chore: update model references to latest versions across docs and code

- Update default summarize model to `claude-sonnet-4-5`
- Replace `gpt-4o` references with `gpt-5.2` throughout docs
- Replace `gpt-4o-mini` references with `gpt-5-mini`
- Add MiniMax-M2.5 and M2.5-lightning to static models list
- Update image generation warning to suggest `gpt-5.2`
- Update OpenAI chat example script to use `gpt-5-mini`
- Update REST API docs and examples with current model names

cmd/generate_changelog/README.md

@@ -246,7 +246,7 @@ Set the model via environment variable:
 ```bash
 export FABRIC_CHANGELOG_SUMMARIZE_MODEL=claude-opus-4
 # or
-export FABRIC_CHANGELOG_SUMMARIZE_MODEL=gpt-4
+export FABRIC_CHANGELOG_SUMMARIZE_MODEL=gpt-5.2
 ```
 
 AI summaries are cached and only regenerated when:

cmd/generate_changelog/internal/changelog/summarize.go

@@ -7,7 +7,7 @@ import (
 	"strings"
 )
 
-const DefaultSummarizeModel = "claude-sonnet-4-20250514"
+const DefaultSummarizeModel = "claude-sonnet-4-5"
 const MinContentLength = 256 // Minimum content length to consider for summarization
 
 const prompt = `# ROLE