Hugging Face's logo

veriloop-lab
/
veriloop-coder-e1

Text Generation
Transformers
Safetensors
PEFT
English
Chinese
qwen3_5
image-text-to-text
veriloop
veriloop-coder
code
coding-agent
software-engineering
repository-understanding
tool-use
lora
harness-engineering
evidence-binding
rollback
uncertainty-calibration
long-context
open-weights
conversational
Model card Files
xet
 Community
ConorWang commited on
Commit
ed67500
·
verified ·
1 Parent(s): 10132f1

Clear legacy 35B artifacts except README

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +0 -40
  2. _drive_refresh_manifest.txt +0 -40
  3. chat_template.jinja +0 -154
  4. config.json +0 -119
  5. configuration.json +0 -1
  6. evidence_adapter/.gitkeep +0 -0
  7. evidence_adapter/adapter/README.md +0 -203
  8. evidence_adapter/adapter/adapter_config.json +0 -54
  9. evidence_adapter/adapter/adapter_model.safetensors +0 -3
  10. evidence_adapter/best_checkpoint_manifest.json +0 -29
  11. evidence_adapter/epoch_history.json +0 -124
  12. evidence_adapter/evidence_binding_adapter_plan.json +0 -223
  13. evidence_adapter/evidence_binding_adapter_train_result.json +0 -338
  14. evidence_adapter/evidence_binding_eval.jsonl +0 -0
  15. evidence_adapter/evidence_binding_head.pt +0 -3
  16. evidence_adapter/evidence_binding_train.jsonl +0 -0
  17. evidence_adapter/evidence_binding_training_manifest.json +0 -120
  18. evidence_adapter/host_manifest.json +0 -268
  19. evidence_adapter/tokenizer/chat_template.jinja +0 -154
  20. evidence_adapter/tokenizer/tokenizer.json +0 -3
  21. evidence_adapter/tokenizer/tokenizer_config.json +0 -31
  22. generation_config.json +0 -12
  23. merges.txt +0 -0
  24. model.safetensors.index.json +0 -0
  25. preprocessor_config.json +0 -21
  26. rollback_adapter/.gitkeep +0 -0
  27. rollback_adapter/adapter/README.md +0 -203
  28. rollback_adapter/adapter/adapter_config.json +0 -57
  29. rollback_adapter/adapter/adapter_model.safetensors +0 -3
  30. rollback_adapter/best_checkpoint_manifest.json +0 -28
  31. rollback_adapter/epoch_history.json +0 -120
  32. rollback_adapter/host_manifest.json +0 -288
  33. rollback_adapter/rollback_adapter_plan.json +0 -251
  34. rollback_adapter/rollback_adapter_train_result.json +0 -363
  35. rollback_adapter/rollback_eval.jsonl +0 -45
  36. rollback_adapter/rollback_head.pt +0 -3
  37. rollback_adapter/rollback_train.jsonl +0 -0
  38. rollback_adapter/rollback_training_manifest.json +0 -121
  39. rollback_adapter/tokenizer/chat_template.jinja +0 -154
  40. rollback_adapter/tokenizer/tokenizer.json +0 -3
  41. rollback_adapter/tokenizer/tokenizer_config.json +0 -31
  42. tokenizer.json +0 -3
  43. tokenizer_config.json +0 -305
  44. toolspec_adapter/.gitkeep +0 -1
  45. toolspec_adapter/adapter/README.md +0 -203
  46. toolspec_adapter/adapter/adapter_config.json +0 -52
  47. toolspec_adapter/adapter/adapter_model.safetensors +0 -3
  48. toolspec_adapter/best_checkpoint_manifest.json +0 -27
  49. toolspec_adapter/epoch_history.json +0 -144
  50. toolspec_adapter/host_manifest.json +0 -238
.gitattributes DELETED
@@ -1,40 +0,0 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
- *.ftz filter=lfs diff=lfs merge=lfs -text
7
- *.gz filter=lfs diff=lfs merge=lfs -text
8
- *.h5 filter=lfs diff=lfs merge=lfs -text
9
- *.joblib filter=lfs diff=lfs merge=lfs -text
10
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
- *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
- *.onnx filter=lfs diff=lfs merge=lfs -text
17
- *.ot filter=lfs diff=lfs merge=lfs -text
18
- *.parquet filter=lfs diff=lfs merge=lfs -text
19
- *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
- *.pt filter=lfs diff=lfs merge=lfs -text
23
- *.pth filter=lfs diff=lfs merge=lfs -text
24
- *.rar filter=lfs diff=lfs merge=lfs -text
25
- *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
- *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
- *.tflite filter=lfs diff=lfs merge=lfs -text
30
- *.tgz filter=lfs diff=lfs merge=lfs -text
31
- *.wasm filter=lfs diff=lfs merge=lfs -text
32
- *.xz filter=lfs diff=lfs merge=lfs -text
33
- *.zip filter=lfs diff=lfs merge=lfs -text
34
- *.zst filter=lfs diff=lfs merge=lfs -text
35
- *tfevents* filter=lfs diff=lfs merge=lfs -text
36
- tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
- toolspec_adapter/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
- uncertainty_adapter/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
- evidence_adapter/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
- rollback_adapter/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
_drive_refresh_manifest.txt DELETED
@@ -1,40 +0,0 @@
1
- DIR 0 .cache
2
- FILE 1570 .gitattributes
3
- FILE 64908 README.md
4
- FILE 7764 chat_template.jinja
5
- FILE 3686 config.json
6
- FILE 58 configuration.json
7
- FILE 202 generation_config.json
8
- FILE 3353259 merges.txt
9
- FILE 3996199712 model-00001-of-00026.safetensors
10
- FILE 1284907696 model-00002-of-00026.safetensors
11
- FILE 3357898360 model-00003-of-00026.safetensors
12
- FILE 3370808712 model-00004-of-00026.safetensors
13
- FILE 3357898360 model-00005-of-00026.safetensors
14
- FILE 3959424904 model-00006-of-00026.safetensors
15
- FILE 1096788232 model-00007-of-00026.safetensors
16
- FILE 3946842008 model-00008-of-00026.safetensors
17
- FILE 1096460848 model-00009-of-00026.safetensors
18
- FILE 3946841992 model-00010-of-00026.safetensors
19
- FILE 1096460752 model-00011-of-00026.safetensors
20
- FILE 3409971080 model-00012-of-00026.safetensors
21
- FILE 1633331664 model-00013-of-00026.safetensors
22
- FILE 3422553872 model-00014-of-00026.safetensors
23
- FILE 1633659224 model-00015-of-00026.safetensors
24
- FILE 3946842136 model-00016-of-00026.safetensors
25
- FILE 1096460608 model-00017-of-00026.safetensors
26
- FILE 3946841992 model-00018-of-00026.safetensors
27
- FILE 1096460808 model-00019-of-00026.safetensors
28
- FILE 3409971072 model-00020-of-00026.safetensors
29
- FILE 1633331744 model-00021-of-00026.safetensors
30
- FILE 3370808752 model-00022-of-00026.safetensors
31
- FILE 3357898392 model-00023-of-00026.safetensors
32
- FILE 3370808752 model-00024-of-00026.safetensors
33
- FILE 3832888256 model-00025-of-00026.safetensors
34
- FILE 2231416848 model-00026-of-00026.safetensors
35
- FILE 98383 model.safetensors.index.json
36
- FILE 390 preprocessor_config.json
37
- FILE 12807982 tokenizer.json
38
- FILE 16718 tokenizer_config.json
39
- FILE 385 video_preprocessor_config.json
40
- FILE 6722759 vocab.json
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
chat_template.jinja DELETED
@@ -1,154 +0,0 @@
1
- {%- set image_count = namespace(value=0) %}
2
- {%- set video_count = namespace(value=0) %}
3
- {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
- {%- if content is string %}
5
- {{- content }}
6
- {%- elif content is iterable and content is not mapping %}
7
- {%- for item in content %}
8
- {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
- {%- if is_system_content %}
10
- {{- raise_exception('System message cannot contain images.') }}
11
- {%- endif %}
12
- {%- if do_vision_count %}
13
- {%- set image_count.value = image_count.value + 1 %}
14
- {%- endif %}
15
- {%- if add_vision_id %}
16
- {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
- {%- endif %}
18
- {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
- {%- elif 'video' in item or item.type == 'video' %}
20
- {%- if is_system_content %}
21
- {{- raise_exception('System message cannot contain videos.') }}
22
- {%- endif %}
23
- {%- if do_vision_count %}
24
- {%- set video_count.value = video_count.value + 1 %}
25
- {%- endif %}
26
- {%- if add_vision_id %}
27
- {{- 'Video ' ~ video_count.value ~ ': ' }}
28
- {%- endif %}
29
- {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
- {%- elif 'text' in item %}
31
- {{- item.text }}
32
- {%- else %}
33
- {{- raise_exception('Unexpected item type in content.') }}
34
- {%- endif %}
35
- {%- endfor %}
36
- {%- elif content is none or content is undefined %}
37
- {{- '' }}
38
- {%- else %}
39
- {{- raise_exception('Unexpected content type.') }}
40
- {%- endif %}
41
- {%- endmacro %}
42
- {%- if not messages %}
43
- {{- raise_exception('No messages provided.') }}
44
- {%- endif %}
45
- {%- if tools and tools is iterable and tools is not mapping %}
46
- {{- '<|im_start|>system\n' }}
47
- {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
48
- {%- for tool in tools %}
49
- {{- "\n" }}
50
- {{- tool | tojson }}
51
- {%- endfor %}
52
- {{- "\n</tools>" }}
53
- {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
54
- {%- if messages[0].role == 'system' %}
55
- {%- set content = render_content(messages[0].content, false, true)|trim %}
56
- {%- if content %}
57
- {{- '\n\n' + content }}
58
- {%- endif %}
59
- {%- endif %}
60
- {{- '<|im_end|>\n' }}
61
- {%- else %}
62
- {%- if messages[0].role == 'system' %}
63
- {%- set content = render_content(messages[0].content, false, true)|trim %}
64
- {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
65
- {%- endif %}
66
- {%- endif %}
67
- {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
68
- {%- for message in messages[::-1] %}
69
- {%- set index = (messages|length - 1) - loop.index0 %}
70
- {%- if ns.multi_step_tool and message.role == "user" %}
71
- {%- set content = render_content(message.content, false)|trim %}
72
- {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
73
- {%- set ns.multi_step_tool = false %}
74
- {%- set ns.last_query_index = index %}
75
- {%- endif %}
76
- {%- endif %}
77
- {%- endfor %}
78
- {%- if ns.multi_step_tool %}
79
- {{- raise_exception('No user query found in messages.') }}
80
- {%- endif %}
81
- {%- for message in messages %}
82
- {%- set content = render_content(message.content, true)|trim %}
83
- {%- if message.role == "system" %}
84
- {%- if not loop.first %}
85
- {{- raise_exception('System message must be at the beginning.') }}
86
- {%- endif %}
87
- {%- elif message.role == "user" %}
88
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
89
- {%- elif message.role == "assistant" %}
90
- {%- set reasoning_content = '' %}
91
- {%- if message.reasoning_content is string %}
92
- {%- set reasoning_content = message.reasoning_content %}
93
- {%- else %}
94
- {%- if '</think>' in content %}
95
- {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
96
- {%- set content = content.split('</think>')[-1].lstrip('\n') %}
97
- {%- endif %}
98
- {%- endif %}
99
- {%- set reasoning_content = reasoning_content|trim %}
100
- {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
101
- {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
102
- {%- else %}
103
- {{- '<|im_start|>' + message.role + '\n' + content }}
104
- {%- endif %}
105
- {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
106
- {%- for tool_call in message.tool_calls %}
107
- {%- if tool_call.function is defined %}
108
- {%- set tool_call = tool_call.function %}
109
- {%- endif %}
110
- {%- if loop.first %}
111
- {%- if content|trim %}
112
- {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
113
- {%- else %}
114
- {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
115
- {%- endif %}
116
- {%- else %}
117
- {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
- {%- endif %}
119
- {%- if tool_call.arguments is defined %}
120
- {%- for args_name, args_value in tool_call.arguments|items %}
121
- {{- '<parameter=' + args_name + '>\n' }}
122
- {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
123
- {{- args_value }}
124
- {{- '\n</parameter>\n' }}
125
- {%- endfor %}
126
- {%- endif %}
127
- {{- '</function>\n</tool_call>' }}
128
- {%- endfor %}
129
- {%- endif %}
130
- {{- '<|im_end|>\n' }}
131
- {%- elif message.role == "tool" %}
132
- {%- if loop.previtem and loop.previtem.role != "tool" %}
133
- {{- '<|im_start|>user' }}
134
- {%- endif %}
135
- {{- '\n<tool_response>\n' }}
136
- {{- content }}
137
- {{- '\n</tool_response>' }}
138
- {%- if not loop.last and loop.nextitem.role != "tool" %}
139
- {{- '<|im_end|>\n' }}
140
- {%- elif loop.last %}
141
- {{- '<|im_end|>\n' }}
142
- {%- endif %}
143
- {%- else %}
144
- {{- raise_exception('Unexpected message role.') }}
145
- {%- endif %}
146
- {%- endfor %}
147
- {%- if add_generation_prompt %}
148
- {{- '<|im_start|>assistant\n' }}
149
- {%- if enable_thinking is defined and enable_thinking is false %}
150
- {{- '<think>\n\n</think>\n\n' }}
151
- {%- else %}
152
- {{- '<think>\n' }}
153
- {%- endif %}
154
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json DELETED
@@ -1,119 +0,0 @@
1
- {
2
- "architectures": [
3
- "Qwen3_5MoeForConditionalGeneration"
4
- ],
5
- "image_token_id": 248056,
6
- "model_type": "qwen3_5_moe",
7
- "text_config": {
8
- "attention_bias": false,
9
- "attention_dropout": 0.0,
10
- "attn_output_gate": true,
11
- "bos_token_id": 248044,
12
- "dtype": "bfloat16",
13
- "eos_token_id": 248044,
14
- "full_attention_interval": 4,
15
- "head_dim": 256,
16
- "hidden_act": "silu",
17
- "hidden_size": 2048,
18
- "initializer_range": 0.02,
19
- "layer_types": [
20
- "linear_attention",
21
- "linear_attention",
22
- "linear_attention",
23
- "full_attention",
24
- "linear_attention",
25
- "linear_attention",
26
- "linear_attention",
27
- "full_attention",
28
- "linear_attention",
29
- "linear_attention",
30
- "linear_attention",
31
- "full_attention",
32
- "linear_attention",
33
- "linear_attention",
34
- "linear_attention",
35
- "full_attention",
36
- "linear_attention",
37
- "linear_attention",
38
- "linear_attention",
39
- "full_attention",
40
- "linear_attention",
41
- "linear_attention",
42
- "linear_attention",
43
- "full_attention",
44
- "linear_attention",
45
- "linear_attention",
46
- "linear_attention",
47
- "full_attention",
48
- "linear_attention",
49
- "linear_attention",
50
- "linear_attention",
51
- "full_attention",
52
- "linear_attention",
53
- "linear_attention",
54
- "linear_attention",
55
- "full_attention",
56
- "linear_attention",
57
- "linear_attention",
58
- "linear_attention",
59
- "full_attention"
60
- ],
61
- "linear_conv_kernel_dim": 4,
62
- "linear_key_head_dim": 128,
63
- "linear_num_key_heads": 16,
64
- "linear_num_value_heads": 32,
65
- "linear_value_head_dim": 128,
66
- "mamba_ssm_dtype": "float32",
67
- "max_position_embeddings": 262144,
68
- "model_type": "qwen3_5_moe_text",
69
- "moe_intermediate_size": 512,
70
- "mtp_num_hidden_layers": 1,
71
- "mtp_use_dedicated_embeddings": false,
72
- "num_attention_heads": 16,
73
- "num_experts": 256,
74
- "num_experts_per_tok": 8,
75
- "num_hidden_layers": 40,
76
- "num_key_value_heads": 2,
77
- "output_router_logits": false,
78
- "pad_token_id": null,
79
- "partial_rotary_factor": 0.25,
80
- "rms_norm_eps": 1e-06,
81
- "rope_parameters": {
82
- "mrope_interleaved": true,
83
- "mrope_section": [
84
- 11,
85
- 11,
86
- 10
87
- ],
88
- "partial_rotary_factor": 0.25,
89
- "rope_theta": 10000000,
90
- "rope_type": "default"
91
- },
92
- "router_aux_loss_coef": 0.001,
93
- "shared_expert_intermediate_size": 512,
94
- "tie_word_embeddings": false,
95
- "use_cache": true,
96
- "vocab_size": 248320
97
- },
98
- "tie_word_embeddings": false,
99
- "transformers_version": "4.57.1",
100
- "video_token_id": 248057,
101
- "vision_config": {
102
- "deepstack_visual_indexes": [],
103
- "depth": 27,
104
- "hidden_act": "gelu_pytorch_tanh",
105
- "hidden_size": 1152,
106
- "in_channels": 3,
107
- "initializer_range": 0.02,
108
- "intermediate_size": 4304,
109
- "model_type": "qwen3_5_moe",
110
- "num_heads": 16,
111
- "num_position_embeddings": 2304,
112
- "out_hidden_size": 2048,
113
- "patch_size": 16,
114
- "spatial_merge_size": 2,
115
- "temporal_patch_size": 2
116
- },
117
- "vision_end_token_id": 248054,
118
- "vision_start_token_id": 248053
119
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
configuration.json DELETED
@@ -1 +0,0 @@
1
- {"framework":"Pytorch","task":"visual-question-answering"}
 
