refactor(core): ♻️ Flatten update_plan input and require core fields

[HayWolf]

Summary

• Flatten the update_plan tool schema by removing the redundant nested plan object so the model only sees top-level fields.
• Add a required array (title, summary, context, design, keyImplementation, steps, verification, risks) so empty-argument calls are rejected at generation time instead of after execution.
• Make the runtime validation errors self-correcting by listing the expected fields and a minimal valid JSON example, and drop the .get("plan") fallback in build_plan_artifact_from_tool_input.

Motivation

Models (e.g. Claude) repeatedly called update_plan with empty {} arguments and looped on the error update_plan requires a non-empty title .... The schema had no required constraint and exposed an ambiguous nested plan object mirroring the top-level fields, so the machine-readable contract said everything was optional and the model could not self-correct from the opaque error.

Test Plan

• cargo fmt --check --manifest-path src-tauri/Cargo.toml
• cargo test --locked --manifest-path src-tauri/Cargo.toml --lib plan (37 passed)
• Run full cargo test in CI

🤖 Generated with TiyCode

[github-actions]

AI Code Review Summary

PR: #228 (refactor(core): ♻️ Flatten update_plan input and require core fields)
Preferred language: English

Overall Assessment

No blocking issue was detected in the reviewed diff; keep focused regression testing before merge.

Major Findings by Severity

No major issues identified from the reviewed diff.

Actionable Suggestions

• Address the highest severity findings first and add targeted tests for changed logic.

Potential Risks

• Potential hidden risks remain in edge cases not covered by the current diff context.

Test Suggestions

• Add happy-path + boundary + failure-path tests for touched modules.

File-Level Coverage Notes

• src-tauri/src/core/agent_session_execution.rs: ok (Error messages are clearer and use consistent phrasing. Validation logic remains correct.)
• src-tauri/src/core/agent_session_tests.rs: ok (Test expectations correctly updated to match the flattened schema and required fields.)
• src-tauri/src/core/agent_session_tools.rs: ok (Schema flattened, redundant nested plan object removed, required fields added. Description updated to forbid nested wrappers.)
• src-tauri/src/core/plan_checkpoint.rs: ok (Plan artifact builder simplified to read directly from tool_input without checking for nested 'plan' key.)

Inline Downgraded Items (processed but not inline)

• None

Coverage Status

• Target files: 4
• Covered files: 4
• Uncovered files: 0
• No-patch/binary covered as file-level: 0
• Findings with unknown confidence (N/A): 0

Uncovered list:

• None

No-patch covered list:

• None

Runtime/Budget

• Rounds used: 1/4
• Planned batches: 1
• Executed batches: 1
• Sub-agent runs: 1
• Planner calls: 1
• Reviewer calls: 1
• Model calls: 2/64
• Structured-output summary-only degradation: NO

[github-actions]

Automated PR review completed.

• Findings kept: 0
• Findings with unknown confidence: 0
• Inline comments attempted: 1
• Target files: 4
• Covered files: 4
• Uncovered files: 0
  See the summary comment for detailed analysis and coverage details.

[github-actions]

Automated review completed for this PR diff. No concrete inline issue was selected after aggregation.