semantics

.opencode/agents/closure-gate.md

@@ -83,5 +83,6 @@ Surface these as unresolved:
 - `[NEED_CONTEXT: ...]` markers not resolved
 - Decision memory debt accumulated without documentation
 - Test gaps in C4/C5 contracts
+- **ANCHOR CORRUPTION: mismatched `#region`/`#endregion` count, duplicate `#endregion`, `@C N` artifacts, `@COMPLEXITY N` instead of `[C:N]`** — these are NOT cosmetic; they destroy the semantic index. Reject worker output immediately if detected.
 
 #endregion Closure.Gate

.opencode/agents/fullstack-coder.md

@@ -165,6 +165,17 @@ request:
 - No retained workaround without local `@RATIONALE` and `@REJECTED`.
 - No implementation may silently re-enable an upstream rejected path.
 
+## SEMANTIC SAFETY: Anti-Corruption Protocol
+
+The `#region`/`#endregion` markers are AST boundaries. Breaking them destroys the semantic index. Same rules as python-coder:
+
+1. **Before editing:** `axiom_semantic_discovery read_outline` to see exact boundaries
+2. **Never:** insert between `#region` and first `@TAG`; remove/move/duplicate `#endregion`; add `@COMPLEXITY N` or `@C N` (use `[C:N]` in anchor)
+3. **After editing:** verify with `read_outline` — all pairs must match
+4. **If corrupted:** roll back immediately, do not continue editing
+5. **One file at a time** — verify between files
+6. **When adding contracts:** always include BOTH `#region` AND `#endregion`
+
 ## Recursive Delegation
 - For large features, you MAY spawn `python-coder` for backend-only subtasks or `svelte-coder` for frontend-only subtasks.
 - If you cannot complete within the step limit, spawn a new-fullstack-coder or appropriate subagent to continue.

.opencode/agents/python-coder.md

@@ -183,6 +183,35 @@ request:
 - No implementation may silently re-enable an upstream rejected path.
 - Handoff must state complexity, contracts, decision-memory updates, remaining semantic debt, or the bounded `<ESCALATION>` payload when anti-loop escalation is triggered.
 
+## SEMANTIC SAFETY: Anti-Corruption Protocol
+
+You MUST NOT corrupt the `#region`/`#endregion` AST boundaries. If you break a pair, the semantic index breaks and ALL downstream agents hallucinate.
+
+### Before editing any Python file
+1. **Read the file's region outline:** `axiom_semantic_discovery read_outline file_path="<your file>"`
+2. **Identify nested contracts** — if the file has child `#region` inside a parent `#region`, you are inside a fractal tree
+3. **Never:**
+   - Insert code between `#region` and the first `# @TAG` metadata line
+   - Remove, move, or duplicate ANY `#endregion` line
+   - Add `@COMPLEXITY N` — complexity goes in the anchor: `[C:N]`
+   - Add `@C N` — this is a non-standard legacy artifact, never create it
+   - Put code outside all regions — every line must be inside a `#region`/`#endregion` pair
+
+### After every edit
+4. **Verify:** run `axiom_semantic_discovery read_outline` on the file — confirm all pairs match
+5. **If a `#endregion` is missing** → the file is corrupted, roll back immediately
+6. **If you changed anchors** → run `axiom_semantic_index rebuild rebuild_mode="full"`
+
+### When adding new contracts
+7. Always add BOTH `#region Id [C:N] [TYPE Type]` and `# #endregion Id`
+8. Complexity `[C:N]` goes in the ANCHOR line, never as a separate `@` tag
+9. If the new contract is nested inside another → DO NOT close the parent until after your child's `#endregion`
+
+### Critical: batch semantic fixes
+10. **ONE FILE AT A TIME.** Verify each file before moving to the next.
+11. **NEVER use `@C N`** — always `[C:N]` in the anchor.
+12. If a contract has children (nested `#region` inside), use `destructive_intent=true` with extreme caution.
+
 ## Recursive Delegation
 - If you cannot complete the task within the step limit or if the task is too complex, you MUST spawn a new subagent of the same type (or appropriate type) to continue the work or handle a subset of the task.
 - Do NOT escalate back to the orchestrator with incomplete work unless anti-loop escalation mode has been triggered.

.opencode/agents/qa-tester.md

@@ -27,6 +27,14 @@ You are an Agentic QA Engineer. MANDATORY USE `skill({name="semantics-core"})`,
 - The Logic Mirror Anti-pattern is forbidden: never duplicate the implementation algorithm inside the test.
 - Code review is part of QA: audit semantic protocol compliance before executing tests.
 
+## Anchor Safety (Mandatory)
+QA tests often add `#region`/`#endregion` around test classes. You MUST:
+1. Always add BOTH `#region TestClass [C:3] [TYPE Class]` AND `# #endregion TestClass`
+2. Never insert test code outside a `#region`/`#endregion` pair
+3. Never remove existing `#endregion` markers
+4. After adding test anchors, verify with `axiom_semantic_discovery read_outline`
+5. Never use `@C N` or `@COMPLEXITY N` — use `[C:N]` in anchor
+
 ## Orthogonal Verification Projections
 
 Every verification pass is classified into exactly one primary projection. A single contract may generate findings across multiple projections — that is intentional.

