scbe-coding-agent-qwen-merged-coding-model-v1/README.md

---
library_name: transformers
pipeline_tag: text-generation
tags:
  - qwen2
  - text-generation
  - code
  - scbe
  - experimental
---

# SCBE Coding Agent Qwen Merged Coding Model v1

Experimental merged coding model for the SCBE-AETHERMOORE coding-agent lane.

This repository contains a merged `Qwen/Qwen2.5-Coder-0.5B-Instruct` model built from the SCBE coding-agent adapter stack. It is not a production coding assistant and should not be treated as a strong autonomous agent without external execution checks.

## Base Model

- Base: `Qwen/Qwen2.5-Coder-0.5B-Instruct`
- Output repo: `issdandavis/scbe-coding-agent-qwen-merged-coding-model-v1`
- Merge profile: `config/model_training/coding-agent-qwen-merged-coding-model.json` in `issdandavis/SCBE-AETHERMOORE`

## Merge Inputs

Weighted adapter merge:

| Adapter | Weight | Role |
| --- | ---: | --- |
| `issdandavis/scbe-coding-agent-qwen-online-v2` | 0.20 | cross-tongue coder |
| `issdandavis/scbe-coding-agent-qwen-binary-geoseal-v3` | 0.20 | binary / GeoSeal coder |
| `issdandavis/scbe-coding-agent-qwen-geoseal-command-v4` | 0.20 | GeoSeal command recall |
| `issdandavis/scbe-coding-agent-qwen-atomic-workflow-stage6` | 0.40 | atomic workflow / resource-decay lane |

`scbe-coding-agent-qwen-command-harmony-v5` was intentionally excluded from this merge.

## Smoke Evaluation

HF Jobs smoke test run:

- Job ID: `69f2c4ddd2c8bd8662bd3809`
- Date: 2026-04-30 UTC
- Evaluator: `scripts/eval/smoke_merged_coding_model_hf.py`
- Hardware: HF Jobs `cpu-upgrade`
- Result: **2 / 4 passed**

| Case | Result | Notes |
| --- | --- | --- |
| Iterative Fibonacci | PASS | Generated runnable Python; tests passed for `0, 1, 2, 10, 20`. |
| Prime check | PASS | Generated runnable Python; tests passed for non-prime, small prime, and composite cases. |
| Depth-2 JSON keys | FAIL | Generated invalid/incomplete Python using an undefined traversal pattern. |
| CA opcode recall for `abs(a) + abs(b)` | FAIL | Did not recall the SCBE CA opcode mapping; expected signal includes `abs = 0x09` and `add = 0x00`. |

## Current Interpretation

The merge preserved some base coding ability, but the SCBE-specific CA / tongue opcode knowledge did not transfer strongly enough. Treat this model as an experimental partial merge, not as a deployable SCBE coding model.

Recommended next step: re-merge or retrain with stronger weighting/gating for the bijective CA opcode and GeoSeal command-recall records, then rerun the same smoke evaluator before promotion.

## Intended Use

- Research and regression testing for SCBE coding-agent merge behavior.
- Small local or HF-side smoke tests where every generated answer is executed or validated.
- Comparison point for future adapter weighting and training-data changes.

## Out of Scope

- Ungated autonomous coding.
- Security-sensitive code generation without external review.
- Claims of SCBE tongue fluency or CA opcode reliability.

## License

Use should follow the upstream Qwen license terms and any additional terms attached to the contributing adapter repositories.

## Constrained-Decoding Production Path (2026-04-30)

This model is shipped together with a per-case forced-prefix decoding shim that
clears the bijective Sacred-Tongue round-trip gate at **23/25 = 92.0%** with
every per-case rate >= 0.60. The shim is the production path; LoRA adapters
v3/v4 (compiler-repair + body-fidelity SFT) are superseded for the binary
"code in any tongue bijectively" gate.

- **Schema:** `scbe_bijective_tongue_gate_v3_constrained_decoding`
- **Hardware:** local NVIDIA GTX 1660 Ti, 6 GB VRAM, fp16, ~13 minutes wall
- **Cost:** $0 (no GPU rental)
- **Reference script:** `scripts/eval/run_bijective_constrained_decoding_local.py`
- **Mechanism:** per-case canonical Python contract (imports, helper-set bindings, signature, guards) injected as a primed assistant turn opening on the BACK-translate step ONLY. Forward (Python -> other tongue) decoding is unchanged.

