feat: add refine_message for interactive commit refinement

Users can now provide feedback to regenerate commit messages with
natural language guidance. The refine_message method accepts user
feedback and calls resolve_refinement_prompt to build a targeted LLM
request, enabling iterative message improvement before committing.

Author: Sephyi

CHANGELOG.md

@@ -8,10 +8,17 @@ SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-Commercial
 
 All notable changes to CommitBee are documented here.
 
-## `v0.6.0-rc.1` — Deep Understanding (release candidate)
+## `v0.6.0-dev` — Deep Understanding (release candidate)
+
+### UI/UX
+
+- **Interactive message refinement** — Added a "Refine" option to the candidate selection and confirmation menu. Users can provide feedback to the LLM (e.g., "more detail about the API change") to regenerate the message with natural language guidance.
+- **Native clipboard support** — Replaced external commands (`pbcopy`, `xclip`) with the `arboard` crate for a native, cross-platform clipboard implementation.
+- **Interactive commit editing** — Added an "Edit" option to the candidate selection and confirmation menu. Users can now refine the generated message using their system editor before committing.
 
 ### Semantic Analysis
 
+- **Full AST diffs for structs and enums** — `AstDiffer` now supports structured diffing for structs, enums, classes, interfaces, and traits. Detects added/removed fields, changed variants, and type modifications.
 - **Parent scope extraction** — Methods inside `impl`, `class`, or `trait` blocks now show their parent in the prompt: `CommitValidator > pub fn validate(...)`. Walks the AST tree through intermediate nodes (declaration_list, class_body). Verified across 7 languages (Rust, Python, TypeScript, Java, Go, Ruby, C#).
 - **Import change detection** — New `IMPORTS CHANGED:` prompt section shows added/removed import statements. Supports Rust `use`, JS/TS `import`, Python `from`/`import`, Node `require()`, and C/C++ `#include`. Capped at 10 entries.
 - **Doc-vs-code distinction** — `SpanChangeKind` enum classifies modified symbols as WhitespaceOnly, DocsOnly, Mixed, or Semantic. Doc-only changes suggest `docs` type. Modified symbols show `[docs only]` or `[docs + code]` suffix in the prompt.
@@ -30,21 +37,26 @@ All notable changes to CommitBee are documented here.
 - **Diff-based intent patterns** — Scans added lines for error handling (`Result`, `?`, `Err()`), test additions (`#[test]`, `assert!`), logging (`tracing::`, `debug!`), and dependency updates. Shown as `INTENT:` section in the prompt with confidence scores.
 - **Conservative type refinement** — High-confidence performance optimization patterns can override the base type to `perf`.
 
-### Prompt Quality
-
-- **Token budget rebalance** — Symbol budget reduced from 30% to 20% when structural diffs are available, freeing space for the raw diff. SYSTEM_PROMPT updated to guide the LLM to prefer STRUCTURED CHANGES for signature details.
-- **Unsafe constraint rule** — When `unsafe` is added to a function, a CONSTRAINTS rule instructs the LLM to mention safety justification in the commit body.
-
-### Fixes
+### Security
 
+- **Accurate secret scan line numbers** — The secret scanner now parses `@@` hunk headers to report accurate source line numbers for potential secrets, instead of absolute diff line numbers.
 - **API key validation ordering** — `set-key`, `get-key`, `init`, `config`, `completions`, and `hook` commands no longer require an API key to be present. CLI `--provider` flag now applies before keyring lookup.
 - **Platform-native keyring backends** — keyring v3 now uses macOS Keychain (`apple-native`), Windows Credential Manager (`windows-native`), and Linux Secret Service (`linux-native`) instead of a mock file-based backend.
 - **SecretString for API keys** — API keys stored as `secrecy::SecretString` in Config and provider structs. Memory zeroed on drop, never exposed except at HTTP header insertion.
 - **Overflow checks in release builds** — `overflow-checks = true` added to release profile for ANSSI-FR compliance.
 
