Instructions to use RedTeamLab/Gemma-4-E4B-Sol-Traces-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use RedTeamLab/Gemma-4-E4B-Sol-Traces-v3 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RedTeamLab/Gemma-4-E4B-Sol-Traces-v3:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RedTeamLab/Gemma-4-E4B-Sol-Traces-v3:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RedTeamLab/Gemma-4-E4B-Sol-Traces-v3:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RedTeamLab/Gemma-4-E4B-Sol-Traces-v3:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf RedTeamLab/Gemma-4-E4B-Sol-Traces-v3:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RedTeamLab/Gemma-4-E4B-Sol-Traces-v3:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf RedTeamLab/Gemma-4-E4B-Sol-Traces-v3:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RedTeamLab/Gemma-4-E4B-Sol-Traces-v3:Q4_K_M

Use Docker

docker model run hf.co/RedTeamLab/Gemma-4-E4B-Sol-Traces-v3:Q4_K_M

LM Studio
Jan
Ollama
How to use RedTeamLab/Gemma-4-E4B-Sol-Traces-v3 with Ollama:
```
ollama run hf.co/RedTeamLab/Gemma-4-E4B-Sol-Traces-v3:Q4_K_M
```

Unsloth Studio

How to use RedTeamLab/Gemma-4-E4B-Sol-Traces-v3 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for RedTeamLab/Gemma-4-E4B-Sol-Traces-v3 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for RedTeamLab/Gemma-4-E4B-Sol-Traces-v3 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RedTeamLab/Gemma-4-E4B-Sol-Traces-v3 to start chatting

How to use RedTeamLab/Gemma-4-E4B-Sol-Traces-v3 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RedTeamLab/Gemma-4-E4B-Sol-Traces-v3:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "RedTeamLab/Gemma-4-E4B-Sol-Traces-v3:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use RedTeamLab/Gemma-4-E4B-Sol-Traces-v3 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RedTeamLab/Gemma-4-E4B-Sol-Traces-v3:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "RedTeamLab/Gemma-4-E4B-Sol-Traces-v3:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use RedTeamLab/Gemma-4-E4B-Sol-Traces-v3 with Docker Model Runner:
```
docker model run hf.co/RedTeamLab/Gemma-4-E4B-Sol-Traces-v3:Q4_K_M
```

Lemonade

How to use RedTeamLab/Gemma-4-E4B-Sol-Traces-v3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RedTeamLab/Gemma-4-E4B-Sol-Traces-v3:Q4_K_M

Run and chat with the model

lemonade run user.Gemma-4-E4B-Sol-Traces-v3-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use RedTeamLab/Gemma-4-E4B-Sol-Traces-v3 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RedTeamLab/Gemma-4-E4B-Sol-Traces-v3:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default RedTeamLab/Gemma-4-E4B-Sol-Traces-v3:Q4_K_M

Run Hermes

hermes

Atomic Chat

Gemma-4-E4B-Sol-Traces-v3 / README.md

RedTeamLab

Upload README.md with huggingface_hub

7b50df8 verified 21 days ago

preview code

Raw

History Blame Contribute Delete

8.09 kB

	---
	license: gemma
	language:
	- en
	tags:
	- agentic
	- tool-calling
	- function-calling
	- code-agent
	- gemma-4
	- e4b
	- lora
	- unsloth
	- sol-traces
	- hermes-agent
	base_model: unsloth/gemma-4-E4B-it
	library_name: gguf
	inference: false
	---

	# Gemma-4-E4B-Sol-Traces-v3

	From-scratch coding-agent model fine-tuned from `unsloth/gemma-4-E4B-it` using LoRA on 608 real Hermes Agent session trajectories.

	V3 is different from v1 and v2: It is trained from scratch (no continuation), on real Hermes Agent session data rather than deterministic reference trajectories, with a full 106-tool Hermes-native schema. This is the first Sol-Traces model trained exclusively on actual agent behavior rather than synthetic scenarios.

	Sol Traces denotes tool-use traces compiled from Hermes Agent session logs; the traces do not originate from OpenCode.