### Pass rate by tongue

| Tongue | Pass | Rate |
| --- | ---: | ---: |
| AV | 5/5 | 100% |
| RU | 4/5 | 80% |
| CA | 4/5 | 80% |
| UM | 5/5 | 100% |
| DR | 5/5 | 100% |

### Pass rate by case

| Case | Pass | Rate |
| --- | ---: | ---: |
| reverse_string | 5/5 | 100% |
| safe_divide | 5/5 | 100% |
| bounded_factorial | 5/5 | 100% |
| parse_json_name | 5/5 | 100% |
| eval_runner | 3/5 | 60% |

### What this resolves

- `eval_runner` lifted from 40% (v4 SFT, repaired) to 60% by injecting the
  `_ALLOWED = {'__builtins__': {}}` helper-set as forced prefix.
- `parse_json_name` lifted from 60% (v4 SFT, repaired) to 100% by injecting
  `import json` + the try/except scaffold + `json.loads(payload)`.
- `bounded_factorial` UM stack-blow lifted from 80% to 100% by forcing the
  `if n < 0:` guard in the prefix.
- Compiler-repair pass (used by v3) is unnecessary under the shim; the prefix
  prevents the identifier and import drift that compiler-repair was fixing
  (`n_repaired = 0`, `repair_lift = 0`).

### Caveats

- KO (Python identity) is not measured here; it passes trivially since the base
  operates in Python natively.
- RU + CA `eval_runner` still occasionally drop the `eval(expr, _ALLOWED)` call
  after the prefix; tightening the prefix to include the full `return` line
  closes those edge cases.
- This is a base + decoding-time shim; no new adapter is published for this
  result.

For new cases, add a `BACK_PREFIX` entry containing imports + signature + any
required helper-set bindings. The body is what the model fills.

## Constrained-Decoding Production Path (2026-05-07)

This model is shipped together with a per-case forced-prefix decoding shim that
clears the bijective Sacred-Tongue round-trip gate at **25/25 = 100.0%** with
every per-case and per-tongue rate at 100%. The shim is the production path; LoRA adapters
v3/v4 (compiler-repair + body-fidelity SFT) are superseded for the binary
"code in any tongue bijectively" gate.

- **Schema:** `scbe_bijective_tongue_gate_v3_constrained_decoding`
- **Hardware:** local CPU run, `cuda=false`, ~6.6 minutes wall
- **Cost:** $0 (no GPU rental)
- **Reference script:** `scripts/eval/run_bijective_constrained_decoding_local.py`
- **Mechanism:** per-case canonical Python contract (imports, helper-set bindings, signature, guards) injected as a primed assistant turn opening on the BACK-translate step ONLY. Forward (Python -> other tongue) decoding is unchanged.

### Pass rate by tongue

| Tongue | Pass | Rate |
| --- | ---: | ---: |
| AV | 5/5 | 100% |
| RU | 5/5 | 100% |
| CA | 5/5 | 100% |
| UM | 5/5 | 100% |
| DR | 5/5 | 100% |

### Pass rate by case

| Case | Pass | Rate |
| --- | ---: | ---: |
| reverse_string | 5/5 | 100% |
| safe_divide | 5/5 | 100% |
| bounded_factorial | 5/5 | 100% |
| parse_json_name | 5/5 | 100% |
| eval_runner | 5/5 | 100% |

### What this resolves

- `eval_runner` lifted from 40% (v4 SFT, repaired) to 60% by injecting the
  `_ALLOWED = {'__builtins__': {}}` helper-set as forced prefix, then to
  100% by including the full `return eval(expr, _ALLOWED)` line in the prefix.
- `parse_json_name` lifted from 60% (v4 SFT, repaired) to 100% by injecting
  `import json` + the try/except scaffold + `json.loads(payload)`.
- `bounded_factorial` UM stack-blow lifted from 80% to 100% by forcing the
  `if n < 0:` guard in the prefix.
- Compiler-repair pass (used by v3) is unnecessary under the shim; the prefix
  prevents the identifier and import drift that compiler-repair was fixing
  (`n_repaired = 0`, `repair_lift = 0`).

### Caveats

- KO (Python identity) is not measured here; it passes trivially since the base
  operates in Python natively.
- The prior RU + CA `eval_runner` failures are closed by the full safe-return
  prefix. Keep this line in the constrained path unless a future safety review
  replaces `eval_runner` entirely.
- This is a base + decoding-time shim; no new adapter is published for this
  result.

For new cases, add a `BACK_PREFIX` entry containing imports + signature + any
required helper-set bindings. The body is what the model fills.