 
evidence_adapter/.gitkeep DELETED
File without changes
evidence_adapter/adapter/README.md DELETED
@@ -1,203 +0,0 @@
1
- ---
2
- library_name: peft
3
- tags:
4
- - lora
5
- ---
6
-
7
- # Model Card for Model ID
8
-
9
- <!-- Provide a quick summary of what the model is/does. -->
10
-
11
-
12
-
13
- ## Model Details
14
-
15
- ### Model Description
16
-
17
- <!-- Provide a longer summary of what this model is. -->
18
-
19
-
20
-
21
- - **Developed by:** [More Information Needed]
22
- - **Funded by [optional]:** [More Information Needed]
23
- - **Shared by [optional]:** [More Information Needed]
24
- - **Model type:** [More Information Needed]
25
- - **Language(s) (NLP):** [More Information Needed]
26
- - **License:** [More Information Needed]
27
- - **Finetuned from model [optional]:** [More Information Needed]
28
-
29
- ### Model Sources [optional]
30
-
31
- <!-- Provide the basic links for the model. -->
32
-
33
- - **Repository:** [More Information Needed]
34
- - **Paper [optional]:** [More Information Needed]
35
- - **Demo [optional]:** [More Information Needed]
36
-
37
- ## Uses
38
-
39
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
40
-
41
- ### Direct Use
42
-
43
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
44
-
45
- [More Information Needed]
46
-
47
- ### Downstream Use [optional]
48
-
49
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
50
-
51
- [More Information Needed]
52
-
53
- ### Out-of-Scope Use
54
-
55
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
56
-
57
- [More Information Needed]
58
-
59
- ## Bias, Risks, and Limitations
60
-
61
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
62
-
63
- [More Information Needed]
64
-
65
- ### Recommendations
66
-
67
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
68
-
69
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
70
-
71
- ## How to Get Started with the Model
72
-
73
- Use the code below to get started with the model.
74
-
75
- [More Information Needed]
76
-
77
- ## Training Details
78
-
79
- ### Training Data
80
-
81
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
82
-
83
- [More Information Needed]
84
-
85
- ### Training Procedure
86
-
87
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
88
-
89
- #### Preprocessing [optional]
90
-
91
- [More Information Needed]
92
-
93
-
94
- #### Training Hyperparameters
95
-
96
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
97
-
98
- #### Speeds, Sizes, Times [optional]
99
-
100
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
101
-
102
- [More Information Needed]
103
-
104
- ## Evaluation
105
-
106
- <!-- This section describes the evaluation protocols and provides the results. -->
107
-
108
- ### Testing Data, Factors & Metrics
109
-
110
- #### Testing Data
111
-
112
- <!-- This should link to a Dataset Card if possible. -->
113
-
114
- [More Information Needed]
115
-
116
- #### Factors
117
-
118
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
119
-
120
- [More Information Needed]
121
-
122
- #### Metrics
123
-
124
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
125
-
126
- [More Information Needed]
127
-
128
- ### Results
129
-
130
- [More Information Needed]
131
-
132
- #### Summary
133
-
134
-
135
-
136
- ## Model Examination [optional]
137
-
138
- <!-- Relevant interpretability work for the model goes here -->
139
-
140
- [More Information Needed]
141
-
142
- ## Environmental Impact
143
-
144
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
145
-
146
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
147
-
148
- - **Hardware Type:** [More Information Needed]
149
- - **Hours used:** [More Information Needed]
150
- - **Cloud Provider:** [More Information Needed]
151
- - **Compute Region:** [More Information Needed]
152
- - **Carbon Emitted:** [More Information Needed]
153
-
154
- ## Technical Specifications [optional]
155
-
156
- ### Model Architecture and Objective
157
-
158
- [More Information Needed]
159
-
160
- ### Compute Infrastructure
161
-
162
- [More Information Needed]
163
-
164
- #### Hardware
165
-
166
- [More Information Needed]
167
-
168
- #### Software
169
-
170
- [More Information Needed]
171
-
172
- ## Citation [optional]
173
-
174
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
175
-
176
- **BibTeX:**
177
-
178
- [More Information Needed]
179
-
180
- **APA:**
181
-
182
- [More Information Needed]
183
-
184
- ## Glossary [optional]
185
-
186
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
187
-
188
- [More Information Needed]
189
-
190
- ## More Information [optional]
191
-
192
- [More Information Needed]
193
-
194
- ## Model Card Authors [optional]
195
-
196
- [More Information Needed]
197
-
198
- ## Model Card Contact
199
-
200
- [More Information Needed]
201
- ### Framework versions
202
-
203
- - PEFT 0.19.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
evidence_adapter/adapter/adapter_config.json DELETED
@@ -1,54 +0,0 @@
1
- {
2
- "alora_invocation_tokens": null,
3
- "alpha_pattern": {},
4
- "arrow_config": null,
5
- "auto_mapping": null,
6
- "base_model_name_or_path": null,
7
- "bias": "none",
8
- "corda_config": null,
9
- "ensure_weight_tying": false,
10
- "eva_config": null,
11
- "exclude_modules": null,
12
- "fan_in_fan_out": false,
13
- "inference_mode": true,
14
- "init_lora_weights": true,
15
- "layer_replication": null,
16
- "layers_pattern": null,
17
- "layers_to_transform": null,
18
- "loftq_config": {},
19
- "lora_alpha": 16,
20
- "lora_bias": false,
21
- "lora_dropout": 0.05,
22
- "lora_ga_config": null,
23
- "megatron_config": null,
24
- "megatron_core": "megatron.core",
25
- "modules_to_save": null,
26
- "peft_type": "LORA",
27
- "peft_version": "0.19.0",
28
- "qalora_group_size": 16,
29
- "r": 8,
30
- "rank_pattern": {},
31
- "revision": null,
32
- "target_modules": [
33
- "surface_host.evidence_binding.adapter",
34
- "surface_host.tool_receipt_binding.adapter",
35
- "surface_host.citation_binding.adapter",
36
- "surface_host.reverse_engineering_binding.adapter",
37
- "surface_host.runtime_binding.adapter",
38
- "surface_host.validator_receipt_bridge.adapter",
39
- "surface_host.selfcheck_binding.adapter",
40
- "surface_host.execution_binding.adapter",
41
- "surface_host.patch_binding.adapter",
42
- "surface_host.proof_carrying_hints.bridge",
43
- "surface_host.provenance_binding.adapter",
44
- "surface_host.worktree_binding.adapter",
45
- "surface_host.claim_extractor.adapter"
46
- ],
47
- "target_parameters": null,
48
- "task_type": "FEATURE_EXTRACTION",
49
- "trainable_token_indices": null,
50
- "use_bdlora": null,
51
- "use_dora": false,
52
- "use_qalora": false,
53
- "use_rslora": false
54
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
evidence_adapter/adapter/adapter_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d2e07f819fdde8c0954f3f6d21bd5877e26627d145d125a959669cfc6f9f38e
3
- size 855584
 
