…terns (code-yeongyu#5)

* fix(publish): make git operations idempotent

- Check for staged changes before commit
- Check if tag exists before creating
- Check if release exists before creating

* fix(ast-grep): add validation for incomplete function declaration patterns

- Add validatePatternForCli function to detect incomplete patterns like
  'export async function $METHOD' (missing params and body)
- Only validates JS/TS languages (javascript, typescript, tsx)
- Provides helpful error message with correct pattern examples
- Update tool description to clarify complete AST nodes required

This fixes the issue where incomplete patterns would fail silently
with no results instead of providing actionable feedback.

- Remove sisyphusJuniorModel fallback bypass (BUG #1)
  - userModel fallback was incorrectly bypassing category fallbackChain
  - Now correctly uses category requirements before system default

- Fix variant preservation in actualModel fallback path (BUG #2)
  - Variant was lost when categoryModel undefined but actualModel existed
  - Now preserves variant when falling back to actualModel parsing

- Add variant to session continuation (BUG code-yeongyu#3)
  - Session resume didn't pass variant from message history
  - Now extracts resumeVariant and passes as body.variant

- Remove unused inheritedModel parameter (BUG code-yeongyu#4)
  - resolveCategoryConfig had misleading unused parameter
  - Cleaned up function signature and all call sites

- Add variant-model compatibility validation (BUG code-yeongyu#5)
  - No warning when variant might not be supported by provider
  - Added isVariantLikelySupported() validation with console.warn

Test coverage:
- Updated 10+ existing tests to remove inheritedModel references
- Added 9 new tests for variant validation functions
- All 110 tests pass (77 delegate-task + 33 model-requirements)

…-yeongyu#309)

Critical fixes:
- Bug #1: SubagentStop hook defaulted all agents to 'failed' because SDK
  doesn't provide `success` field. Now defaults to 'completed' when undefined.
- Bug code-yeongyu#4: Token stats lost across TokenTracker instances. Constructor now
  restores session stats from global state for the same session ID.
- Bug code-yeongyu#5: Ultrawork session isolation bypassed when both session IDs were
  undefined (undefined === undefined). Now rejects all falsy session IDs.

High priority fixes:
- Bug code-yeongyu#6: Cancel skill force-clear missed 12+ state files (boulder,
  hud-state, subagent-tracking, checkpoints, etc). Added comprehensive list.
- Bug code-yeongyu#7: HUD semverCompare() returned NaN on pre-release versions like
  "3.9.5-beta". Fixed to use parseInt and handle pre-release ordering.
- Bug code-yeongyu#8: Silent JSON parse failures in critical state readers. Added
  error logging to ralph and ultrawork state readers.
- Bug code-yeongyu#9: Stale task detection had no default behavior when onStaleSession
  callback was not configured. Now auto-cleans after 2x threshold.
- Bug code-yeongyu#10: Hardcoded 3-architect assumption in validation. Extracted to
  REQUIRED_ARCHITECTS constant.

Medium priority fixes:
- Bug code-yeongyu#11: Auto-invoke history used non-atomic writes. Now uses
  atomicWriteJson to prevent corruption from concurrent sessions.
- Bug code-yeongyu#12: Ecomode docs said "all tasks" use Haiku, contradicting the
  escalation paths. Clarified to "most tasks" with upgrade criteria.
- Bug code-yeongyu#13: Added safeUnlinkSync/safeRmSync utilities to prevent ENOENT
  crashes during cleanup operations.
- Bug code-yeongyu#14: State files containing user prompts written with 0644
  permissions. Now writes with 0600 (owner-only read/write).
- Bug code-yeongyu#15: Model names recorded inconsistently (e.g., 'claude-3-5-haiku'
  vs 'claude-haiku-4'). Now normalizes at recording time via exported
  normalizeModelName().

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>

…hardening

Fixes from multi-model council audit (7 members, 19 findings, 9 selected):

- Use parseModelString() for cross-provider Anthropic thinking config (#3)
- Update stale AGENTS.md athena directory listing (#4)
- Replace prompt in appendMissingCouncilPrompt instead of appending (#5)
- Extract duplicated session cleanup logic in agent-switch hook (#6)
- Surface skipped council members when >=2 valid members exist (#9)
- Expand fallback handoff regex with negation guards (#11)
- Remove dead council-member agent from agentSources and tests (#12)
- Make runtime council member duplicate check case-insensitive (#14)
- Fix false-positive schema tests by adding required name field (#18)

…hardening

Fixes from multi-model council audit (7 members, 19 findings, 9 selected):

- Use parseModelString() for cross-provider Anthropic thinking config (#3)
- Update stale AGENTS.md athena directory listing (#4)
- Replace prompt in appendMissingCouncilPrompt instead of appending (#5)
- Extract duplicated session cleanup logic in agent-switch hook (#6)
- Surface skipped council members when >=2 valid members exist (#9)
- Expand fallback handoff regex with negation guards (#11)
- Remove dead council-member agent from agentSources and tests (#12)
- Make runtime council member duplicate check case-insensitive (#14)
- Fix false-positive schema tests by adding required name field (#18)

…hardening

Fixes from multi-model council audit (7 members, 19 findings, 9 selected):

- Use parseModelString() for cross-provider Anthropic thinking config (code-yeongyu#3)
- Update stale AGENTS.md athena directory listing (code-yeongyu#4)
- Replace prompt in appendMissingCouncilPrompt instead of appending (code-yeongyu#5)
- Extract duplicated session cleanup logic in agent-switch hook (code-yeongyu#6)
- Surface skipped council members when >=2 valid members exist (code-yeongyu#9)
- Expand fallback handoff regex with negation guards (code-yeongyu#11)
- Remove dead council-member agent from agentSources and tests (code-yeongyu#12)
- Make runtime council member duplicate check case-insensitive (code-yeongyu#14)
- Fix false-positive schema tests by adding required name field (code-yeongyu#18)

**Justification — Oracle analysis #5:**
Oracle: 'Replace infinite retry language with debugger-style escalation:
after three materially different failed fix attempts, stop guessing,
gather evidence, consult Oracle, then resume with implementation_handoff.'

Atlas's current 'no retry cap' policy (default-prompt-sections.ts:149)
creates failure loops — agents retry the same broken approach indefinitely,
burning tokens without progress.

**What changed — default-prompt-sections.ts:**
- Section 3.5 renamed from 'NEVER GIVE UP' to 'Three-Fail Rule'
- Hard 3-attempt cap: attempts 1-2 use task_id retry with different
  approaches, attempt 3 triggers Oracle escalation
- Escalation path: gather evidence bundle → consult Oracle → receive
  implementation_handoff → resume with handoff (do_not_reinvestigate)
- Red flags section: conditions that trigger immediate escalation
  ('just one more fix', fixing before understanding, quick-fix mindset)
- Removed 'There is no retry cap' language and infinite-retry guidance
- Retained task_id usage instructions for attempts 1-2

**Remaining work:**
gpt-prompt-sections.ts, gemini-prompt-sections.ts, kimi-prompt-sections.ts,
and opus-4-7-prompt-sections.ts all have the same 'no retry cap' language
and need the same Three-Fail Rule update.

**Gem-team source:**
- gem-debugger Three-Fail Rule (gem-debugger.agent.md:170-197)
- implementation_handoff schema (gem-debugger.agent.md:224-229)