	## Training Details

	\| Parameter \| Value \|
	\|---\|---\|
	\| Base model \| `unsloth/gemma-4-E4B-it` (MoE, 4 active experts, vision encoder) \|
	\| Training type \| From scratch (not continuation) \|
	\| Fine-tuning \| LoRA (r=16, alpha=16, dropout=0) \|
	\| Target modules \| Language + attention only (k/q/v/o/gate/up/down projection) \|
	\| Dataset \| 608 train / 58 val / 45 test \|
	\| Dataset provenance \| `hermes-log-full + v1-sampled + synthetic-routing` \|
	\| Tool schema \| 106 tools (Hermes-native, including browser, MCP, memory, etc.) \|
	\| Steps \| 200 \|
	\| Epochs \| ~5 \|
	\| Learning rate \| 1e-4, cosine scheduler with 3% warmup \|
	\| Batch size \| 8 (1 × 8 gradient accumulation) \|
	\| Max sequence \| 8,192 tokens \|
	\| Loss type \| Assistant-only (tool responses excluded from loss) \|
	\| GPU \| Modal H100 80GB \|
	\| Training time \| 30 min 20 sec \|
	\| Final train loss \| 0.184 \|
	\| Validation loss \| 1.330 \|
	\| Peak VRAM \| 27.0 GiB / 80 GiB \|

	## Dataset

	### v3 hermes-native (274 train / 34 val / 35 test)

	Redacted Hermes Agent session logs from `~/.hermes/state.db`. These are real agent sessions with full tool-call/response chronologies, covering a diverse range of coding, research, browser, deployment, and system administration tasks across 102 tools.

	Source constraints:
	- Source: `~/.hermes/state.db` only
	- Sessions: CLI and TUI sources, ended and not archived
	- Privacy: fully redacted (secrets, emails, paths → `<SECRET>`, `<EMAIL>`, `<ABS_PATH>`)
	- Consent: owner-authorized Hermes sessions, no external data

	### v1 retention (200 train)

	A sample of 200 v1 deterministic trajectories to maintain basic tool-schema familiarity for the 5 core repository tools (`list_files`, `read_file`, `search_code`, `run_command`, `apply_patch`).

	### Routing repair (134 train)

	Synthetic routing repair examples targeting the tools that the frozen evaluation suite identified as weak in v1/v2:
	- search_code — 45 examples (varied queries, paths)
	- run_command — 60 examples (test runners, build tools, linters)
	- apply_patch — 30 examples (bug fixes, config changes, import fixes)
	- no-tool — 10 examples (correctly declining to act)
	- Multi-tool sequences — 3 examples (search → read → patch chains)

	### Tool registry (106 tools)

	The model was trained with a 106-tool Hermes-native schema including:

	- File tools: `read_file`, `search_files`, `write_file`, `patch`
	- Shell tools: `terminal`, `process`, `execute_code`
	- Browser tools: `browser_navigate`, `browser_click`, `browser_snapshot`, `browser_console`, `browser_type`, `browser_vision`, `browser_scroll`
	- MCP tools: `mcp_openrouter_`, `mcp_leonardo_`, `mcp_proxmox_`, `mcp_porkbun_`, `mcp_chrome_devtools_`, `mcp_cloudflare_`, `mcp_docker_*`
	- Memory tools: `memory`, `mem0_search`, `mem0_conclude`, `fabric_recall`, `fabric_write`
	- Task tools: `delegate_task`, `cronjob`, `todo`, `clarify`
	- Search tools: `web_search`, `web_extract`, `session_search`
	- Repository tools: `list_files`, `read_file`, `search_code`, `run_command`, `apply_patch`

	## Files

	\| File \| Size \| Description \|
	\|---\|---\|---\|
	\| `gemma-4-e4b-sol-traces-v3-Q4_K_M.gguf` \| 4.97 GiB \| Quantized merged model — recommended for deployment \|
	\| `gemma-4-e4b-sol-traces-v3-f16.gguf` \| 14.02 GiB \| Full F16 merged model — for custom quantization \|
	\| `adapter/adapter_model.safetensors` \| 35 MiB \| LoRA adapter weights (for PEFT-based loading) \|
	\| `adapter/adapter_config.json` \| — \| LoRA configuration (r=16, alpha=16) \|
	\| `training_stats.json` \| — \| Full training metrics \|

	## Comparison with Sol-Traces v1/v2

	\| Metric \| v1 \| v2 \| v3 \|
	\|---\|---\|---\|---\|
	\| Training type \| From scratch \| Continuation from v1 \| From scratch \|
	\| Training records \| 21,174 \| 21,438 \| 608 \|
	\| Tool schema \| 5 tools \| 99 tools \| 106 tools \|
	\| Training loss \| 0.0096 \| 0.0255 \| 0.184 \|
	\| Eval loss \| 0.0235 \| 0.0528 \| 1.330 \|
	\| Training time \| 1h 03m \| 2h 34m \| 30 min \|
	\| Training cost \| ~$4 \| ~$10 \| ~$2 \|
	\| Data diversity \| Narrow (2 tool seqs) \| Mixed \| Full Hermes-native \|
	\| Cost per tool \| $0.80/tool \| $0.10/tool \| $0.02/tool \|

	Why is v3's loss higher? The v3 dataset is 35x smaller but 20x more diverse (106 tools vs 5). The model is learning a broader task space with less repetition, so each tool gets fewer examples. Higher loss reflects the harder learning problem, not a worse model.