 
 
 
evidence_adapter/best_checkpoint_manifest.json DELETED
@@ -1,29 +0,0 @@
1
- {
2
- "best_epoch": 4,
3
- "best_quality_score": 0.5592996196176252,
4
- "eval_metrics": {
5
- "avg_binary_accuracy": 0.8444444444444446,
6
- "citation_binding_required_accuracy": 1.0,
7
- "contradiction_visible_accuracy": 0.7692307692307693,
8
- "count": 65,
9
- "eval_batches": 65,
10
- "eval_loss": 4.7871557712554935,
11
- "execution_needed_accuracy": 0.8461538461538461,
12
- "mode_accuracy": 0.5692307692307692,
13
- "next_action_accuracy": 0.5538461538461539,
14
- "patch_continuity_accuracy": 0.6461538461538462,
15
- "proof_carrying_compatible_accuracy": 0.8,
16
- "provenance_accuracy": 0.6461538461538462,
17
- "quality_score": 0.5592996196176252,
18
- "reverse_engineering_ready_accuracy": 0.8461538461538461,
19
- "tool_selfcheck_needed_accuracy": 0.7692307692307693,
20
- "validator_required_accuracy": 1.0,
21
- "verdict_accuracy": 0.6307692307692307,
22
- "worktree_safe_accuracy": 0.9230769230769231
23
- },
24
- "train_metrics": {
25
- "loss": 0.23536107725985758,
26
- "micro_batches": 182,
27
- "optimizer_steps": 12
28
- }
29
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
evidence_adapter/epoch_history.json DELETED
@@ -1,124 +0,0 @@
1
- {
2
- "epochs": [
3
- {
4
- "epoch": 1,
5
- "eval_metrics": {
6
- "avg_binary_accuracy": 0.823931623931624,
7
- "citation_binding_required_accuracy": 1.0,
8
- "contradiction_visible_accuracy": 0.6461538461538462,
9
- "count": 65,
10
- "eval_batches": 65,
11
- "eval_loss": 5.821129791553204,
12
- "execution_needed_accuracy": 0.8461538461538461,
13
- "mode_accuracy": 0.4461538461538462,
14
- "next_action_accuracy": 0.4307692307692308,
15
- "patch_continuity_accuracy": 0.6153846153846154,
16
- "proof_carrying_compatible_accuracy": 0.7692307692307693,
17
- "provenance_accuracy": 0.6153846153846154,
18
- "quality_score": 0.4452868058783377,
19
- "reverse_engineering_ready_accuracy": 0.8461538461538461,
20
- "tool_selfcheck_needed_accuracy": 0.7692307692307693,
21
- "validator_required_accuracy": 1.0,
22
- "verdict_accuracy": 0.47692307692307695,
23
- "worktree_safe_accuracy": 0.9230769230769231
24
- },
25
- "improved": true,
26
- "quality_score": 0.4452868058783377,
27
- "train_metrics": {
28
- "loss": 0.4255874376375597,
29
- "micro_batches": 182,
30
- "optimizer_steps": 12
31
- }
32
- },
33
- {
34
- "epoch": 2,
35
- "eval_metrics": {
36
- "avg_binary_accuracy": 0.8376068376068376,
37
- "citation_binding_required_accuracy": 1.0,
38
- "contradiction_visible_accuracy": 0.7384615384615385,
39
- "count": 65,
40
- "eval_batches": 65,
41
- "eval_loss": 4.975605465815618,
42
- "execution_needed_accuracy": 0.8461538461538461,
43
- "mode_accuracy": 0.5538461538461539,
44
- "next_action_accuracy": 0.5538461538461539,
45
- "patch_continuity_accuracy": 0.6461538461538462,
46
- "proof_carrying_compatible_accuracy": 0.7692307692307693,
47
- "provenance_accuracy": 0.6,
48
- "quality_score": 0.5249323351281322,
49
- "reverse_engineering_ready_accuracy": 0.8461538461538461,
50
- "tool_selfcheck_needed_accuracy": 0.7692307692307693,
51
- "validator_required_accuracy": 1.0,
52
- "verdict_accuracy": 0.5692307692307692,
53
- "worktree_safe_accuracy": 0.9230769230769231
54
- },
55
- "improved": true,
56
- "quality_score": 0.5249323351281322,
57
- "train_metrics": {
58
- "loss": 0.28522092685267164,
59
- "micro_batches": 182,
60
- "optimizer_steps": 12
61
- }
62
- },
63
- {
64
- "epoch": 3,
65
- "eval_metrics": {
66
- "avg_binary_accuracy": 0.8444444444444446,
67
- "citation_binding_required_accuracy": 1.0,
68
- "contradiction_visible_accuracy": 0.7692307692307693,
69
- "count": 65,
70
- "eval_batches": 65,
71
- "eval_loss": 4.801326029117291,
72
- "execution_needed_accuracy": 0.8461538461538461,
73
- "mode_accuracy": 0.5538461538461539,
74
- "next_action_accuracy": 0.5538461538461539,
75
- "patch_continuity_accuracy": 0.6461538461538462,
76
- "proof_carrying_compatible_accuracy": 0.8,
77
- "provenance_accuracy": 0.6307692307692307,
78
- "quality_score": 0.5544008298450047,
79
- "reverse_engineering_ready_accuracy": 0.8461538461538461,
80
- "tool_selfcheck_needed_accuracy": 0.7692307692307693,
81
- "validator_required_accuracy": 1.0,
82
- "verdict_accuracy": 0.6307692307692307,
83
- "worktree_safe_accuracy": 0.9230769230769231
84
- },
85
- "improved": true,
86
- "quality_score": 0.5544008298450047,
87
- "train_metrics": {
88
- "loss": 0.24240652721498038,
89
- "micro_batches": 182,
90
- "optimizer_steps": 12
91
- }
92
- },
93
- {
94
- "epoch": 4,
95
- "eval_metrics": {
96
- "avg_binary_accuracy": 0.8444444444444446,
97
- "citation_binding_required_accuracy": 1.0,
98
- "contradiction_visible_accuracy": 0.7692307692307693,
99
- "count": 65,
100
- "eval_batches": 65,
101
- "eval_loss": 4.7871557712554935,
102
- "execution_needed_accuracy": 0.8461538461538461,
103
- "mode_accuracy": 0.5692307692307692,
104
- "next_action_accuracy": 0.5538461538461539,
105
- "patch_continuity_accuracy": 0.6461538461538462,
106
- "proof_carrying_compatible_accuracy": 0.8,
107
- "provenance_accuracy": 0.6461538461538462,
108
- "quality_score": 0.5592996196176252,
109
- "reverse_engineering_ready_accuracy": 0.8461538461538461,
110
- "tool_selfcheck_needed_accuracy": 0.7692307692307693,
111
- "validator_required_accuracy": 1.0,
112
- "verdict_accuracy": 0.6307692307692307,
113
- "worktree_safe_accuracy": 0.9230769230769231
114
- },
115
- "improved": true,
116
- "quality_score": 0.5592996196176252,
117
- "train_metrics": {
118
- "loss": 0.23536107725985758,
119
- "micro_batches": 182,
120
- "optimizer_steps": 12
121
- }
122
- }
123
- ]
124
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
evidence_adapter/evidence_binding_adapter_plan.json DELETED
@@ -1,223 +0,0 @@
1
- {
2
- "backbone": "/public/wang_libo/veriloop_coder_e1/model",
3
- "dataset_summary": {
4
- "eval_size": 65,
5
- "mode_vocab": [
6
- "direct_support",
7
- "multi_support",
8
- "conflict_visible",
9
- "evidence_gap",
10
- "execution_needed",
11
- "high_risk_unbound",
12
- "validator_negation",
13
- "patch_regression",
14
- "worktree_conflict",
15
- "tool_selfcheck_confirmed",
16
- "tool_selfcheck_negated",
17
- "reverse_engineering_bindable",
18
- "reverse_engineering_gap"
19
- ],
20
- "modes": [
21
- "conflict_visible",
22
- "direct_support",
23
- "evidence_gap",
24
- "execution_needed",
25
- "high_risk_unbound",
26
- "multi_support",
27
- "patch_regression",
28
- "reverse_engineering_bindable",
29
- "reverse_engineering_gap",
30
- "tool_selfcheck_confirmed",
31
- "tool_selfcheck_negated",
32
- "validator_negation",
33
- "worktree_conflict"
34
- ],
35
- "next_action_vocab": [
36
- "none",
37
- "validator_review",
38
- "sandbox_exec",
39
- "selfcheck_exec",
40
- "bounded_observation",
41
- "fail_closed",
42
- "worktree_reconcile"
43
- ],
44
- "provenance_vocab": [
45
- "inadequate",
46
- "partial",
47
- "adequate"
48
- ],
49
- "train_size": 182,
50
- "verdict_vocab": [
51
- "supported",
52
- "conflicted",
53
- "insufficient",
54
- "execution_required"
55
- ]
56
- },
57
- "excluded_surfaces": [
58
- "(^|\\.)lm_head($|\\.)::Do not retune final token head; too broad and evaluation-heavy.",
59
- "(^|\\.)embed_tokens($|\\.)::Embedding surgery risks broad semantic drift.",
60
- "(^|\\.)norm($|\\.)::Global norm tuning can destabilize calibration across scenes.",
61
- "attnres|attention_residual::Block AttnRes may be mounted structurally but is never a PEFT target.",
62
- "dualpath::DualPath is serving/runtime infrastructure only.",
63
- "mhc|hyper[-_]?connection::mHC-inspired stability hooks remain structural, not PEFT surfaces.",
64
- "rope|rotary::RoPE/context surgery is handled architecturally, not by narrow PEFT here.",
65
- "kvcache|kv_cache::KV-cache runtime surfaces are not PEFT targets.",
66
- "(^|\\.)memory(_store|_bank)?($|\\.)::Persistent memory stores are harness/runtime policy surfaces, not PEFT targets."
67
- ],
68
- "notes": [
69
- "Primary route is host-surface-first evidence-binding training.",
70
- "Claim↔evidence fidelity, contradiction visibility, provenance discipline, validator receipts, execution-needed escalation, tool self-check compatibility, reverse-engineering boundedness, and proof-carrying hint obedience are first-class signals.",
71
- "DualPath, Block AttnRes, mHC hooks, visual branches, and MoE routers/experts remain structurally excluded.",
72
- "This adapter should improve evidence-gate obedience, not broad free-form coding behavior.",
73
- "Target coverage is rooted in the full evidence-binding decision graph rather than the selector-only subset, so execution/tool/citation/reverse-engineering surfaces are not silently left untuned."
74
- ],
75
- "peft_method": "lora_narrow",
76
- "product_line": "veriloop_coder",
77
- "recipe": {
78
- "adapter_family": "evidence_binding",
79
- "backbone": "/public/wang_libo/veriloop_coder_e1/model",
80
- "backbone_family": "qwen_dense",
81
- "excluded_patterns": [
82
- "(?i)\\bdualpath\\b",
83
- "(?i)\\bmhc\\b",
84
- "(?i)\\bfull[_\\- ]?attnres\\b",
85
- "(?i)\\battnres(_full)?\\b",
86
- "(?i)\\brouter\\b",
87
- "(?i)\\bexperts?\\b",
88
- "(?i)\\bmoe\\b.*\\b(gate|router|expert)\\b",
89
- "(?i)\\brope\\b.*\\b(freq|inv_freq|theta|rotary)\\b",
90
- "(?i)\\bkvcache\\b",
91
- "(?i)\\bposition_embedding\\b",
92
- "(?i)\\bembed(tokens|ding)?\\b",
93
- "(?i)\\blm_head\\b"
