busya/ss-tools
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

semantic update

Browse Source
This commit is contained in:
busya
2026-03-10 21:33:09 +03:00
parent 4f1c33e02b
commit 5e527a8af2
10 changed files with 2084 additions and 1499 deletions
Download Patch File Download Diff File Expand all files Collapse all files

81
.kilocode/workflows/speckit.semantics.md
View File

@@ -1,5 +1,5 @@
---
description: Maintain semantic integrity via multi-agent delegation. Analyzes codebase, delegates markup tasks to Semantic Engineer, verifies via Reviewer Agent, and reports status.
description: Maintain semantic integrity by generating maps and auditing compliance reports.
---
## User Input
@@ -12,62 +12,63 @@ You **MUST** consider the user input before proceeding (if not empty).
## Goal
Ensure the codebase 100% adheres to the semantic standards defined in `.ai/standards/semantics.md` (GRACE-Poly Protocol). You are the **Manager/Supervisor**. You do not write code. You manage the queue, delegate files to the Semantic Engineer, audit their work via the Reviewer Agent, and commit successful changes.
Ensure the codebase adheres to the semantic standards defined in `.ai/standards/semantics.md`. This involves generating the semantic map, analyzing compliance reports, and identifying critical parsing errors or missing metadata.
## Operating Constraints
1. **ROLE: Orchestrator**: High-level coordination ONLY. Do not output raw code diffs yourself.
2. **DELEGATION PATTERN**: Strict `Orchestrator -> Engineer -> Reviewer -> Orchestrator` loop.
3. **FAIL-FAST METRICS**: If the Reviewer Agent rejects a file 3 times in a row, drop the file from the current queue and mark it as `[HUMAN_INTERVENTION_REQUIRED]`.
4. **TIER AWARENESS**: CRITICAL files MUST be processed first. A failure in a CRITICAL file blocks the entire pipeline.
1. **ROLE: Orchestrator**: You are responsible for the high-level coordination of semantic maintenance.
2. **STRICT ADHERENCE**: Follow `.ai/standards/semantics.md` for all anchor and tag syntax.
3. **NON-DESTRUCTIVE**: Do not remove existing code logic; only add or update semantic annotations.
4. **TIER AWARENESS**: Prioritize CRITICAL and STANDARD modules for compliance fixes.
5. **NO PSEUDO-CONTRACTS (CRITICAL)**: You are STRICTLY FORBIDDEN from using automated scripts (e.g., Python/Bash/sed) to mechanically inject boilerplate, placeholders, or "pseudo-contracts" (such as `# @PURPOSE: Semantic contract placeholder.` or `# @PRE: Inputs satisfy function contract.`) merely to artificially inflate the compliance score. Every semantic tag, anchor, and contract you add MUST reflect a genuine, deep understanding of the specific code's actual logic and business requirements. Automated "stubbing" of semantics is classified as codebase corruption.
## Execution Steps
### 1. Generate Semantic State (Analyze)
Run the generator script to map the current reality:
### 1. Generate Semantic Map
Run the generator script from the repository root with the agent report option:
```bash
python3 generate_semantic_map.py
python3 generate_semantic_map.py --agent-report
```
Parse the output (Global Score, Critical Parsing Errors, Files with Score < 0.7).
### 2. Formulate Task Queue
Create an execution queue based on the report. Priority:
- **Priority 1 (Blockers)**: Files with "Critical Parsing Errors" (unclosed `[/DEF]` anchors).
- **Priority 2 (Tier 1)**: `CRITICAL` tier modules missing mandatory tags (`@PRE`, `@POST`, `belief_scope`).
- **Priority 3 (Tier 2)**: `STANDARD` modules with missing graph relations (`@RELATION`).
### 2. Analyze Compliance Status
### 3. The Delegation Loop (For each file in the queue)
For every target file, execute this exact sequence:
**Parse the JSON output to identify**:
- `global_score`: The overall compliance percentage.
- `critical_parsing_errors_count`: Number of Priority 1 blockers.
- `priority_2_tier1_critical_missing_mandatory_tags_files`: Number of CRITICAL files needing metadata.
- `targets`: Status of key architectural files.
* **Step 3A (Delegate to Worker):** Send the file path and the specific violation from the report to the **Semantic Markup Agent (Engineer)**.
*Prompt*: `"Fix semantic violations in [FILE]. Current issues: [ISSUES]. Apply GRACE-Poly standards without changing business logic."*
* **Step 3B (Delegate to Auditor):** Once the Engineer returns the modified file, send it to the **Reviewer Agent (Auditor)**.
*Prompt*: `"Verify GRACE-Poly compliance for [FILE]. Check for paired [DEF] anchors, complete contracts, and belief_scope usage. Return PASS or FAIL with specific line errors."*
* **Step 3C (Evaluate):**
* If Auditor returns `PASS`: Apply the diff to the codebase. Move to the next file.
* If Auditor returns `FAIL`: Send the Auditor's error report back to the Engineer (Step 3A). Repeat max 3 times.
### 3. Audit Critical Issues
### 4. Verification
Once the queue is empty, re-run `python3 generate_semantic_map.py` to prove the metrics have improved.
Read the latest report and extract:
- **Critical Parsing Errors**: Unclosed anchors or mismatched tags.
- **Low-Score Files**: Files with score < 0.7 or marked with 🔴.
- **Missing Mandatory Tags**: Specifically for CRITICAL tier modules.
## Output Format
### 4. Formulate Remediation Plan
Return a structured summary of the operation:
Create a list of files requiring immediate attention:
1. **Priority 1**: Fix all "Critical Parsing Errors" (unclosed anchors).
2. **Priority 2**: Add missing mandatory tags for CRITICAL modules.
3. **Priority 3**: Improve coverage for STANDARD modules.
```text
=== GRACE SEMANTIC ORCHESTRATION REPORT ===
Initial Global Score: [X]%
Final Global Score: [Y]%
Status:[PASS / BLOCKED]
### 5. Execute Fixes (Optional/Handoff)
Files Processed:
1. [file_path] -[PASS (1 attempt) | PASS (2 attempts) | FAILED]
2. ...
If $ARGUMENTS contains "fix" or "apply":
- For each target file, use `read_file` to get context.
- Apply semantic fixes using `apply_diff`, preserving all code logic.
- Re-run `python3 generate_semantic_map.py --agent-report` to verify the fix.
## Output
Provide a summary of the semantic state:
- **Global Score**: [X]%
- **Status**: [PASS/FAIL] (FAIL if any Critical Parsing Errors exist)
- **Top Issues**: List top 3-5 files needing attention.
- **Action Taken**: Summary of maps generated or fixes applied.
Escalations (Human Intervention Required):
-[file_path]: Failed auditor review 3 times. Reason: [Last Auditor Note].
```
## Context
$ARGUMENTS
```