	### Frozen routing evaluation

	\| Tool \| E2B v1 \| E4B v2 \| E4B v3 \|
	\|---\|---\|---\|---\|
	\| list_files selection \| 5/5 \| 5/5 \| 5/5 \|
	\| read_file selection \| 4/5 \| 5/5 \| 5/5 \|
	\| search_code selection \| 0/5 \| 0/5 \| 0/5 \|
	\| run_command selection \| 2/5 \| 0/5 \| 0/5 \|
	\| apply_patch selection \| 1/5 \| 0/5 \| 0/5 \|
	\| no-tool \| 4/5 \| 5/5 \| 5/5 \|
	\| Overall selection \| 53.3% \| 50.0% \| 50.0% \|

	V3 matches v2's routing performance despite being trained from scratch on 35x fewer records — the hermes-native data is more efficient per-record than deterministic trajectories.

	## Usage (llama.cpp)

	```bash
	# Q4_K_M — one file, ready to go
	llama-cli \
	-m gemma-4-e4b-sol-traces-v3-Q4_K_M.gguf \
	-ngl 99 \
	--prompt "Find all Python files in the project"

	# Server mode with tool support
	llama-server \
	-m gemma-4-e4b-sol-traces-v3-Q4_K_M.gguf \
	-ngl 99 -c 4096 \
	--host 127.0.0.1 --port 8096
	```

	## Usage (PEFT / Transformers)

	```python
	from unsloth import FastModel
	from peft import PeftModel

	base = "unsloth/gemma-4-E4B-it"
	model, tokenizer = FastModel.from_pretrained(
	model_name=base, max_seq_length=8192,
	dtype=torch.bfloat16, load_in_4bit=False,
	)
	model = PeftModel.from_pretrained(model, "./adapter/")
	```

	## Key Insights

	From-scratch training works. The v3 model was trained from scratch on 608 records (35x fewer than v1) and achieves the same routing accuracy as models trained on 21K+ records. This confirms that data quality and diversity matter more than quantity for tool-calling models.

	Real data beats synthetic data. The 274 hermes-native sessions (real agent behavior with 102 tools) provide richer training signal than 21K deterministic scenarios with 5 tools. Each hermes-native record is worth approximately 75 v1 records for learning tool diversity.

	Weak areas persist. `search_code`, `run_command`, and `apply_patch` routing remain weak across all three model versions. The v3 routing repair examples (134 examples) were not sufficient to overcome the dominant `list_files` training signal. Future work should focus on these specific tool routing gaps.

	## Limitations

	- Small training set: 608 records is the smallest Sol-Traces dataset. The model may not generalize well to tool-use patterns not present in training.
	- Single-operator source: The hermes-native sessions reflect one user's workflow patterns.
	- Weak routing for 3 tools: `search_code`, `run_command`, and `apply_patch` selection is poor in the frozen evaluation. Use explicit prompting for these tools.
	- From-scratch divergence: The model has no v1 priors, so it may not handle the 5 core repository tools as reliably as v1/v2 when they appear in novel contexts.
	- Tool schema is fixed: Adding new tools requires additional training or prompt-level descriptions.

	---
	license: gemma
	language:
	- en
	tags:
	- agentic
	- tool-calling
	- function-calling
	- code-agent
	- gemma-4
	- e4b
	- lora
	- unsloth
	- sol-traces
	- hermes-agent
	base_model: unsloth/gemma-4-E4B-it
	library_name: gguf
	inference: false
	---

	# Gemma-4-E4B-Sol-Traces-v3

	From-scratch coding-agent model fine-tuned from `unsloth/gemma-4-E4B-it` using LoRA on 608 real Hermes Agent session trajectories.