94
- ],
95
- "harness_constraints": [
96
- "Harness Engineering remains the primary convergence layer.",
97
- "Adapter must not bypass runtime orchestrator / validator / rollback loops.",
98
- "Adapter outputs remain subordinate to VeriLoop control-plane decisions.",
99
- "Adapter must not create hidden prompt-style memory authority.",
100
- "Adapter must support claim-evidence binding rather than generic retrieval verbosity.",
101
- "Unbound claims must remain rejectable or demotable."
102
- ],
103
- "hyperparams": {
104
- "alpha": 16,
105
- "bias": "none",
106
- "dropout": 0.05,
107
- "fan_in_fan_out": false,
108
- "modules_to_save": [],
109
- "r": 8,
110
- "task_type": "CAUSAL_LM"
111
- },
112
- "merge_policy": "merge_after_guard",
113
- "metadata": {
114
- "allow_backbone_bridge": false,
115
- "allow_vla_action_expert": false,
116
- "evidence_binding_training": true,
117
- "harness_first": true,
118
- "policy_target_floor_applied": true,
119
- "prefer_explicit_heads": true,
120
- "prefer_qlora_for_backbone_bridge": false,
121
- "require_harness_first": true,
122
- "reverse_engineering_readiness": true,
123
- "selector_group_count": 1,
124
- "strict_narrow_scope": true,
125
- "tool_selfcheck_readiness": true,
126
- "trainer": "veriloop.evidence_binding_adapter_trainer.v9.qwen36"
127
- },
128
- "notes": [
129
- "Backbone bridge tuning disabled explicitly; selector stays on custom surfaces or no-op.",
130
- "Backbone family inferred as qwen_dense.",
131
- "PEFT method resolved as lora_narrow.",
132
- "Recipe is harness-first: runtime convergence remains in VeriLoop control-plane + harness, not in broad weight surgery.",
133
- "Block AttnRes, DualPath, mHC hooks, RoPE, KV-cache, and broad MoE routing remain structurally excluded."
134
- ],
135
- "peft_method": "lora_narrow",
136
- "precision_policy": "auto",
137
- "product_line": "veriloop_coder",
138
- "regression_requirements": [
139
- "Must pass PEFT regression guard structural policy checks.",
140
- "Must not introduce forbidden backbone/serving structural targets.",
141
- "Must preserve harness regression envelope for the selected product line.",
142
- "Evidence-conclusion alignment must not regress.",
143
- "High-risk fabrication rate must not increase."
144
- ],
145
- "target_groups": [
146
- {
147
- "alpha": 16,
148
- "dropout": 0.0,
149
- "name": "group_1_custom_control_head",
150
- "rank": 8,
151
- "rationale": "Evidence alignment should land on explicit binding surfaces first.",
152
- "surface": "custom_control_head",
153
- "target_modules": [
154
- "claim_extractor.adapter",
155
- "evidence_binding.adapter",
156
- "proof_carrying_hints.bridge"
157
- ]
158
- },
159
- {
160
- "alpha": 16,
161
- "dropout": 0.0,
162
- "name": "group_policy_expanded_evidence_binding_surface_set",
163
- "rank": 8,
164
- "rationale": "Expand selector-narrow targets to the full host-side evidence-binding decision graph used by verdict/provenance/next-action heads.",
165
- "surface": "policy_expanded_evidence_binding_surface_set",
166
- "target_modules": [
167
- "provenance_binding.adapter",
168
- "validator_receipt_bridge.adapter",
169
- "tool_receipt_binding.adapter",
170
- "execution_binding.adapter",
171
- "citation_binding.adapter",
172
- "runtime_binding.adapter",
173
- "selfcheck_binding.adapter",
174
- "reverse_engineering_binding.adapter",
175
- "patch_binding.adapter",
176
- "worktree_binding.adapter"
177
- ]
178
- }
179
- ],
180
- "target_modules": [
181
- "claim_extractor.adapter",
182
- "evidence_binding.adapter",
183
- "proof_carrying_hints.bridge",
184
- "provenance_binding.adapter",
185
- "validator_receipt_bridge.adapter",
186
- "tool_receipt_binding.adapter",
187
- "execution_binding.adapter",
188
- "citation_binding.adapter",
189
- "runtime_binding.adapter",
190
- "selfcheck_binding.adapter",
191
- "reverse_engineering_binding.adapter",
192
- "patch_binding.adapter",
193
- "worktree_binding.adapter"
194
- ],
195
- "version": "veriloop.lora_recipe_veriloop.v2"
196
- },
197
- "selected_surfaces": [
198
- "custom_control_head",
199
- "policy_expanded_evidence_binding_surface_set"
200
- ],
201
- "selected_target_modules": [
202
- "claim_extractor.adapter",
203
- "evidence_binding.adapter",
204
- "proof_carrying_hints.bridge",
205
- "provenance_binding.adapter",
206
- "validator_receipt_bridge.adapter",
207
- "tool_receipt_binding.adapter",
208
- "execution_binding.adapter",
209
- "citation_binding.adapter",
210
- "runtime_binding.adapter",
211
- "selfcheck_binding.adapter",
212
- "reverse_engineering_binding.adapter",
213
- "patch_binding.adapter",
214
- "worktree_binding.adapter"
215
- ],
216
- "selection_mode": "minimal",
217
- "version": "veriloop.evidence_binding_adapter_trainer.v9.qwen36",
218
- "warnings": [
219
- "Harness Engineering is primary; PEFT is limited to obedience-facing, interface-facing support surfaces.",
220
- "Backbone bridge tuning disabled explicitly; selector stays on custom surfaces or no-op.",
221
- "Selector target set was narrower than the evidence-binding decision graph; host-side policy floor expanded the PEFT targets."
222
- ]
223
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
evidence_adapter/evidence_binding_adapter_train_result.json DELETED
@@ -1,338 +0,0 @@
1
- {
2
- "artifacts": {
3
- "adapter_dir": "/private/wang_libo/veriloop_coder_e1/outputs/evidence_binding_qwen36_run1/adapter",
4
- "best_checkpoint_manifest": "/private/wang_libo/veriloop_coder_e1/outputs/evidence_binding_qwen36_run1/best_checkpoint_manifest.json",
5
- "epoch_history": "/private/wang_libo/veriloop_coder_e1/outputs/evidence_binding_qwen36_run1/epoch_history.json",
6
- "eval_jsonl": "/private/wang_libo/veriloop_coder_e1/outputs/evidence_binding_qwen36_run1/evidence_binding_eval.jsonl",
7
- "evidence_binding_head": "/private/wang_libo/veriloop_coder_e1/outputs/evidence_binding_qwen36_run1/evidence_binding_head.pt",
8
- "host_manifest": "/private/wang_libo/veriloop_coder_e1/outputs/evidence_binding_qwen36_run1/host_manifest.json",
9
- "plan_json": "/private/wang_libo/veriloop_coder_e1/outputs/evidence_binding_qwen36_run1/evidence_binding_adapter_plan.json",
10
- "tokenizer_dir": "/private/wang_libo/veriloop_coder_e1/outputs/evidence_binding_qwen36_run1/tokenizer",
11
- "train_jsonl": "/private/wang_libo/veriloop_coder_e1/outputs/evidence_binding_qwen36_run1/evidence_binding_train.jsonl",
12
- "training_manifest": "/private/wang_libo/veriloop_coder_e1/outputs/evidence_binding_qwen36_run1/evidence_binding_training_manifest.json"
13
- },
14
- "dataset": {
15
- "eval_size": 65,
16
- "mode_vocab": [
17
- "direct_support",
18
- "multi_support",
19
- "conflict_visible",
20
- "evidence_gap",
21
- "execution_needed",
22
- "high_risk_unbound",
23
- "validator_negation",
24
- "patch_regression",
25
- "worktree_conflict",
26
- "tool_selfcheck_confirmed",
27
- "tool_selfcheck_negated",
28
- "reverse_engineering_bindable",
29
- "reverse_engineering_gap"
30
- ],
31
- "modes": [
32
- "conflict_visible",
33
- "direct_support",
34
- "evidence_gap",
35
- "execution_needed",
36
- "high_risk_unbound",
37
- "multi_support",
38
- "patch_regression",
39
- "reverse_engineering_bindable",
40
- "reverse_engineering_gap",
41
- "tool_selfcheck_confirmed",
42
- "tool_selfcheck_negated",
43
- "validator_negation",
44
- "worktree_conflict"
45
- ],
46
- "next_action_vocab": [
47
- "none",
48
- "validator_review",
49
- "sandbox_exec",
50
- "selfcheck_exec",
51
- "bounded_observation",
52
- "fail_closed",
53
- "worktree_reconcile"
54
- ],
55
- "provenance_vocab": [
56
- "inadequate",
57
- "partial",
58
- "adequate"
59
- ],
60
- "train_size": 182,
61
- "verdict_vocab": [
62
- "supported",
63
- "conflicted",
64
- "insufficient",
65
- "execution_required"
66
- ]
67
- },
68
- "eval_metrics": {
69
- "adapter_exported": true,
70
- "auto_lora_from_ia3": false,
71
- "avg_binary_accuracy": 0.8444444444444446,
72
- "best_epoch": 4,
73
- "best_quality_score": 0.5592996196176252,
74
- "citation_binding_required_accuracy": 1.0,
75
- "contradiction_visible_accuracy": 0.7692307692307693,
76
- "count": 65,
77
- "eval_batches": 65,
78
- "eval_loss": 4.7871557712554935,
79
- "execution_needed_accuracy": 0.8461538461538461,
80
- "mode_accuracy": 0.5692307692307692,
81
- "next_action_accuracy": 0.5538461538461539,
82
- "patch_continuity_accuracy": 0.6461538461538462,
83
- "peft_method": "lora_narrow",
84
- "proof_carrying_compatible_accuracy": 0.8,
85
- "provenance_accuracy": 0.6461538461538462,
86
- "quality_score": 0.5592996196176252,
87
- "reverse_engineering_ready_accuracy": 0.8461538461538461,
88
- "tool_selfcheck_needed_accuracy": 0.7692307692307693,
89
- "used_peft": true,
90
- "validator_required_accuracy": 1.0,
91
- "verdict_accuracy": 0.6307692307692307,
92
- "worktree_safe_accuracy": 0.9230769230769231
93
- },
94
- "plan": {
95
- "backbone": "/public/wang_libo/veriloop_coder_e1/model",
96
- "dataset_summary": {
97
- "eval_size": 65,
98
- "mode_vocab": [
99
- "direct_support",
100
- "multi_support",
101
- "conflict_visible",
102
- "evidence_gap",
103
- "execution_needed",
104
- "high_risk_unbound",
105
- "validator_negation",
106
- "patch_regression",
107
- "worktree_conflict",
108
- "tool_selfcheck_confirmed",
109
- "tool_selfcheck_negated",
110
- "reverse_engineering_bindable",
111
- "reverse_engineering_gap"
112
- ],
113
- "modes": [
114
