Update default reasoning model to GPT-5

[devin-ai-integration]

Update default reasoning model to GPT-5

Summary

This PR updates the default reasoning model across the entire Talos codebase from gpt-4o to gpt-5. The changes affect CLI commands, daemon operations, skills, memory systems, documentation, and test files while preserving intentional uses of gpt-4o-mini and other model variants.

Key changes:

• Updated default model parameters in CLI commands (main.py, daemon.py, proposals.py)
• Updated skill defaults (twitter_voice.py, twitter_persona.py)
• Updated memory system defaults (memory.py)
• Updated documentation and examples across docs/ and AGENTS.md
• Updated integration tests to use gpt-5 for consistency
• Fixed daemon.py inconsistency (was using gpt-4 instead of gpt-4o)

Preserved unchanged:

• All gpt-4o-mini references (intentionally using mini model variant)
• utils/llm.py (uses different naming conventions like o4-mini, o3-deep-research)

Review & Testing Checklist for Human

⚠️ CRITICAL: Verify GPT-5 model availability in your OpenAI account before merging - this PR will break all functionality if GPT-5 isn't available yet

• Test basic CLI functionality: Run uv run talos --help and uv run talos "test query" to ensure the agent still initializes and responds
• Verify model access: Confirm your OpenAI API key has access to GPT-5 model
• Spot check remaining references: Search codebase for any missed gpt-4o references that should have been updated
• Test daemon mode: Verify uv run talos daemon starts successfully with new defaults

---

Diagram

%%{ init : { "theme" : "default" }}%%
graph TD
    CLI["src/talos/cli/main.py<br/>Primary CLI entry point"]:::major-edit
    Daemon["src/talos/cli/daemon.py<br/>Continuous operation"]:::major-edit  
    Proposals["src/talos/cli/proposals.py<br/>Governance CLI"]:::major-edit
    
    Skills["src/talos/skills/<br/>twitter_voice.py<br/>twitter_persona.py"]:::major-edit
    Memory["src/talos/core/memory.py<br/>Memory system"]:::major-edit
    
    Docs["AGENTS.md<br/>docs/ folder<br/>Documentation"]:::minor-edit
    Tests["tests/<br/>integration_tests/<br/>Test files"]:::minor-edit
    
    Preserved["utils/llm.py<br/>*-mini references<br/>Preserved unchanged"]:::context
    
    CLI --> Skills
    CLI --> Memory
    Daemon --> Memory
    Skills --> Memory
    
    subgraph Legend
        L1["Major Edit"]:::major-edit
        L2["Minor Edit"]:::minor-edit  
        L3["Context/No Edit"]:::context
    end

    
    classDef major-edit fill:#90EE90
    classDef minor-edit fill:#87CEEB
    classDef context fill:#FFFFFF

Loading

Notes

• 21 files changed with clean 1:1 replacement of gpt-4o → gpt-5 (37 insertions, 37 deletions)
• Model availability risk: This change assumes GPT-5 is available through OpenAI's API, which may not be the case yet
• Behavioral impact: GPT-5 may have different performance characteristics than GPT-4o
• Link to Devin run: https://app.devin.ai/sessions/371639a562aa444681e1a92ddf0d8de0
• Requested by: @talos-agent

[devin-ai-integration]

🤖 Devin AI Engineer

I'll be helping with this pull request! Here's what you should know:

✅ I will automatically:

• Address comments on this PR. Add '(aside)' to your comment to have me ignore it.
• Look at CI failures and help fix them

Note: I can only respond to comments from users who have write access to this repository.

⚙️ Control Options:

• Disable automatic comment and CI monitoring

[finnjclancy]

yo devin, should've changed 4o to openai_model_name or sum so you don't have to change all those files every time openai release a new model