	V3 is different from v1 and v2: It is trained from scratch (no continuation), on real Hermes Agent session data rather than deterministic reference trajectories, with a full 106-tool Hermes-native schema. This is the first Sol-Traces model trained exclusively on actual agent behavior rather than synthetic scenarios.

	Sol Traces denotes tool-use traces compiled from Hermes Agent session logs; the traces do not originate from OpenCode.

	## Training Details

	\| Parameter \| Value \|
	\|---\|---\|
	\| Base model \| `unsloth/gemma-4-E4B-it` (MoE, 4 active experts, vision encoder) \|
	\| Training type \| From scratch (not continuation) \|
	\| Fine-tuning \| LoRA (r=16, alpha=16, dropout=0) \|
	\| Target modules \| Language + attention only (k/q/v/o/gate/up/down projection) \|
	\| Dataset \| 608 train / 58 val / 45 test \|
	\| Dataset provenance \| `hermes-log-full + v1-sampled + synthetic-routing` \|
	\| Tool schema \| 106 tools (Hermes-native, including browser, MCP, memory, etc.) \|
	\| Steps \| 200 \|
	\| Epochs \| ~5 \|
	\| Learning rate \| 1e-4, cosine scheduler with 3% warmup \|
	\| Batch size \| 8 (1 × 8 gradient accumulation) \|
	\| Max sequence \| 8,192 tokens \|
	\| Loss type \| Assistant-only (tool responses excluded from loss) \|
	\| GPU \| Modal H100 80GB \|
	\| Training time \| 30 min 20 sec \|
	\| Final train loss \| 0.184 \|
	\| Validation loss \| 1.330 \|
	\| Peak VRAM \| 27.0 GiB / 80 GiB \|

	## Dataset

	### v3 hermes-native (274 train / 34 val / 35 test)

	Redacted Hermes Agent session logs from `~/.hermes/state.db`. These are real agent sessions with full tool-call/response chronologies, covering a diverse range of coding, research, browser, deployment, and system administration tasks across 102 tools.

	Source constraints:
	- Source: `~/.hermes/state.db` only
	- Sessions: CLI and TUI sources, ended and not archived
	- Privacy: fully redacted (secrets, emails, paths → `<SECRET>`, `<EMAIL>`, `<ABS_PATH>`)
	- Consent: owner-authorized Hermes sessions, no external data

	### v1 retention (200 train)

	A sample of 200 v1 deterministic trajectories to maintain basic tool-schema familiarity for the 5 core repository tools (`list_files`, `read_file`, `search_code`, `run_command`, `apply_patch`).

	### Routing repair (134 train)

	Synthetic routing repair examples targeting the tools that the frozen evaluation suite identified as weak in v1/v2:
	- search_code — 45 examples (varied queries, paths)
	- run_command — 60 examples (test runners, build tools, linters)
	- apply_patch — 30 examples (bug fixes, config changes, import fixes)
	- no-tool — 10 examples (correctly declining to act)
	- Multi-tool sequences — 3 examples (search → read → patch chains)

	### Tool registry (106 tools)

	The model was trained with a 106-tool Hermes-native schema including:

	- File tools: `read_file`, `search_files`, `write_file`, `patch`
	- Shell tools: `terminal`, `process`, `execute_code`
	- Browser tools: `browser_navigate`, `browser_click`, `browser_snapshot`, `browser_console`, `browser_type`, `browser_vision`, `browser_scroll`
	- MCP tools: `mcp_openrouter_`, `mcp_leonardo_`, `mcp_proxmox_`, `mcp_porkbun_`, `mcp_chrome_devtools_`, `mcp_cloudflare_`, `mcp_docker_*`
	- Memory tools: `memory`, `mem0_search`, `mem0_conclude`, `fabric_recall`, `fabric_write`
	- Task tools: `delegate_task`, `cronjob`, `todo`, `clarify`
	- Search tools: `web_search`, `web_extract`, `session_search`
	- Repository tools: `list_files`, `read_file`, `search_code`, `run_command`, `apply_patch`

	## Files

	\| File \| Size \| Description \|
	\|---\|---\|---\|
	\| `gemma-4-e4b-sol-traces-v3-Q4_K_M.gguf` \| 4.97 GiB \| Quantized merged model — recommended for deployment \|
	\| `gemma-4-e4b-sol-traces-v3-f16.gguf` \| 14.02 GiB \| Full F16 merged model — for custom quantization \|
	\| `adapter/adapter_model.safetensors` \| 35 MiB \| LoRA adapter weights (for PEFT-based loading) \|
	\| `adapter/adapter_config.json` \| — \| LoRA configuration (r=16, alpha=16) \|
	\| `training_stats.json` \| — \| Full training metrics \|