- "conflict_visible",
115
- "direct_support",
116
- "evidence_gap",
117
- "execution_needed",
118
- "high_risk_unbound",
119
- "multi_support",
120
- "patch_regression",
121
- "reverse_engineering_bindable",
122
- "reverse_engineering_gap",
123
- "tool_selfcheck_confirmed",
124
- "tool_selfcheck_negated",
125
- "validator_negation",
126
- "worktree_conflict"
127
- ],
128
- "next_action_vocab": [
129
- "none",
130
- "validator_review",
131
- "sandbox_exec",
132
- "selfcheck_exec",
133
- "bounded_observation",
134
- "fail_closed",
135
- "worktree_reconcile"
136
- ],
137
- "provenance_vocab": [
138
- "inadequate",
139
- "partial",
140
- "adequate"
141
- ],
142
- "train_size": 182,
143
- "verdict_vocab": [
144
- "supported",
145
- "conflicted",
146
- "insufficient",
147
- "execution_required"
148
- ]
149
- },
150
- "excluded_surfaces": [
151
- "(^|\\.)lm_head($|\\.)::Do not retune final token head; too broad and evaluation-heavy.",
152
- "(^|\\.)embed_tokens($|\\.)::Embedding surgery risks broad semantic drift.",
153
- "(^|\\.)norm($|\\.)::Global norm tuning can destabilize calibration across scenes.",
154
- "attnres|attention_residual::Block AttnRes may be mounted structurally but is never a PEFT target.",
155
- "dualpath::DualPath is serving/runtime infrastructure only.",
156
- "mhc|hyper[-_]?connection::mHC-inspired stability hooks remain structural, not PEFT surfaces.",
157
- "rope|rotary::RoPE/context surgery is handled architecturally, not by narrow PEFT here.",
158
- "kvcache|kv_cache::KV-cache runtime surfaces are not PEFT targets.",
159
- "(^|\\.)memory(_store|_bank)?($|\\.)::Persistent memory stores are harness/runtime policy surfaces, not PEFT targets."
160
- ],
161
- "notes": [
162
- "Primary route is host-surface-first evidence-binding training.",
163
- "Claim↔evidence fidelity, contradiction visibility, provenance discipline, validator receipts, execution-needed escalation, tool self-check compatibility, reverse-engineering boundedness, and proof-carrying hint obedience are first-class signals.",
164
- "DualPath, Block AttnRes, mHC hooks, visual branches, and MoE routers/experts remain structurally excluded.",
165
- "This adapter should improve evidence-gate obedience, not broad free-form coding behavior.",
166
- "Target coverage is rooted in the full evidence-binding decision graph rather than the selector-only subset, so execution/tool/citation/reverse-engineering surfaces are not silently left untuned."
167
- ],
168
- "peft_method": "lora_narrow",
169
- "product_line": "veriloop_coder",
170
- "recipe": {
171
- "adapter_family": "evidence_binding",
172
- "backbone": "/public/wang_libo/veriloop_coder_e1/model",
173
- "backbone_family": "qwen_dense",
174
- "excluded_patterns": [
175
- "(?i)\\bdualpath\\b",
176
- "(?i)\\bmhc\\b",
177
- "(?i)\\bfull[_\\- ]?attnres\\b",
178
- "(?i)\\battnres(_full)?\\b",
179
- "(?i)\\brouter\\b",
180
- "(?i)\\bexperts?\\b",
181
- "(?i)\\bmoe\\b.*\\b(gate|router|expert)\\b",
182
- "(?i)\\brope\\b.*\\b(freq|inv_freq|theta|rotary)\\b",
183
- "(?i)\\bkvcache\\b",
184
- "(?i)\\bposition_embedding\\b",
185
- "(?i)\\bembed(tokens|ding)?\\b",
186
- "(?i)\\blm_head\\b"
187
- ],
188
- "harness_constraints": [
189
- "Harness Engineering remains the primary convergence layer.",
190
- "Adapter must not bypass runtime orchestrator / validator / rollback loops.",
191
- "Adapter outputs remain subordinate to VeriLoop control-plane decisions.",
192
- "Adapter must not create hidden prompt-style memory authority.",
193
- "Adapter must support claim-evidence binding rather than generic retrieval verbosity.",
194
- "Unbound claims must remain rejectable or demotable."
195
- ],
196
- "hyperparams": {
197
- "alpha": 16,
198
- "bias": "none",
199
- "dropout": 0.05,
200
- "fan_in_fan_out": false,
201
- "modules_to_save": [],
202
- "r": 8,
203
- "task_type": "CAUSAL_LM"
204
- },
205
- "merge_policy": "merge_after_guard",
206
- "metadata": {
207
- "allow_backbone_bridge": false,
208
- "allow_vla_action_expert": false,
209
- "evidence_binding_training": true,
210
- "harness_first": true,
211
- "policy_target_floor_applied": true,
212
- "prefer_explicit_heads": true,
213
- "prefer_qlora_for_backbone_bridge": false,
214
- "require_harness_first": true,
215
- "reverse_engineering_readiness": true,
216
- "selector_group_count": 1,
217
- "strict_narrow_scope": true,
218
- "tool_selfcheck_readiness": true,
219
- "trainer": "veriloop.evidence_binding_adapter_trainer.v9.qwen36"
220
- },
221
- "notes": [
222
- "Backbone bridge tuning disabled explicitly; selector stays on custom surfaces or no-op.",
223
- "Backbone family inferred as qwen_dense.",
224
- "PEFT method resolved as lora_narrow.",
225
- "Recipe is harness-first: runtime convergence remains in VeriLoop control-plane + harness, not in broad weight surgery.",
226
- "Block AttnRes, DualPath, mHC hooks, RoPE, KV-cache, and broad MoE routing remain structurally excluded."
227
- ],
228
- "peft_method": "lora_narrow",
229
- "precision_policy": "auto",
230
- "product_line": "veriloop_coder",
231
- "regression_requirements": [
232
- "Must pass PEFT regression guard structural policy checks.",
233
- "Must not introduce forbidden backbone/serving structural targets.",
234
- "Must preserve harness regression envelope for the selected product line.",
235
- "Evidence-conclusion alignment must not regress.",
236
- "High-risk fabrication rate must not increase."
237
- ],
238
- "target_groups": [
239
- {
240
- "alpha": 16,
241
- "dropout": 0.0,
242
- "name": "group_1_custom_control_head",
243
- "rank": 8,
244
- "rationale": "Evidence alignment should land on explicit binding surfaces first.",
245
- "surface": "custom_control_head",
246
- "target_modules": [
247
- "claim_extractor.adapter",
248
- "evidence_binding.adapter",
249
- "proof_carrying_hints.bridge"
250
- ]
251
- },
252
- {
253
- "alpha": 16,
254
- "dropout": 0.0,
255
- "name": "group_policy_expanded_evidence_binding_surface_set",
256
- "rank": 8,
257
- "rationale": "Expand selector-narrow targets to the full host-side evidence-binding decision graph used by verdict/provenance/next-action heads.",
258
- "surface": "policy_expanded_evidence_binding_surface_set",
259
- "target_modules": [
260
- "provenance_binding.adapter",
261
- "validator_receipt_bridge.adapter",
262
- "tool_receipt_binding.adapter",
263
- "execution_binding.adapter",
264
- "citation_binding.adapter",
265
- "runtime_binding.adapter",
266
- "selfcheck_binding.adapter",
267
- "reverse_engineering_binding.adapter",
268
- "patch_binding.adapter",
269
- "worktree_binding.adapter"
270
- ]
271
- }
272
- ],
273
- "target_modules": [
274
- "claim_extractor.adapter",
275
- "evidence_binding.adapter",
276
- "proof_carrying_hints.bridge",
277
- "provenance_binding.adapter",
278
- "validator_receipt_bridge.adapter",
279
- "tool_receipt_binding.adapter",
280
- "execution_binding.adapter",
281
- "citation_binding.adapter",
282
- "runtime_binding.adapter",
283
- "selfcheck_binding.adapter",
284
- "reverse_engineering_binding.adapter",
285
- "patch_binding.adapter",
286
- "worktree_binding.adapter"
287
- ],
288
- "version": "veriloop.lora_recipe_veriloop.v2"
289
- },
290
- "selected_surfaces": [
291
- "custom_control_head",
292
- "policy_expanded_evidence_binding_surface_set"
293
- ],
294
- "selected_target_modules": [
295
- "claim_extractor.adapter",
296
- "evidence_binding.adapter",
297
- "proof_carrying_hints.bridge",
298
- "provenance_binding.adapter",
299
- "validator_receipt_bridge.adapter",
300
- "tool_receipt_binding.adapter",
301
- "execution_binding.adapter",
302
- "citation_binding.adapter",
303
- "runtime_binding.adapter",
304
- "selfcheck_binding.adapter",
305
- "reverse_engineering_binding.adapter",
306
- "patch_binding.adapter",
307
- "worktree_binding.adapter"
308
- ],
309
- "selection_mode": "minimal",
310
- "version": "veriloop.evidence_binding_adapter_trainer.v9.qwen36",
311
- "warnings": [
312
- "Harness Engineering is primary; PEFT is limited to obedience-facing, interface-facing support surfaces.",
313
- "Backbone bridge tuning disabled explicitly; selector stays on custom surfaces or no-op.",
314
- "Selector target set was narrower than the evidence-binding decision graph; host-side policy floor expanded the PEFT targets."
315
- ]
316
- },
317
- "status": "trained",
318
- "train_metrics": {
319
- "adapter_exported": true,
320
- "auto_lora_from_ia3": false,
321
- "best_epoch": 4,
322
- "best_quality_score": 0.5592996196176252,
323
- "epochs_completed": 4,
324
- "loss": 0.23536107725985758,
325
- "micro_batches": 182,
326
- "micro_batches_total": 728,
327
- "optimizer_steps": 12,
328
- "optimizer_steps_total": 48,
329
- "peft_method": "lora_narrow",
330
- "used_peft": true
331
- },
332
- "version": "veriloop.evidence_binding_adapter_trainer.v9.qwen36",
333
- "warnings": [
334
- "Harness Engineering is primary; PEFT is limited to obedience-facing, interface-facing support surfaces.",
335
- "Backbone bridge tuning disabled explicitly; selector stays on custom surfaces or no-op.",
336
- "Selector target set was narrower than the evidence-binding decision graph; host-side policy floor expanded the PEFT targets."
337
- ]
338
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
evidence_adapter/evidence_binding_eval.jsonl DELETED
The diff for this file is too large to render. See raw diff
 
