docs: comprehensive README.md with usage, deployment, and testing guide

[konard]

Summary

• Replaces the template README with comprehensive documentation for Link.Assistant.Router
• Adds scripts/test-manual.sh for automated end-to-end testing of all endpoints
• Adds changelog fragment for the documentation addition
• Merges latest main (v0.3.0 release) and fixes Cargo.lock version mismatch

README covers

• Architecture overview — how the proxy sits between clients and Anthropic API
• Quick start — build, configure, start, issue tokens, make requests
• Claude Code integration — step-by-step setup for routing Claude Code through the proxy
• API reference — all endpoints (/health, /api/tokens, proxy routes) with request/response examples
• Configuration — all environment variables with defaults and descriptions
• Docker deployment — build, run, and Docker Compose example
• VPS deployment — systemd service setup for production
• Token system — lifecycle, format (JWT with la_sk_ prefix), and security notes
• Testing — unit tests, integration tests, manual testing, and the test script
• Project structure — file-by-file description of the codebase

Manual testing script

scripts/test-manual.sh automatically:

1. Creates temporary OAuth credentials
2. Builds and starts the router
3. Tests health check endpoint
4. Issues tokens and validates the response format
5. Tests proxy authentication (missing, invalid, wrong-prefix, valid tokens)
6. Tests query string preservation
7. Reports pass/fail for each test
8. Cleans up on exit

All features from issue #1 were verified against the implementation.

Test plan

• cargo fmt --check passes
• cargo clippy --all-targets --all-features passes (0 warnings)
• cargo test passes (15 unit + 9 integration = 24 tests)
• CI pipeline passes (all checks green)

Fixes #3

🤖 Generated with Claude Code

[konard]

🤖 Solution Draft Log

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

💰 Cost estimation:

• Public pricing estimate: $3.943015
• Calculated by Anthropic: $1.947406 USD
• Difference: $-1.995609 (-50.61%)

🤖 Models used:

• Tool: Claude
• Requested: opus
• Main model: Claude Opus 4.6 (ID: claude-opus-4-6, Anthropic, cutoff: 2025-05)
  📎 Log file uploaded as Gist (878KB)
  🔗 View complete solution draft log

---

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

[konard]

🔄 Auto-restart triggered (attempt 1)

Reason: CI failures detected

Starting new session to address the issues.

---

Auto-restart-until-mergeable mode is active. Will continue until PR becomes mergeable.

[konard]

🔄 Auto-restart-until-mergeable Log (iteration 1)

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

💰 Cost estimation:

• Public pricing estimate: $3.637675
• Calculated by Anthropic: $2.137990 USD
• Difference: $-1.499685 (-41.23%)

🤖 Models used:

• Tool: Claude
• Requested: opus
• Main model: Claude Opus 4.6 (ID: claude-opus-4-6, Anthropic, cutoff: 2025-05)
  📎 Log file uploaded as Gist (1836KB)
  🔗 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