+### Performance
+
+- **Optimized symbol dependency merging** — Improved `CommitSplitter` performance for large commits by pre-indexing symbols and optimizing diff scanning.
+
+### Prompt Quality
+
+- **Token budget rebalance** — Symbol budget reduced from 30% to 20% when structural diffs are available, freeing space for the raw diff. SYSTEM_PROMPT updated to guide the LLM to prefer STRUCTURED CHANGES for signature details.
+- **Unsafe constraint rule** — When `unsafe` is added to a function, a CONSTRAINTS rule instructs the LLM to mention safety justification in the commit body.
+
 ### Testing
 
-- **424 tests** total (up from 367 at v0.5.0).
+- **442 tests** total (up from 367 at v0.5.0).
 
 ## `v0.5.0` — Beyond the Diff
 
@@ -79,7 +91,7 @@ All notable changes to CommitBee are documented here.
 - **Evaluation harness** — 36 fixtures covering all 11 commit types, AST features, and edge cases. Per-type accuracy reporting with `EvalSummary`.
 - **15+ new unit tests** — Coverage for `detect_primary_change`, `detect_metadata_breaking`, `detect_bug_evidence` (all 7 patterns), Deleted/Renamed status, signature edge cases, connection content assertions.
 - **5 fuzz targets** — `fuzz_sanitizer`, `fuzz_safety`, `fuzz_diff_parser`, `fuzz_signature`, `fuzz_classify_span`.
-- **367 tests** total (up from 308 at v0.4.0). Current count at v0.6.0-rc.1: 410.
+- **367 tests** total (up from 308 at v0.4.0).
 
 ### API
 

Cargo.lock

@@ -4,7 +4,7 @@
 
 [package]
 name = "commitbee"
-version = "0.6.0-rc.1"
+version = "0.6.0-dev"
 edition = "2024"
 rust-version = "1.94"
 description = "AI-powered commit message generator using tree-sitter semantic analysis and local LLMs"

Cargo.toml

@@ -6,23 +6,25 @@ SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-Commercial
 
 # CommitBee — Product Requirements Document
 
-**Version**: 5.2
-**Date**: 2026-03-28
+**Version**: 5.4
+**Date**: 2026-04-07
 **Status**: Active  
-**Author**: [Sephyi](https://github.com/Sephyi) + [Claude Opus 4.6](https://www.anthropic.com/news/claude-opus-4-6)  
+**Author**: [Sephyi](https://github.com/Sephyi) + Junie (LLM Agent)
 
 ## Changelog
 
 <details>
-<summary>Revision history (v3.3 → v5.2)</summary>
+<summary>Revision history (v3.3 → v6.0)</summary>
 