evidence_adapter/evidence_binding_head.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e85ad23a3e89f3d07cbbe6352f185277569160e403a41acdbf36f3fb1e182bc0
3
- size 340358929
 
 
 
 
evidence_adapter/evidence_binding_train.jsonl DELETED
The diff for this file is too large to render. See raw diff
 
evidence_adapter/evidence_binding_training_manifest.json DELETED
@@ -1,120 +0,0 @@
1
- {
2
- "adapter_exported": true,
3
- "dataset_summary": {
4
- "eval_size": 65,
5
- "mode_vocab": [
6
- "direct_support",
7
- "multi_support",
8
- "conflict_visible",
9
- "evidence_gap",
10
- "execution_needed",
11
- "high_risk_unbound",
12
- "validator_negation",
13
- "patch_regression",
14
- "worktree_conflict",
15
- "tool_selfcheck_confirmed",
16
- "tool_selfcheck_negated",
17
- "reverse_engineering_bindable",
18
- "reverse_engineering_gap"
19
- ],
20
- "modes": [
21
- "conflict_visible",
22
- "direct_support",
23
- "evidence_gap",
24
- "execution_needed",
25
- "high_risk_unbound",
26
- "multi_support",
27
- "patch_regression",
28
- "reverse_engineering_bindable",
29
- "reverse_engineering_gap",
30
- "tool_selfcheck_confirmed",
31
- "tool_selfcheck_negated",
32
- "validator_negation",
33
- "worktree_conflict"
34
- ],
35
- "next_action_vocab": [
36
- "none",
37
- "validator_review",
38
- "sandbox_exec",
39
- "selfcheck_exec",
40
- "bounded_observation",
41
- "fail_closed",
42
- "worktree_reconcile"
43
- ],
44
- "provenance_vocab": [
45
- "inadequate",
46
- "partial",
47
- "adequate"
48
- ],
49
- "train_size": 182,
50
- "verdict_vocab": [
51
- "supported",
52
- "conflicted",
53
- "insufficient",
54
- "execution_required"
55
- ]
56
- },
57
- "eval_metrics": {
58
- "adapter_exported": true,
59
- "auto_lora_from_ia3": false,
60
- "avg_binary_accuracy": 0.8444444444444446,
61
- "best_epoch": 4,
62
- "best_quality_score": 0.5592996196176252,
63
- "citation_binding_required_accuracy": 1.0,
64
- "contradiction_visible_accuracy": 0.7692307692307693,
65
- "count": 65,
66
- "eval_batches": 65,
67
- "eval_loss": 4.7871557712554935,
68
- "execution_needed_accuracy": 0.8461538461538461,
69
- "mode_accuracy": 0.5692307692307692,
70
- "next_action_accuracy": 0.5538461538461539,
71
- "patch_continuity_accuracy": 0.6461538461538462,
72
- "peft_method": "lora_narrow",
73
- "proof_carrying_compatible_accuracy": 0.8,
74
- "provenance_accuracy": 0.6461538461538462,
75
- "quality_score": 0.5592996196176252,
76
- "reverse_engineering_ready_accuracy": 0.8461538461538461,
77
- "tool_selfcheck_needed_accuracy": 0.7692307692307693,
78
- "used_peft": true,
79
- "validator_required_accuracy": 1.0,
80
- "verdict_accuracy": 0.6307692307692307,
81
- "worktree_safe_accuracy": 0.9230769230769231
82
- },
83
- "load_meta": {
84
- "chosen_class": "AutoModelForCausalLM",
85
- "hidden_size": 2048,
86
- "quantization_mode": "4bit"
87
- },
88
- "peft_method": "lora_narrow",
89
- "selected_target_modules": [
90
- "claim_extractor.adapter",
91
- "evidence_binding.adapter",
92
- "proof_carrying_hints.bridge",
93
- "provenance_binding.adapter",
94
- "validator_receipt_bridge.adapter",
95
- "tool_receipt_binding.adapter",
96
- "execution_binding.adapter",
97
- "citation_binding.adapter",
98
- "runtime_binding.adapter",
99
- "selfcheck_binding.adapter",
100
- "reverse_engineering_binding.adapter",
101
- "patch_binding.adapter",
102
- "worktree_binding.adapter"
103
- ],
104
- "status": "trained",
105
- "train_metrics": {
106
- "adapter_exported": true,
107
- "auto_lora_from_ia3": false,
108
- "best_epoch": 4,
109
- "best_quality_score": 0.5592996196176252,
110
- "epochs_completed": 4,
111
- "loss": 0.23536107725985758,
112
- "micro_batches": 182,
113
- "micro_batches_total": 728,
114
- "optimizer_steps": 12,
115
- "optimizer_steps_total": 48,
116
- "peft_method": "lora_narrow",
117
- "used_peft": true
118
- },
119
- "used_peft": true
120
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
evidence_adapter/host_manifest.json DELETED
@@ -1,268 +0,0 @@
1
- {
2
- "hidden_size": 2048,
3
- "host_config": {
4
- "attn_implementation": null,
5
- "backbone_name_or_path": "/public/wang_libo/veriloop_coder_e1/model",
6
- "device_map": null,
7
- "dtype": null,
8
- "evidence_rank_hint": 8,
9
- "expose_backbone_inventory": false,
10
- "freeze_backbone": true,
11
- "hidden_size_override": 2048,
12
- "host_dropout": 0.0,
13
- "identity_rank_hint": 8,
14
- "load_backbone_weights": false,
15
- "local_files_only": true,
16
- "low_cpu_mem_usage": true,
17
- "memory_rank_hint": 4,
18
- "rollback_rank_hint": 8,
19
- "runtime_rank_hint": 8,
20
- "toolspec_rank_hint": 8,
21
- "trust_remote_code": true,
22
- "uncertainty_rank_hint": 8,
23
- "use_safetensors": null,
24
- "validator_rank_hint": 8
25
- },
26
- "load_result": {
27
- "has_base_config": true,
28
- "has_base_model": true,
29
- "hidden_size": 2048,
30
- "notes": [
31
- "class=AutoModelForCausalLM",
32
- "quant=4bit"
33
- ],
34
- "source": "trainer_qwen36_loader"
35
- },
36
- "peft_named_modules": [
37
- "citation_binding",
38
- "citation_binding.adapter",
39
- "citation_binding.adapter.base_layer",
40
- "citation_binding.adapter.lora_A",
41
- "citation_binding.adapter.lora_A.default",
42
- "citation_binding.adapter.lora_B",
43
- "citation_binding.adapter.lora_B.default",
44
- "citation_binding.adapter.lora_dropout",
45
- "citation_binding.adapter.lora_dropout.default",
46
- "citation_binding.adapter.lora_embedding_A",
47
- "citation_binding.adapter.lora_embedding_B",
48
- "citation_binding.adapter.lora_magnitude_vector",
49
- "claim_extractor",
50
- "claim_extractor.adapter",
51
- "claim_extractor.adapter.base_layer",
52
- "claim_extractor.adapter.lora_A",
53
- "claim_extractor.adapter.lora_A.default",
54
- "claim_extractor.adapter.lora_B",
55
- "claim_extractor.adapter.lora_B.default",
56
- "claim_extractor.adapter.lora_dropout",
57
- "claim_extractor.adapter.lora_dropout.default",
58
- "claim_extractor.adapter.lora_embedding_A",
59
- "claim_extractor.adapter.lora_embedding_B",
60
- "claim_extractor.adapter.lora_magnitude_vector",
61
- "dropout",
62
- "episodic_memory",
63
- "episodic_memory.adapter",
64
- "evidence_binding",
65
- "evidence_binding.adapter",
66
- "evidence_binding.adapter.base_layer",
67
- "evidence_binding.adapter.lora_A",
68
- "evidence_binding.adapter.lora_A.default",
69
- "evidence_binding.adapter.lora_B",
70
- "evidence_binding.adapter.lora_B.default",
71
- "evidence_binding.adapter.lora_dropout",
72
- "evidence_binding.adapter.lora_dropout.default",
73
- "evidence_binding.adapter.lora_embedding_A",
74
- "evidence_binding.adapter.lora_embedding_B",
75
- "evidence_binding.adapter.lora_magnitude_vector",
76
- "execution_binding",
77
- "execution_binding.adapter",
78
- "execution_binding.adapter.base_layer",
79
- "execution_binding.adapter.lora_A",
80
- "execution_binding.adapter.lora_A.default",
81
- "execution_binding.adapter.lora_B",
82
- "execution_binding.adapter.lora_B.default",
83
- "execution_binding.adapter.lora_dropout",
84
- "execution_binding.adapter.lora_dropout.default",
85
- "execution_binding.adapter.lora_embedding_A",
86
- "execution_binding.adapter.lora_embedding_B",
87
- "execution_binding.adapter.lora_magnitude_vector",
88
- "failure_signal_bridge",
89
- "failure_signal_bridge.rollback_bridge",
90
- "identity_adapter",
91
- "identity_adapter.bridge",
92
- "identity_guard",
93
- "identity_guard.adapter",
94
- "input_norm",
95
- "memory_boundary_guard",
96
- "memory_boundary_guard.adapter",
97
- "memory_boundary_guard.rollback_filter",
98
- "patch_binding",
99
- "patch_binding.adapter",
100
- "patch_binding.adapter.base_layer",
101
- "patch_binding.adapter.lora_A",
102
- "patch_binding.adapter.lora_A.default",
103
- "patch_binding.adapter.lora_B",
104
- "patch_binding.adapter.lora_B.default",
105
- "patch_binding.adapter.lora_dropout",
106
- "patch_binding.adapter.lora_dropout.default",
107
- "patch_binding.adapter.lora_embedding_A",
108
- "patch_binding.adapter.lora_embedding_B",
109
- "patch_binding.adapter.lora_magnitude_vector",
110
- "permission_context_manager",
111
- "permission_context_manager.adapter",
112
- "progress_state_tracker",
113
- "progress_state_tracker.adapter",
114
- "progress_state_tracker.rollback_memory",
115
- "proof_carrying_hints",
116
- "proof_carrying_hints.bridge",
117
- "proof_carrying_hints.bridge.base_layer",
118
- "proof_carrying_hints.bridge.lora_A",
119
- "proof_carrying_hints.bridge.lora_A.default",
120
- "proof_carrying_hints.bridge.lora_B",
121
- "proof_carrying_hints.bridge.lora_B.default",
122
- "proof_carrying_hints.bridge.lora_dropout",
123
- "proof_carrying_hints.bridge.lora_dropout.default",
124
- "proof_carrying_hints.bridge.lora_embedding_A",
125
- "proof_carrying_hints.bridge.lora_embedding_B",
126
- "proof_carrying_hints.bridge.lora_magnitude_vector",
127
- "provenance_binding",
128
- "provenance_binding.adapter",
129
- "provenance_binding.adapter.base_layer",
130
- "provenance_binding.adapter.lora_A",
131
- "provenance_binding.adapter.lora_A.default",
132
- "provenance_binding.adapter.lora_B",
133
- "provenance_binding.adapter.lora_B.default",
134
- "provenance_binding.adapter.lora_dropout",
135
- "provenance_binding.adapter.lora_dropout.default",
136
- "provenance_binding.adapter.lora_embedding_A",
137
- "provenance_binding.adapter.lora_embedding_B",
138
- "provenance_binding.adapter.lora_magnitude_vector",
139
- "public_identity_head",
140
- "public_identity_head.proj",
141
- "query_runtime_engine",
142
- "query_runtime_engine.adapter",
143
- "request_normalizer",
144
- "request_normalizer.adapter",
145
- "reverse_engineering_binding",
146
- "reverse_engineering_binding.adapter",
147
- "reverse_engineering_binding.adapter.base_layer",
148
- "reverse_engineering_binding.adapter.lora_A",
149
- "reverse_engineering_binding.adapter.lora_A.default",
150
- "reverse_engineering_binding.adapter.lora_B",
151
- "reverse_engineering_binding.adapter.lora_B.default",
152
- "reverse_engineering_binding.adapter.lora_dropout",
153
- "reverse_engineering_binding.adapter.lora_dropout.default",
154
- "reverse_engineering_binding.adapter.lora_embedding_A",
155
- "reverse_engineering_binding.adapter.lora_embedding_B",
156
- "reverse_engineering_binding.adapter.lora_magnitude_vector",
157
- "rollback_adapter",
158
- "rollback_adapter.head",
159
- "rollback_engine",
160
- "rollback_engine.adapter",
161
- "runtime_binding",
162
- "runtime_binding.adapter",
163
- "runtime_binding.adapter.base_layer",
164
- "runtime_binding.adapter.lora_A",
165
- "runtime_binding.adapter.lora_A.default",
166
- "runtime_binding.adapter.lora_B",
