = client.chat.completions.create(
+    model="gpt-4",
+    messages=[
+        {"role": "user", "content": "Test message"}
+    ],
+)
+print(completion.choices[0].message.content)
+```
+
+**Example with curl:**
+
+```bash
+curl -X POST http://localhost:8090/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer your-key" \
+  -d '{
+    "model": "gpt-4",
+    "messages": [{"role": "user", "content": "Test"}]
+  }'
+```
+
+</details>
+
+## Checklist
+
+<!-- Mark completed items with an "x" -->
+
+### Code Quality
+
+- [ ] Code follows the project's style guidelines
+- [ ] I have performed a self-review of my code
+- [ ] I have commented my code, particularly in hard-to-understand areas
+- [ ] My changes generate no new linter warnings (`make lint`)
+- [ ] Type checking passes (`make mypy`)
+- [ ] All tests pass (`make test`)
+
+### Documentation
+
+- [ ] I have updated the documentation accordingly
+- [ ] Docstrings follow Google style with imperative mood
+- [ ] I have added examples for new features (if applicable)
+- [ ] README.md updated (if applicable)
+
+### Dependencies
+
+- [ ] No new dependencies added
+- [ ] If dependencies added, they are justified and minimal
+- [ ] `uv.lock` updated (if dependencies changed)
+
+### Compatibility
+
+- [ ] Changes are compatible with Python 3.10-3.14
+- [ ] No use of `type[...]` syntax (use `Type[...]` for Python 3.8)
+- [ ] Async/sync variants both work correctly (if applicable)
+
+### Commits
+
+- [ ] Commit messages are clear and follow conventional commits style
+- [ ] Commits are logically organized
+- [ ] No debug code or commented-out code left in
+
+## Additional Context
+
+<!-- Add any other context, screenshots, or information about the PR here -->
+
+## Pre-merge Actions
+
+<!-- For maintainers -->
+
+- [ ] Changelog updated (if applicable)
+- [ ] Version bump considered (if applicable)

.pre-commit-config.yaml

@@ -15,20 +15,20 @@ repos:
     hooks:
       - id: ruff
         name: ruff check
-        entry: poetry run ruff check
+        entry: uv run ruff check
         language: system
         types_or: [python, pyi]
         args: [--fix]
       - id: ruff-format
         name: ruff format
-        entry: poetry run ruff format
+        entry: uv run ruff format
         language: system
         types_or: [python, pyi]
         args: [--config, pyproject.toml]
 
-#      - id: black
-#        name: black check
-#        entry: poetry run black .
-#        language: system
-#        types_or: [ python, pyi ]
-#        args: [--check]
+      - id: black
+        name: black check
+        entry: uv run black .
+        language: system
+        types_or: [ python, pyi ]
+        args: [--check]

gpt2giga/protocol/__init__.py

@@ -2,4 +2,8 @@
 from .request_mapper import RequestTransformer
 from .response_mapper import ResponseProcessor
 
-__all__ = ["AttachmentProcessor", "RequestTransformer", "ResponseProcessor"]
+__all__ = [
+    "AttachmentProcessor",
+    "RequestTransformer",
+    "ResponseProcessor",
+]

gpt2giga/protocol/content_utils.py

@@ -0,0 +1,64 @@
+import ast
+import json
+from typing import Any
+
+
+def ensure_json_object_str(value: Any) -> str:
+    """
+    Ensures the value is a valid JSON object string.
+
+    GigaChat requires function/tool results to be valid JSON objects.
+    The SDK `gigachat.models.Messages` expects `content: str`.
+
+    OpenAI-compatible clients often send:
+    - dict (ok)
+    - JSON string (needs json.loads)
+    - double JSON string (needs json.loads multiple times)
+    - python-like string (single quotes) — try ast.literal_eval
+
+    Args:
+        value: Any value that needs to be converted to JSON object string
+
+    Returns:
+        A valid JSON object string
+    """
+    if value is None:
+        return "{}"
+
+    if isinstance(value, bytes):
+        try:
+            value = value.decode("utf-8", errors="ignore")
+        except Exception:
+            return json.dumps({"result": str(value)}, ensure_ascii=False)
+
+    if isinstance(value, dict):
+        return json.dumps(value, ensure_ascii=False)
+
+    if isinstance(value, str):
+        s: Any = value.strip()
+        for _ in range(3):
+            if not isinstance(s, str):
+                break
+            if s == "":
+                return "{}"
+            try:
+                s = json.loads(s)
+                continue
+            except json.JSONDecodeError:
+                break
+
+        if isinstance(s, dict):
+            return json.dumps(s, ensure_ascii=False)
+        if isinstance(s, (list, int, float, bool)) or s is None:
+            return json.dumps({"result": s}, ensure_ascii=False)
+
+        if isinstance(s, str):
+            try:
+                lit = ast.literal_eval(s)
+                if isinstance(lit, dict):
+                    return json.dumps(lit, ensure_ascii=False)
+                return json.dumps({"result": lit}, ensure_ascii=False)
+            except Exception:
+                return json.dumps({"result": s}, ensure_ascii=False)
+
+    return json.dumps({"result": value}, ensure_ascii=False)