 | Version | Date       | Summary |
 | ------- | ---------- | ------- |
+| 5.4     | 2026-04-07 | v0.6.0-dev: Added FR-081 (Interactive Message Refinement). Updated test count to 442. |
+| 5.3     | 2026-04-07 | v0.6.0-dev: Added FR-076 to FR-080 (Interactive editing, optimized splitter, native clipboard, secret scan accuracy, struct/enum diff completion). Updated test count to 440. |
 | 5.2     | 2026-03-28 | Security hardening: `secrecy::SecretString` for API keys (F-004), overflow-checks in release profile (F-001). Updated SR-002, DR-005, DR-006. |
 | 5.1     | 2026-03-28 | fix: keyring platform-native backends, API key validation ordering for set-key command. Updated FR-019 and SR-002. |
 | 5.0     | 2026-03-28 | PRD structural overhaul: removed stale §3.1 Resolved Issues (all v0.2.0), removed Dependency Status table, removed dead ORCommit references. Updated §2 competitive landscape for 2026 (added IDE-native competitors: GitHub Copilot Desktop, Cursor, Windsurf; updated star counts; refreshed feature matrix). Updated §3 codebase structure (added diff.rs, differ.rs, progress.rs). Updated PE-001/PE-002 with v0.6.0 prompt sections (STRUCTURED CHANGES, IMPORTS, RELATED FILES, INTENT). Updated PR-005 with adaptive budget. Added v0.6.0 feature section §4.6 (FR-064–FR-072). Renumbered Future to §4.7. |
 | 4.4     | 2026-03-27 | Added future requirements from audit: FR-073 (move detection), FR-074 (AST-based splitting), FR-075 (configurable categorization), TR-008 (LLM quality testing), PE-007 (token-accurate budgets). |
-| 4.3     | 2026-03-27 | v0.6.0-rc.1 deep semantic understanding: parent scope, import detection, doc-vs-code, structural AST diffs, semantic markers (FR-071), change intent (FR-072). 424 tests. |
+| 4.3     | 2026-03-27 | v0.6.0-dev deep semantic understanding: parent scope, import detection, doc-vs-code, structural AST diffs, semantic markers (FR-071), change intent (FR-072). 424 tests. |
 | 4.2     | 2026-03-22 | v0.5.0 hardening: security fixes (SSRF prevention, streaming caps), prompt optimization (budget fix, evidence omission, emoji removal), eval harness (36 fixtures, per-type reporting), test coverage (15+ new tests), API hygiene (pub(crate) demotions), 5 fuzz targets. 359 tests. |
 | 4.1     | 2026-03-22 | AST context overhaul (v0.5.0): full signature extraction from tree-sitter nodes, semantic change classification (whitespace vs body vs signature), old→new signature diffs, cross-file connection detection, formatting auto-detection via symbols. 359 tests. |
 | 4.0     | 2026-03-13 | PRD normalization: aligned phases with shipped versions (v0.2.0/v0.3.x/v0.4.0), collapsed revision history, unified status markers, resolved stale critical issues, canonicalized test count to 308, removed dead cross-references. FR-031 (Exclude Files) and FR-033 (Copy to Clipboard) shipped. |
@@ -66,7 +68,7 @@ CommitBee is a Rust-native CLI tool that uses tree-sitter semantic analysis and
 | v0.3.1  | Patch — default model → `qwen3.5:4b`, subject length validation, `think` config | None |
 | v0.4.0  | Feature completion (templates, languages, rename detection, history learning) | None |
 | v0.5.0  | AST context overhaul (signatures, semantic classification, cross-file connections) | None |
-| v0.6.0-rc.1 | Deep semantic understanding (parent scope, imports, doc-vs-code, structural AST diffs) | None |
+| v0.6.0-dev | Deep semantic understanding (parent scope, imports, doc-vs-code, structural AST diffs, native clipboard, interactive edit) | None |
 
 ## 2. Competitive Landscape
 
@@ -98,7 +100,7 @@ CommitBee is a Rust-native CLI tool that uses tree-sitter semantic analysis and
 | Multiple message generation (pick from N)          | Common (aicommits, aicommit2) | ✅ v0.2.0       |
 | Commit splitting (multi-concern detection)         | No competitor has this        | ✅ v0.2.0       |
 | Custom prompt/instruction files                    | Growing (Copilot, aicommit2)  | ✅ v0.4.0       |
-| Unit/integration tests                             | Non-negotiable for quality    | ✅ 424 tests    |
+| Unit/integration tests                             | Non-negotiable for quality    | ✅ 442 tests    |
 
 ## 3. Architecture
 
@@ -457,7 +459,7 @@ Project-level `.commitbee.toml` can no longer override `openai_base_url`, `anthr
 
 Subject character budget accounts for `!` suffix on breaking changes. EVIDENCE section omitted when all flags are default (~200 chars saved). Symbol marker legend added to SYSTEM_PROMPT (`[+] added, [-] removed, [~] modified`). Duplicate JSON schema removed from system prompt. Emoji replaced with text labels (`WARNING:` instead of `⚠`). CONNECTIONS instruction softened for small models. Python tree-sitter queries enhanced with `decorated_definition` support.
 
-### 4.6 Shipped — v0.6.0-rc.1 (Deep Semantic Understanding)
+### 4.6 Shipped — v0.6.0-dev (Deep Semantic Understanding)
 
 #### FR-064: Parent Scope Extraction ✅
 
@@ -495,6 +497,30 @@ In `infer_commit_type`, when >80% of additions are in `FileCategory::Test` files
 
 `detect_intents()` scans added diff lines for error handling patterns (9 patterns including `Result<>`, `?`, `Err()`, `.map_err()`), test patterns (6 patterns including `#[test]`, `assert!`), logging patterns (9 patterns including `tracing::`, `debug!()`, `info!()`), and dependency updates (version changes in manifests). `INTENT:` prompt section shows detected patterns with confidence scores. `refine_type_with_intents()` conservatively overrides base type only for high-confidence performance optimization. 7 tests.
 