167
- "runtime_binding.adapter.lora_B.default",
168
- "runtime_binding.adapter.lora_dropout",
169
- "runtime_binding.adapter.lora_dropout.default",
170
- "runtime_binding.adapter.lora_embedding_A",
171
- "runtime_binding.adapter.lora_embedding_B",
172
- "runtime_binding.adapter.lora_magnitude_vector",
173
- "runtime_harness_adapter",
174
- "runtime_harness_adapter.bridge",
175
- "runtime_harness_uncertainty_bridge",
176
- "runtime_harness_uncertainty_bridge.adapter",
177
- "sandbox_rollback_bridge",
178
- "sandbox_rollback_bridge.adapter",
179
- "selfcheck_binding",
180
- "selfcheck_binding.adapter",
181
- "selfcheck_binding.adapter.base_layer",
182
- "selfcheck_binding.adapter.lora_A",
183
- "selfcheck_binding.adapter.lora_A.default",
184
- "selfcheck_binding.adapter.lora_B",
185
- "selfcheck_binding.adapter.lora_B.default",
186
- "selfcheck_binding.adapter.lora_dropout",
187
- "selfcheck_binding.adapter.lora_dropout.default",
188
- "selfcheck_binding.adapter.lora_embedding_A",
189
- "selfcheck_binding.adapter.lora_embedding_B",
190
- "selfcheck_binding.adapter.lora_magnitude_vector",
191
- "session_compactor",
192
- "session_compactor.adapter",
193
- "session_state_manager",
194
- "session_state_manager.adapter",
195
- "session_state_manager.rollback_state",
196
- "tool_protocol_adapter",
197
- "tool_protocol_adapter.bridge",
198
- "tool_receipt_binding",
199
- "tool_receipt_binding.adapter",
200
- "tool_receipt_binding.adapter.base_layer",
201
- "tool_receipt_binding.adapter.lora_A",
202
- "tool_receipt_binding.adapter.lora_A.default",
203
- "tool_receipt_binding.adapter.lora_B",
204
- "tool_receipt_binding.adapter.lora_B.default",
205
- "tool_receipt_binding.adapter.lora_dropout",
206
- "tool_receipt_binding.adapter.lora_dropout.default",
207
- "tool_receipt_binding.adapter.lora_embedding_A",
208
- "tool_receipt_binding.adapter.lora_embedding_B",
209
- "tool_receipt_binding.adapter.lora_magnitude_vector",
210
- "toolspec_bridge",
211
- "toolspec_bridge.adapter",
212
- "toolspec_head",
213
- "toolspec_head.param_schema_adapter",
214
- "toolspec_head.postcondition_adapter",
215
- "toolspec_head.precondition_adapter",
216
- "toolspec_head.receipt_formatter",
217
- "toolspec_head.trigger_gate",
218
- "toolspec_head.validator_gate",
219
- "uncertainty_head",
220
- "uncertainty_head.calibration_mlp",
221
- "uncertainty_head.proj",
222
- "validator_feedback_bridge",
223
- "validator_feedback_bridge.adapter",
224
- "validator_feedback_loop",
225
- "validator_feedback_loop.rollback_adapter",
226
- "validator_receipt_bridge",
227
- "validator_receipt_bridge.adapter",
228
- "validator_receipt_bridge.adapter.base_layer",
229
- "validator_receipt_bridge.adapter.lora_A",
230
- "validator_receipt_bridge.adapter.lora_A.default",
231
- "validator_receipt_bridge.adapter.lora_B",
232
- "validator_receipt_bridge.adapter.lora_B.default",
233
- "validator_receipt_bridge.adapter.lora_dropout",
234
- "validator_receipt_bridge.adapter.lora_dropout.default",
235
- "validator_receipt_bridge.adapter.lora_embedding_A",
236
- "validator_receipt_bridge.adapter.lora_embedding_B",
237
- "validator_receipt_bridge.adapter.lora_magnitude_vector",
238
- "validator_uncertainty_bridge",
239
- "validator_uncertainty_bridge.adapter",
240
- "workspace_snapshot_manager",
241
- "workspace_snapshot_manager.rollback_context",
242
- "worktree_binding",
243
- "worktree_binding.adapter",
244
- "worktree_binding.adapter.base_layer",
245
- "worktree_binding.adapter.lora_A",
246
- "worktree_binding.adapter.lora_A.default",
247
- "worktree_binding.adapter.lora_B",
248
- "worktree_binding.adapter.lora_B.default",
249
- "worktree_binding.adapter.lora_dropout",
250
- "worktree_binding.adapter.lora_dropout.default",
251
- "worktree_binding.adapter.lora_embedding_A",
252
- "worktree_binding.adapter.lora_embedding_B",
253
- "worktree_binding.adapter.lora_magnitude_vector",
254
- "worktree_manager",
255
- "worktree_manager.adapter"
256
- ],
257
- "trainable_parameter_report": {
258
- "backbone_frozen": true,
259
- "backbone_present": true,
260
- "hidden_size": 2048,
261
- "host_parameters": 197668869,
262
- "host_trainable_parameters": 425984,
263
- "total_parameters": 34153726597,
264
- "trainable_parameters": 425984,
265
- "version": "veriloop.coder_peft_host.v1"
266
- },
267
- "version": "veriloop.coder_peft_host.v1"
268
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
evidence_adapter/tokenizer/chat_template.jinja DELETED
@@ -1,154 +0,0 @@
1
- {%- set image_count = namespace(value=0) %}
2
- {%- set video_count = namespace(value=0) %}
3
- {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
- {%- if content is string %}
5
- {{- content }}
6
- {%- elif content is iterable and content is not mapping %}
7
- {%- for item in content %}
8
- {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
- {%- if is_system_content %}
10
- {{- raise_exception('System message cannot contain images.') }}
11
- {%- endif %}
12
- {%- if do_vision_count %}
13
- {%- set image_count.value = image_count.value + 1 %}
14
- {%- endif %}
15
- {%- if add_vision_id %}
16
- {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
- {%- endif %}
18
- {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
- {%- elif 'video' in item or item.type == 'video' %}
20
- {%- if is_system_content %}
21
- {{- raise_exception('System message cannot contain videos.') }}
22
- {%- endif %}
23
- {%- if do_vision_count %}
24
- {%- set video_count.value = video_count.value + 1 %}
25
- {%- endif %}
26
- {%- if add_vision_id %}
27
- {{- 'Video ' ~ video_count.value ~ ': ' }}
28
- {%- endif %}
29
- {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
- {%- elif 'text' in item %}
31
- {{- item.text }}
32
- {%- else %}
33
- {{- raise_exception('Unexpected item type in content.') }}
34
- {%- endif %}
35
- {%- endfor %}
36
- {%- elif content is none or content is undefined %}
37
- {{- '' }}
38
- {%- else %}
39
- {{- raise_exception('Unexpected content type.') }}
40
- {%- endif %}
41
- {%- endmacro %}
42
- {%- if not messages %}
43
- {{- raise_exception('No messages provided.') }}
44
- {%- endif %}
45
- {%- if tools and tools is iterable and tools is not mapping %}
46
- {{- '<|im_start|>system\n' }}
47
- {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
48
- {%- for tool in tools %}
49
- {{- "\n" }}
50
- {{- tool | tojson }}
51
- {%- endfor %}
52
- {{- "\n</tools>" }}
53
- {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
54
- {%- if messages[0].role == 'system' %}
55
- {%- set content = render_content(messages[0].content, false, true)|trim %}
56
- {%- if content %}
57
- {{- '\n\n' + content }}
58
- {%- endif %}
59
- {%- endif %}
60
- {{- '<|im_end|>\n' }}
61
- {%- else %}
62
- {%- if messages[0].role == 'system' %}
63
- {%- set content = render_content(messages[0].content, false, true)|trim %}
64
- {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
65
- {%- endif %}
66
- {%- endif %}
67
- {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
68
- {%- for message in messages[::-1] %}
69
- {%- set index = (messages|length - 1) - loop.index0 %}
70
- {%- if ns.multi_step_tool and message.role == "user" %}
71
- {%- set content = render_content(message.content, false)|trim %}
72
- {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
73
- {%- set ns.multi_step_tool = false %}
74
- {%- set ns.last_query_index = index %}
75
- {%- endif %}
76
- {%- endif %}
77
- {%- endfor %}
78
- {%- if ns.multi_step_tool %}
79
- {{- raise_exception('No user query found in messages.') }}
80
- {%- endif %}
81
- {%- for message in messages %}
82
- {%- set content = render_content(message.content, true)|trim %}
83
- {%- if message.role == "system" %}
84
- {%- if not loop.first %}
85
- {{- raise_exception('System message must be at the beginning.') }}
86
- {%- endif %}
87
- {%- elif message.role == "user" %}
88
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
89
- {%- elif message.role == "assistant" %}
90
- {%- set reasoning_content = '' %}
91
- {%- if message.reasoning_content is string %}
92
- {%- set reasoning_content = message.reasoning_content %}
93
- {%- else %}
94
- {%- if '</think>' in content %}
95
- {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
96
- {%- set content = content.split('</think>')[-1].lstrip('\n') %}
97
- {%- endif %}
98
- {%- endif %}
99
- {%- set reasoning_content = reasoning_content|trim %}
100
- {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
101
- {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
102
- {%- else %}
103
- {{- '<|im_start|>' + message.role + '\n' + content }}
104
- {%- endif %}
105
- {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
106
- {%- for tool_call in message.tool_calls %}
107
- {%- if tool_call.function is defined %}
108
- {%- set tool_call = tool_call.function %}
109
- {%- endif %}
110
- {%- if loop.first %}
111
- {%- if content|trim %}
112
- {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
113
- {%- else %}
114
- {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
115
- {%- endif %}
116
- {%- else %}
117
- {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
- {%- endif %}
119
- {%- if tool_call.arguments is defined %}
120
- {%- for args_name, args_value in tool_call.arguments|items %}
121
- {{- '<parameter=' + args_name + '>\n' }}
122
- {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
123
- {{- args_value }}
124
- {{- '\n</parameter>\n' }}
125
- {%- endfor %}
126
- {%- endif %}
127
- {{- '</function>\n</tool_call>' }}
128
- {%- endfor %}
129
- {%- endif %}
130
- {{- '<|im_end|>\n' }}
131
- {%- elif message.role == "tool" %}
132
- {%- if loop.previtem and loop.previtem.role != "tool" %}
133
- {{- '<|im_start|>user' }}
134
- {%- endif %}
135
- {{- '\n<tool_response>\n' }}
136
- {{- content }}
137
- {{- '\n</tool_response>' }}
138
- {%- if not loop.last and loop.nextitem.role != "tool" %}
139
- {{- '<|im_end|>\n' }}
140
- {%- elif loop.last %}
141
- {{- '<|im_end|>\n' }}
142
- {%- endif %}
143
- {%- else %}
144
- {{- raise_exception('Unexpected message role.') }}
145
- {%- endif %}
146
- {%- endfor %}
147
- {%- if add_generation_prompt %}
148
- {{- '<|im_start|>assistant\n' }}
149
- {%- if enable_thinking is defined and enable_thinking is false %}
150
- {{- '<think>\n\n</think>\n\n' }}
151
- {%- else %}
152
- {{- '<think>\n' }}
153
- {%- endif %}
154
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
evidence_adapter/tokenizer/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea2e66b594a0906e9a547c9e6ff9e5fb8a8198439c8cf7d6dc48f23529161223
3
- size 19989442
 