.opencode/agents/semantic-curator.md

@@ -56,6 +56,39 @@ Axiom MCP-сервер  полностью работоспособен.
 - **Svelte JS/TS (script block):** `// #region ContractId` / `// #endregion ContractId`
 - **Markdown/ADR:** `## @{ ContractId [C:N] [TYPE TypeName]` / `## @} ContractId`
 
+## 2.5. ANTI-CORRUPTION PROTOCOL (MANDATORY — READ BEFORE ANY MUTATION)
+
+If you corrupt a `#region`/`#endregion` pair, you destroy the AST. Downstream agents will hallucinate. These rules are NOT optional.
+
+### BEFORE every patch
+1. **READ the file** with `read_outline` to see the EXACT region boundaries
+2. **Identify ALL nested child contracts** — never break a child's `#endregion`
+3. **Check that your `new_code` or `replacement` does NOT:**
+   - Insert code between `#region` line and first metadata `# @TAG` line (breaks INV_4)
+   - Remove or move ANY `#endregion` marker
+   - Start a new `#region` before closing the previous one
+   - Add `@COMPLEXITY N` — use `[C:N]` in the anchor ONLY
+
+### AFTER every patch
+1. **Run `read_outline` on the modified file** — verify ALL `#region`/`#endregion` pairs remain intact
+2. **Count `#region` and `#endregion` lines** — they MUST match
+3. **If the count doesn't match or structure is broken** → immediately roll back via `axiom_workspace_checkpoint rollback_apply`
+4. **Run `axiom_semantic_index rebuild rebuild_mode="full"`** — 0 parse warnings required
+
+### FORBIDDEN OPERATIONS (immediate <ESCALATION> if detected)
+- Inserting code between a closing `#endregion` and the parent's `#endregion`
+- Duplicating ANY `#region` or `#endregion` line
+- Adding `@COMPLEXITY` tag — always use `[C:N]` in the anchor header
+- Editing a contract that contains nested children without `destructive_intent=true`
+- Batch-editing more than ONE file at a time without verifying each file between edits
+- Using `@C N` as a standalone tag — this is a non-standard artifact, never add it
+
+### VERIFICATION LOOP (every file, every time)
+```
+read_outline(file) → identify boundaries → apply ONE patch → read_outline(file) → rebuild index → audit_contracts(file)
+```
+If ANY step fails — stop and fix before next file. Never chain patches without verification.
+
 ## 3. HEALTH AUDIT CHECKLIST
 For each file scanned:
 - [ ] Every `#region` has a matching `#endregion` with the same ID
@@ -63,7 +96,7 @@ For each file scanned:
 - [ ] C4 contracts have `@PRE`, `@POST`, `@SIDE_EFFECT`
 - [ ] C5 contracts additionally have `@RATIONALE`, `@REJECTED`, `@DATA_CONTRACT`, `@INVARIANT`
 - [ ] C3 contracts have `@RELATION` but NOT `@PRE`/`@POST`/etc.
-- [ ] No `@RATIONALE`/`@REJECTED` on C1-C4 contracts (complexity tag mismatch)
+- [ ] `@RATIONALE`/`@REJECTED` are allowed at ALL tiers (C1-C5) — they are never a violation
 - [ ] Module files < 400 LOC
 - [ ] Contract nodes < 150 LOC
 - [ ] No orphan `@RELATION` edges (target exists or is `[NEED_CONTEXT]`)

.opencode/agents/swarm-master.md

@@ -104,6 +104,19 @@ Every delegation MUST include a bounded worker packet:
 - [Which tests must pass]
 ```
 
+## VI.5. SEMANTIC SAFETY: Anti-Corruption Coordination
+
+**CRITICAL: NEVER dispatch multiple agents to edit the SAME file simultaneously.** Each `#region`/`#endregion` pair is an AST boundary. Parallel edits to the same file WILL corrupt the anchor pairs.
+
+### Rules for semantic work delegations:
+1. **One file = one agent.** If multiple files need fixes, dispatch one agent per FILE, not one agent per FILE-SCOPE.
+2. **Never dispatch semantic-curator agents in parallel** — they mutate anchors and can step on each other.
+3. **Always include in Constraints:** "Verify file structure with `axiom_semantic_discovery read_outline` BEFORE and AFTER every edit"
+4. **Always include in Constraints:** "Use `[C:N]` in anchors — NEVER add `@C N` or `@COMPLEXITY N` tags"
+5. **Always include in Constraints:** "ONE file at a time. Verify `read_outline` after each file. If `#region`/`#endregion` count doesn't match — roll back."
+6. **For batch semantic fixes (>3 files):** dispatch ONE semantic-curator, tell them to process files SEQUENTIALLY, one at a time, with verification between each.
+7. **Acceptance criteria for semantic work:** "0 parse warnings after `axiom_semantic_index rebuild`; all `#region`/`#endregion` pairs intact per `read_outline`"
+
 ## VII. CLOSURE ROUTING
 After receiving worker outputs, route to:
 1. `qa-tester` — if contracts need verification