Files

swp 657407d5ef fix: replace unavailable model references with available ones

- Replace anthropic/claude-sonnet-4 with ollama-cloud/gpt-oss:120b in:
  - capability-analyst.md
  - agent-architect.md
- Replace openai/compound with ollama-cloud/glm-5 in review-watcher.md
- Remove duplicate model definitions in agent-architect.md
- Add AGENT_AUDIT.md documenting all model fixes

Available models use prefixes:
- ollama-cloud/ (primary)
- openrouter/ (router)
- qwen/ (direct)
- groq/ (fast inference)

NOT available:
- anthropic/ (Claude)
- openai/ (use via ollama-cloud/gpt-oss instead)

All 18 agents and 11 commands now use available models.

2026-04-04 01:54:02 +01:00

4.4 KiB

Raw Blame History

Agent, Workflow, and Skill Audit Report

Audit Date: 2026-04-04

Model Availability

Available model prefixes:

ollama-cloud/ - Primary cloud models
openrouter/ - Router models
qwen/ - Qwen models
groq/ - Groq models

NOT Available:

anthropic/ - Claude models (❌ removed)
openai/ - OpenAI models directly (use via openrouter, or specific ollama-cloud/gpt-oss)

Agents Audit

Agent	Model	Status	Issues
orchestrator	ollama-cloud/glm-5	✅ OK	-
requirement-refiner	ollama-cloud/kimi-k2-thinking	✅ OK	-
history-miner	ollama-cloud/gpt-oss:20b	✅ OK	-
system-analyst	openrouter/qwen/qwen3.6-plus:free	✅ OK	-
product-owner	openrouter/qwen/qwen3.6-plus:free	✅ OK	-
lead-developer	ollama-cloud/qwen3-coder:480b	✅ OK	-
frontend-developer	ollama-cloud/kimi-k2.5	✅ OK	-
sdet-engineer	ollama-cloud/qwen3-coder:480b	✅ OK	-
code-skeptic	ollama-cloud/minimax-m2.5	✅ OK	-
the-fixer	ollama-cloud/minimax-m2.5	✅ OK	-
performance-engineer	ollama-cloud/nemotron-3-super	✅ OK	-
security-auditor	ollama-cloud/kimi-k2.5	✅ OK	-
release-manager	ollama-cloud/qwen3-coder:480b	✅ OK	-
evaluator	ollama-cloud/gpt-oss:120b	✅ OK	-
prompt-optimizer	openrouter/qwen/qwen3.6-plus:free	✅ OK	-
capability-analyst	~~anthropic/claude-sonnet-4~~	⚠️ FIXED	Changed to ollama-cloud/gpt-oss:120b
agent-architect	~~anthropic/claude-sonnet-4~~	⚠️ FIXED	Changed to ollama-cloud/gpt-oss:120b
markdown-validator	qwen/qwen3.6-plus:free	✅ OK	-

Commands/Workflows Audit

Command	Model	Status	Issues
pipeline	-	✅ OK	Uses subagent models
status	qwen/qwen3.6-plus:free	✅ OK	-
evaluate	ollama-cloud/gpt-oss:120b	✅ OK	-
plan	openrouter/qwen/qwen3-coder:free	✅ OK	-
ask	groq/qwen3-32b	✅ OK	-
debug	ollama-cloud/gpt-oss:20b	✅ OK	-
code	openrouter/qwen/qwen3-coder:free	✅ OK	-
review	openrouter/minimax/minimax-m2.5:free	✅ OK	-
feature	openrouter/qwen/qwen3-coder:free	✅ OK	-
hotfix	openrouter/minimax/minimax-m2.5:free	✅ OK	-
review-watcher	~~openai/compound~~	⚠️ FIXED	Changed to ollama-cloud/glm-5

Skills Audit

Skill	Status	Notes
gitea	✅ OK	TypeScript module
scoped-labels	✅ OK	Documentation only
fix-workflow	✅ OK	Documentation only

Issues Fixed

1. Unavailable Models (2 agents)

Before:

capability-analyst: anthropic/claude-sonnet-4-20250514
agent-architect: anthropic/claude-sonnet-4-20250514

After:

capability-analyst: ollama-cloud/gpt-oss:120b
agent-architect: ollama-cloud/gpt-oss:120b

2. Invalid Model for Command (1 command)

Before:

review-watcher: openai/compound

After:

review-watcher: ollama-cloud/glm-5

3. Duplicate Model Definitions (1 agent)

agent-architect.md had 3 model definitions, fixed to single correct one.

Model Profile Recommendations

Analysis & Strategy

ollama-cloud/gpt-oss:120b - Complex reasoning, analysis
ollama-cloud/glm-5 - Routing, orchestration, simple tasks

Code Generation

ollama-cloud/qwen3-coder:480b - Primary code generation
openrouter/qwen/qwen3-coder:free - Free alternative

Code Review

ollama-cloud/minimax-m2.5 - Critical analysis
ollama-cloud/nemotron-3-super - Performance review

Security & Testing

ollama-cloud/kimi-k2.5 - Security audit, frontend
ollama-cloud/kimi-k2-thinking - Requirements analysis

Light Tasks

openrouter/qwen/qwen3.6-plus:free - Documentation, planning
qwen/qwen3.6-plus:free - Quick tasks
groq/qwen3-32b - Fast queries

Remaining Consistency Issues

Model Prefix Inconsistency

Some models use different prefixes for the same provider:

qwen/qwen3.6-plus:free vs openrouter/qwen/qwen3.6-plus:free

Recommendation: Standardize to one prefix pattern.

Suggested Standardization

Current	Standardize To
`qwen/qwen3.6-plus:free`	`openrouter/qwen/qwen3.6-plus:free`

Summary

Total Agents: 18
Total Commands: 11
Total Skills: 3
Issues Found: 4
Issues Fixed: 4
Status: ✅ All models now use available endpoints

4.4 KiB Raw Blame History