+#### FR-076: Interactive Commit Editing ✅
+
+Added an "Edit" choice to the candidate selection and confirmation menu. Users can refine the generated message using their system editor (via the `EDITOR` env var) before committing, allowing for final manual tweaks without leaving the tool's flow.
+
+#### FR-077: Optimized Symbol Dependency Merging ✅
+
+Improved `CommitSplitter` performance for large commits by pre-indexing symbols and optimizing diff scanning. Reduces complexity from $O(F \times S \times L)$ to $O(F \times L)$, where F is files, S is symbols, and L is diff lines. Ensures commit splitting remains fast even for large refactorings.
+
+#### FR-078: Native Clipboard Implementation ✅
+
+Replaced external command dependencies (`pbcopy`, `xclip`) with the `arboard` crate for a native, cross-platform clipboard implementation. (Improvement over `FR-033`).
+
+#### FR-079: Accurate Secret Scan Line Numbers ✅
+
+The secret scanner now parses `@@` hunk headers to correctly report the source line number of detected secrets in the staged file, instead of the absolute diff line number. (Improvement over `SR-001`).
+
+#### FR-080: Full AST Diffs for Structs and Enums ✅
+
+Extended `AstDiffer` to support structured diffing for structs, enums, classes, and traits, detecting added/removed fields and variants. (Completion of `FR-069`).
+
+#### FR-081: Interactive Message Refinement ✅
+
+Added a "Refine" option to the candidate selection and confirmation menu. Users can provide feedback to the LLM (e.g., "more detail about the API change") to regenerate the message with natural language guidance.
+
 ### 4.7 Future — v0.7.0+ (Market Leadership)
 
 #### FR-050: MCP Server Mode
@@ -693,7 +719,7 @@ commitbee eval                         # Run evaluation harness (dev, feature-ga
 
 ## 8. Testing Requirements
 
-**Current test count: 424**
+**Current test count: 440**
 
 ### TR-001: Unit Tests
 
@@ -880,7 +906,7 @@ Replace character-based budget estimation (~4:1 char-to-token ratio approximatio
 | 3 | v0.4.0 | ✅ Shipped | Feature completion — templates, languages, rename, history, eval, fuzzing |
 | 4 | v0.4.x | ✅ Shipped | Remaining polish — exclude files (FR-031), clipboard (FR-033) |
 | 5 | v0.5.0 | ✅ Shipped | AST context overhaul — full signatures, semantic change classification, cross-file connections. 367 tests. |
-| 6 | v0.6.0-rc.1 | ✅ Shipped | Deep semantic understanding — parent scope, import detection, doc-vs-code classification, structural AST diffs, structured changes prompt section, semantic markers, change intent detection. 424 tests. |
+| 6 | v0.6.0-dev | 📋 Active | Deep semantic understanding — parent scope, import detection, doc-vs-code classification, structural AST diffs, structured changes prompt section, semantic markers, change intent detection. 442 tests. |
 | 7 | v0.7.0+ | 📋 Planned | Market leadership — MCP server, changelog, monorepo, version bumping, GitHub Action |
 
 ## 12. Success Metrics
@@ -895,7 +921,7 @@ Replace character-based budget estimation (~4:1 char-to-token ratio approximatio
 | Commit message quality | > 80% "good enough" first try | Manual evaluation + `commitbee eval` |
 | Secret leak rate | 0 | Integration tests with known patterns |
 | MSRV | Rust 1.94 (edition 2024) | CI matrix (stable + 1.94) |
-| Test count | ≥ 308 | `cargo test` (current: 424) |
+| Test count | ≥ 308 | `cargo test` (current: 440) |
 
 ## 13. Non-Goals