- Add repeat_penalty=1.15, presence_penalty=1.5, frequency_penalty=0.5 for qwen3 when force_reasoning is enabled
- Add system prompt addon: 'Do not repeat tool calls. If a tool fails with an [ERROR], do not retry the exact same parameters'
- Add debug output for stop sequences in REASONING MODE DEBUG

- Add pattern for <tool>financial_data_fetcher>{JSON}</tool>
- Add pattern for <tool_call><tool>financial_data_fetcher>{JSON}</tool></tool_call>
- Added to both coder CLI and ToolCallParser

Add Format 3 to parse_tool_calls_from_content:
- Parse <tool_call><tool><name>...</name><arguments>JSON</arguments></tool></tool_call>
- Also handles incomplete closing tags

- Add --dump argument to CLI
- Add dump output for tools schema in both streaming and non-streaming
- Add dump output for raw response content
- Add dump output for parsed tool calls
- Works for both streaming and non-streaming requests

- Add pattern for nested tool_call with multiple tool blocks
- Add pattern for tool name as tag (e.g., <list_files>)
- Add deduplication to avoid duplicate tool calls
- ToolCallParser used as fallback for all model parsers via ModelParserAdapter

- Add pattern for <tool_call><tool><toolname><key>value</key></toolname></tool></tool_call>
- Add pattern for standalone nested tool format <tool><toolname><key>value</key></toolname></tool>
- Update strip_tool_calls_from_content to remove these formats from content
- Tool name is now parsed as the XML tag itself with nested child tags as arguments

- Add local import of json inside raw_stream_generate() nested function
- This fixes NameError that occurred when streaming responses

- Removed incorrect 'await' on generate_stream which returns an async generator

- Added pattern for <tool_call><tool><name>...</name><parameters><key>value</key></parameters></tool></tool_call>
- Added pattern for standalone <tool><name>...</name><parameters><key>value</key></parameters></tool>
- Extracts key-value pairs from nested XML tags inside <parameters>

- Simplified ApexBig50Parser to only keep unique patterns (markdown JSON, react)
- Complex XML parsing is now handled by ToolCallParser as the fallback
- This eliminates code duplication between the two parsers

- Added pattern for <tool_call><tool><function>...</function><parameters>...</parameters></tool></tool_call>
- Added pattern for standalone <tool><function>...</function><parameters>...</parameters></tool>
- Added same patterns to ApexBig50Parser

- Added support for <tool_call><tool><name>...</name><arguments>...</arguments></tool></tool_call> format
- Added support for multiple tool calls in <tool_call> wrapper
- Added same patterns to ApexBig50Parser for direct handling
- Added exception handling for formatter.format_full() to prevent TypeError
- Added fallback response when formatted_response is None
- ToolCallParser now serves as fallback for all specific model parsers

- Added new pattern to parse <tool><action>...</action><parameters>...</parameters></tool>
- Handles both JSON and XML-style key-value pairs in parameters
- Example:
  <tool>
  <action>search</action>
  <parameters>
    <query>Apple AAPL Q4 financials Net Income Revenue</query>
  </parameters>
  </tool>

- Added new pattern to parse <tool>name</tool><tool_call>JSON</tool_call> format
- Handles both closing tag (</tool_call>) and end-of-string as terminator
- Works with formats like:
  <tool>search</tool>
  <tool_call>
  {"query": "Apple AAPL Q4 financial report"}
  </tool_call>

- Added debug output to ToolCallParser.extract_tool_calls() method
- Shows when parser is called, input text (first 200 chars), and output
- Debug logging follows existing codebase pattern using print() with DEBUG prefix
- Useful for troubleshooting tool call extraction issues

- Added _parse_xml_style_tool_calls() method to parse XML format like:
  <tool><name>search</name><arguments>{...}</arguments></tool>
- Modified extract_tool_calls() to use XML parsing as fallback
- ToolCallParser now serves as fallback for all specific model parsers
  via ModelParserAdapter (QwenParser, DeepSeekParser, LlamaParser,
  MistralParser, ClaudeParser, CommandRParser, GemmaParser, GrokParser,
  PhiParser, ApexBig50Parser)

Support for:
<tool_call>
<tool>
<name>search</name>
<arguments>{"query": "..."}</arguments>
</tool>
</tool_call>

Support for:
<tool_call>
<tool>
<name>financial_data_lookup</name>
<param>...</param>
</tool>
</tool_call>

Support for format:
<tool>yahoo_finance_api</tool>[{"symbol": "AAPL", ...}]

Support for:
<tool_call>
<tool>
<action>search</action>
<parameters>
  <query>...</query>
</parameters>
</tool>
</tool_call>

current_manager is the individual model manager which doesn't have 'models'.
multi_model_manager has the 'models' dict with all loaded models.

- Add safety check for None formatted_response in debug output
- Add debug logging when litellm fallback fails

When resolving 'default', skip keys like 'default', 'image', 'audio',
'image:*', 'audio:*' to find the first actual LLM model.

When resolving 'default' model, skip the 'default' key in models dict
and return the first actual loaded model instead.

- Removed --force-all CLI flag
- Updated help text to document 'all' option
- Updated reasoning_choices to expand 'all' to all options
- Updated parsing logic to handle 'all' as string

When requested_model is 'default', get_resolved_model_name now:
1. First tries current_manager.default_model
2. Falls back to the first model in manager.models

This ensures the model family is correctly detected for parser selection.

When the model-specific parser (like QwenParser) doesn't find any
tool calls, fall back to ToolCallParser as a catch-all.

The regex pattern was missing <tool> - it only matched <tool_call>,
funktion>, and <tool_use>. Now it also matches <tool>.

Add custom XML tool format parser for <tool><action>...</action><object>...</object><properties>...</properties></tool>

The model was generating tool calls in this format:
<tool>
<action>search</action>
<object>financial_data</object>
<properties>
  <query>...</query>
</properties>
</tool>

Added parser support in ApexBig50Parser and strip_tool_calls_from_content
to handle this custom format.

- Bug 1: Skip format_tools_for_prompt in raw mode (already had condition)
- Bug 2: Use final_text (after reasoning) instead of generated_text for formatter
- Bug 3: Pass final_text to ModelParserAdapter instead of generated_text

This prevents reasoning from appearing in both content AND reasoning fields,
and allows the tool parser to properly extract tool calls without being
confused by reasoning tags.

- Add new --force-all CLI argument
- Update --force-reasoning help text to mention --force-all
- Handle --force-all in main function to expand to all reasoning options

- Add force_reasoning_prompt function with Big 10 family prefixes
- Add inject_system and force_reasoning parameters
- Update --force-reasoning CLI with comma-separated options
- Add --dump option to show raw output, parsed output, and litellm debug
- Fix stop tokens to include ]]> when prompt is selected
- Add mock strategy for fake reasoning stats
- Chain --system-prompt at start of existing system message
- Add 'raw' option to --force-reasoning
- Fix format_tools_for_prompt to skip in raw mode
- Pass tools to format_for_raw_completion in raw mode
- Add parse_and_format method to OpenAIFormatter for tool extraction
- Use parse_and_format in raw mode for correct tool extraction pipeline

Pipeline: Model output -> Extract reasoning (raw mode) -> ModelParserAdapter (extract tools) -> OpenAIFormatter (final format)