Render AI markdown and signed values

[konard]

Summary

• Add an AI message formatter for **bold**, inline code, fenced code blocks, and signed numeric values.
• Wire the formatter into the AI transcript output so markdown delimiters are rendered as terminal styling instead of literal text.
• Color signed positive values with the long/green theme color and signed negative values with the short/red theme color.
• Add regression coverage plus a reusable screenshot experiment for PR review.

Reproduction

• Ask AI chat a question that returns markdown-like text such as **BYN/USD** and a signed value like (+0.24%).
• Before this change, the transcript showed literal ** markers and signed values were not highlighted.
• After this change, the markers are stripped into styling and values such as +0.24, +890.05, -116, and -187.09 are highlighted.

Screenshot

Tests

• npm test -- tests/cli.test.tsx -t "renders AI markdown markers" failed before the fix and passes after it.
• npm test -- tests/cli.test.tsx -t "AI message markup|renders AI markdown markers"
• npm test -- tests/cli.test.tsx
• npm run typecheck
• npm test
• npm run build
• npx tsx experiments/ai-markup-shot.ts

Fixes #37

[konard]

Working session summary

Implemented and pushed the fix to PR 38: #38

What changed:

• Added AI message formatting in src/cli/ai-markup.tsx.
• Wired AI chat output to render **bold**, inline/fenced code, and signed values.
• Positive signed values render green; negative signed values render red.
• Added regression tests in tests/cli.test.tsx.
• Added the requested screenshot: https://github.com/konard/Payel-git-ol-Tradefast/blob/issue-37-a05df9f50d09/docs/screenshots/ai-markup.png?raw=true

Verification:

• npm run typecheck
• npm test
• npm run build
• npx tsx experiments/ai-markup-shot.ts
• Remote CI build-and-test passed for commit f1374e6.

PR 38 is marked ready for review and the working tree is clean.

---

This summary was automatically extracted from the AI working session output.

[konard]

🤖 Solution Draft Log

This log file contains the complete execution trace of the AI solution draft process.

💰 Cost estimation:

• Model: GPT-5.5
• Provider: OpenAI
• Public pricing estimate: $8.655539

📊 Context and tokens usage:

• 197.6K / 1.1M (19%) input tokens, 25.3K / 128K (20%) output tokens

Total: (197.6K + 5.5M cached) input tokens, 25.3K output tokens, $8.655539 cost

🤖 Models used:

• Tool: OpenAI Codex
• Requested: gpt-5.5
• Model: GPT-5.5 (gpt-5.5)

📎 Log file uploaded as Repository (33054KB)

• View complete solution draft log

---

Now working session is ended, feel free to review and add any feedback on the solution draft.

[konard]

✅ Ready to merge

This pull request is now ready to be merged:

• All CI checks have passed
• No merge conflicts
• No pending changes

---

Monitored by hive-mind with --auto-restart-until-mergeable flag