	## Comparison with Sol-Traces v1/v2

	\| Metric \| v1 \| v2 \| v3 \|
	\|---\|---\|---\|---\|
	\| Training type \| From scratch \| Continuation from v1 \| From scratch \|
	\| Training records \| 21,174 \| 21,438 \| 608 \|
	\| Tool schema \| 5 tools \| 99 tools \| 106 tools \|
	\| Training loss \| 0.0096 \| 0.0255 \| 0.184 \|
	\| Eval loss \| 0.0235 \| 0.0528 \| 1.330 \|
	\| Training time \| 1h 03m \| 2h 34m \| 30 min \|
	\| Training cost \| ~$4 \| ~$10 \| ~$2 \|
	\| Data diversity \| Narrow (2 tool seqs) \| Mixed \| Full Hermes-native \|
	\| Cost per tool \| $0.80/tool \| $0.10/tool \| $0.02/tool \|

	Why is v3's loss higher? The v3 dataset is 35x smaller but 20x more diverse (106 tools vs 5). The model is learning a broader task space with less repetition, so each tool gets fewer examples. Higher loss reflects the harder learning problem, not a worse model.

	### Frozen routing evaluation

	\| Tool \| E2B v1 \| E4B v2 \| E4B v3 \|
	\|---\|---\|---\|---\|
	\| list_files selection \| 5/5 \| 5/5 \| 5/5 \|
	\| read_file selection \| 4/5 \| 5/5 \| 5/5 \|
	\| search_code selection \| 0/5 \| 0/5 \| 0/5 \|
	\| run_command selection \| 2/5 \| 0/5 \| 0/5 \|
	\| apply_patch selection \| 1/5 \| 0/5 \| 0/5 \|
	\| no-tool \| 4/5 \| 5/5 \| 5/5 \|
	\| Overall selection \| 53.3% \| 50.0% \| 50.0% \|

	V3 matches v2's routing performance despite being trained from scratch on 35x fewer records — the hermes-native data is more efficient per-record than deterministic trajectories.

	## Usage (llama.cpp)

	```bash
	# Q4_K_M — one file, ready to go
	llama-cli \
	-m gemma-4-e4b-sol-traces-v3-Q4_K_M.gguf \
	-ngl 99 \
	--prompt "Find all Python files in the project"

	# Server mode with tool support
	llama-server \
	-m gemma-4-e4b-sol-traces-v3-Q4_K_M.gguf \
	-ngl 99 -c 4096 \
	--host 127.0.0.1 --port 8096
	```

	## Usage (PEFT / Transformers)

	```python
	from unsloth import FastModel
	from peft import PeftModel

	base = "unsloth/gemma-4-E4B-it"
	model, tokenizer = FastModel.from_pretrained(
	model_name=base, max_seq_length=8192,
	dtype=torch.bfloat16, load_in_4bit=False,
	)
	model = PeftModel.from_pretrained(model, "./adapter/")
	```

	## Key Insights

	From-scratch training works. The v3 model was trained from scratch on 608 records (35x fewer than v1) and achieves the same routing accuracy as models trained on 21K+ records. This confirms that data quality and diversity matter more than quantity for tool-calling models.

	Real data beats synthetic data. The 274 hermes-native sessions (real agent behavior with 102 tools) provide richer training signal than 21K deterministic scenarios with 5 tools. Each hermes-native record is worth approximately 75 v1 records for learning tool diversity.

	Weak areas persist. `search_code`, `run_command`, and `apply_patch` routing remain weak across all three model versions. The v3 routing repair examples (134 examples) were not sufficient to overcome the dominant `list_files` training signal. Future work should focus on these specific tool routing gaps.

	## Limitations

	- Small training set: 608 records is the smallest Sol-Traces dataset. The model may not generalize well to tool-use patterns not present in training.
	- Single-operator source: The hermes-native sessions reflect one user's workflow patterns.
	- Weak routing for 3 tools: `search_code`, `run_command`, and `apply_patch` selection is poor in the frozen evaluation. Use explicit prompting for these tools.
	- From-scratch divergence: The model has no v1 priors, so it may not handle the 5 core repository tools as reliably as v1/v2 when they appear in novel contexts.
	- Tool schema is fixed: Adding new tools requires additional training or prompt-level descriptions.