 
 
 
evidence_adapter/tokenizer/tokenizer_config.json DELETED
@@ -1,31 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "audio_bos_token": "<|audio_start|>",
4
- "audio_eos_token": "<|audio_end|>",
5
- "audio_token": "<|audio_pad|>",
6
- "backend": "tokenizers",
7
- "bos_token": null,
8
- "clean_up_tokenization_spaces": false,
9
- "eos_token": "<|im_end|>",
10
- "errors": "replace",
11
- "image_token": "<|image_pad|>",
12
- "is_local": true,
13
- "model_max_length": 262144,
14
- "model_specific_special_tokens": {
15
- "audio_bos_token": "<|audio_start|>",
16
- "audio_eos_token": "<|audio_end|>",
17
- "audio_token": "<|audio_pad|>",
18
- "image_token": "<|image_pad|>",
19
- "video_token": "<|video_pad|>",
20
- "vision_bos_token": "<|vision_start|>",
21
- "vision_eos_token": "<|vision_end|>"
22
- },
23
- "pad_token": "<|endoftext|>",
24
- "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
25
- "split_special_tokens": false,
26
- "tokenizer_class": "TokenizersBackend",
27
- "unk_token": null,
28
- "video_token": "<|video_pad|>",
29
- "vision_bos_token": "<|vision_start|>",
30
- "vision_eos_token": "<|vision_end|>"
31
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
generation_config.json DELETED
@@ -1,12 +0,0 @@
1
- {
2
- "bos_token_id": 248044,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 248046,
6
- 248044
7
- ],
8
- "pad_token_id": 248044,
9
- "temperature": 1.0,
10
- "top_k": 20,
11
- "top_p": 0.95
12
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
model.safetensors.index.json DELETED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json DELETED
@@ -1,21 +0,0 @@
1
- {
2
- "size": {
3
- "longest_edge": 16777216,
4
- "shortest_edge": 65536
5
- },
6
- "patch_size": 16,
7
- "temporal_patch_size": 2,
8
- "merge_size": 2,
9
- "image_mean": [
10
- 0.5,
11
- 0.5,
12
- 0.5
13
- ],
14
- "image_std": [
15
- 0.5,
16
- 0.5,
17
- 0.5
18
- ],
19
- "processor_class": "Qwen3VLProcessor",
20
- "image_processor_type": "Qwen2VLImageProcessorFast"
21
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
rollback_adapter/.gitkeep DELETED
File without changes
rollback_adapter/adapter/README.md DELETED
@@ -1,203 +0,0 @@
1
- ---
2
- library_name: peft
3
- tags:
4
- - lora
5
- ---
6
-
7
- # Model Card for Model ID
8
-
9
- <!-- Provide a quick summary of what the model is/does. -->
10
-
11
-
12
-
13
- ## Model Details
14
-
15
- ### Model Description
16
-
17
- <!-- Provide a longer summary of what this model is. -->
18
-
19
-
20
-
21
- - **Developed by:** [More Information Needed]
22
- - **Funded by [optional]:** [More Information Needed]
23
- - **Shared by [optional]:** [More Information Needed]
24
- - **Model type:** [More Information Needed]
25
- - **Language(s) (NLP):** [More Information Needed]
26
- - **License:** [More Information Needed]
27
- - **Finetuned from model [optional]:** [More Information Needed]
28
-
29
- ### Model Sources [optional]
30
-
31
- <!-- Provide the basic links for the model. -->
32
-
33
- - **Repository:** [More Information Needed]
34
- - **Paper [optional]:** [More Information Needed]
35
- - **Demo [optional]:** [More Information Needed]
36
-
37
- ## Uses
38
-
39
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
40
-
41
- ### Direct Use
42
-
43
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
44
-
45
- [More Information Needed]
46
-
47
- ### Downstream Use [optional]
48
-
49
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
50
-
51
- [More Information Needed]
52
-
53
- ### Out-of-Scope Use
54
-
55
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
56
-
57
- [More Information Needed]
58
-
59
- ## Bias, Risks, and Limitations
60
-
61
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
62
-
63
- [More Information Needed]
64
-
65
- ### Recommendations
66
-
67
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
68
-
69
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
70
-
71
- ## How to Get Started with the Model
72
-
73
- Use the code below to get started with the model.
74
-
75
- [More Information Needed]
76
-
77
- ## Training Details
78
-
79
- ### Training Data
80
-
81
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
82
-
83
- [More Information Needed]
84
-
85
- ### Training Procedure
86
-
87
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
88
-
89
- #### Preprocessing [optional]
90
-
91
- [More Information Needed]
92
-
93
-
94
- #### Training Hyperparameters
95
-
96
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
97
-
98
- #### Speeds, Sizes, Times [optional]
99
-
100
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
101
-
102
- [More Information Needed]
103
-
104
- ## Evaluation
105
-
106
- <!-- This section describes the evaluation protocols and provides the results. -->
107
-
108
- ### Testing Data, Factors & Metrics
109
-
110
- #### Testing Data
111
-
112
- <!-- This should link to a Dataset Card if possible. -->
113
-
114
- [More Information Needed]
115
-
116
- #### Factors
117
-
118
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
119
-
120
- [More Information Needed]
121
-
122
- #### Metrics
123
-
124
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
125
-
126
- [More Information Needed]
127
-
128
- ### Results
129
-
130
- [More Information Needed]
131
-
132
- #### Summary
133
-
134
-
135
-
136
- ## Model Examination [optional]
137
-
138
- <!-- Relevant interpretability work for the model goes here -->
139
-
140
- [More Information Needed]
141
-
142
- ## Environmental Impact
143
-
144
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
145
-
146
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
147
-
148
- - **Hardware Type:** [More Information Needed]
149
- - **Hours used:** [More Information Needed]
150
- - **Cloud Provider:** [More Information Needed]
151
- - **Compute Region:** [More Information Needed]
152
- - **Carbon Emitted:** [More Information Needed]
153
-
154
- ## Technical Specifications [optional]
155
-
156
- ### Model Architecture and Objective
157
-
158
- [More Information Needed]
159
-
160
- ### Compute Infrastructure
161
-
162
- [More Information Needed]
163
-
164
- #### Hardware
165
-
166
- [More Information Needed]
167
-
168
- #### Software
169
-
170
- [More Information Needed]
171
-
172
- ## Citation [optional]
173
-
174
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
175
-
176
- **BibTeX:**
177
-
178
- [More Information Needed]
179
-
180
- **APA:**
181
-
182
- [More Information Needed]
183
-
184
- ## Glossary [optional]
185
-
186
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
187
-
188
- [More Information Needed]
189
-
190
- ## More Information [optional]
191
-
192
- [More Information Needed]
193
-
194
- ## Model Card Authors [optional]
195
-
196
- [More Information Needed]
197
-
198
- ## Model Card Contact
199
-
200
- [More Information Needed]
201
- ### Framework versions
202
-
203
- - PEFT 0.19.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
rollback_adapter/adapter/adapter_config.json DELETED
@@ -1,57 +0,0 @@
1
- {
2
- "alora_invocation_tokens": null,
3
- "alpha_pattern": {},
4
- "arrow_config": null,
5
- "auto_mapping": null,
6
- "base_model_name_or_path": null,
7
- "bias": "none",
8
- "corda_config": null,
9
- "ensure_weight_tying": false,
10
- "eva_config": null,
11
- "exclude_modules": null,
12
- "fan_in_fan_out": false,
13
- "inference_mode": true,
14
- "init_lora_weights": true,
15
- "layer_replication": null,
16
- "layers_pattern": null,
17
- "layers_to_transform": null,
18
- "loftq_config": {},
19
- "lora_alpha": 16,
20
- "lora_bias": false,
21
- "lora_dropout": 0.05,
22
- "lora_ga_config": null,
23
- "megatron_config": null,
24
- "megatron_core": "megatron.core",
25
- "modules_to_save": null,
26
- "peft_type": "LORA",
27
- "peft_version": "0.19.0",
28
- "qalora_group_size": 16,
29
- "r": 8,
30
- "rank_pattern": {},
31
- "revision": null,
32
- "target_modules": [
33
- "surface_host.rollback_adapter.head",
34
- "surface_host.toolspec_head.receipt_formatter",
35
- "surface_host.runtime_harness_adapter.bridge",
36
- "surface_host.toolspec_bridge.adapter",
37
- "surface_host.failure_signal_bridge.rollback_bridge",
38
- "surface_host.sandbox_rollback_bridge.adapter",
39
- "surface_host.validator_feedback_bridge.adapter",
40
- "surface_host.validator_feedback_loop.rollback_adapter",
41
- "surface_host.request_normalizer.adapter",
42
- "surface_host.tool_protocol_adapter.bridge",
43
- "surface_host.toolspec_head.precondition_adapter",
44
- "surface_host.memory_boundary_guard.adapter",
45
- "surface_host.toolspec_head.postcondition_adapter",
46
- "surface_host.memory_boundary_guard.rollback_filter",
47
- "surface_host.toolspec_head.validator_gate",
48
- "surface_host.toolspec_head.trigger_gate"
49
- ],
50
- "target_parameters": null,
51
- "task_type": "FEATURE_EXTRACTION",
52
- "trainable_token_indices": null,
53
- "use_bdlora": null,
54
- "use_dora": false,
55
- "use_qalora": false,
56
- "use_rslora": false
57
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
rollback_adapter/adapter/adapter_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:74ca61f2f73640249123de75d35d15493a95e1a70c8ed37db4b0cacf668046b7
3
- size 1053176
 
 
 
 
rollback_adapter/best_checkpoint_manifest.json DELETED
@@ -1,28 +0,0 @@
1
- {
2
- "best_epoch": 3,
3
- "best_quality_score": 0.3986773560841878,
4
- "eval_metrics": {
5
- "avg_binary_accuracy": 0.8194444444444444,
6
- "cause_accuracy": 0.4888888888888889,
7
- "count": 45,
8
- "eval_batches": 45,
9
- "eval_loss": 7.656409973568387,
10
- "fail_closed_accuracy": 0.7777777777777778,
11
- "minimal_diff_accuracy": 0.5555555555555556,
12
- "mode_accuracy": 0.3333333333333333,
13
- "need_accuracy": 0.7777777777777778,
14
- "preserve_conflict_accuracy": 0.7777777777777778,
15
- "quality_score": 0.3986773560841878,
16
- "reverse_engineering_bounded_accuracy": 0.8888888888888888,
17
- "rewrite_accuracy": 0.4888888888888889,
18
- "selfcheck_route_accuracy": 0.5555555555555556,
19
- "session_continuity_accuracy": 1.0,
20
- "validator_aligned_accuracy": 1.0,
21
- "worktree_safe_accuracy": 1.0
22
- },
23
- "train_metrics": {
24
- "loss": 0.4452953128114579,
25
- "micro_batches": 126,
26
- "optimizer_steps": 8
27
- }
28
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
rollback_adapter/epoch_history.json DELETED
@@ -1,120 +0,0 @@
1
- {
2
- "epochs": [
3
- {
4
- "epoch": 1,
5
- "eval_metrics": {
6
- "avg_binary_accuracy": 0.8194444444444444,
7
- "cause_accuracy": 0.4444444444444444,
8
- "count": 45,
9
- "eval_batches": 45,
10
- "eval_loss": 8.320836893717448,
11
- "fail_closed_accuracy": 0.7777777777777778,
12
- "minimal_diff_accuracy": 0.5555555555555556,
13
- "mode_accuracy": 0.26666666666666666,
14
- "need_accuracy": 0.7777777777777778,
15
- "preserve_conflict_accuracy": 0.7777777777777778,
16
- "quality_score": 0.30316659545898433,
17
- "reverse_engineering_bounded_accuracy": 0.8888888888888888,
18
- "rewrite_accuracy": 0.28888888888888886,
19
- "selfcheck_route_accuracy": 0.5555555555555556,
20
- "session_continuity_accuracy": 1.0,
21
- "validator_aligned_accuracy": 1.0,
22
- "worktree_safe_accuracy": 1.0
23
- },
24
- "improved": true,
25
- "quality_score": 0.30316659545898433,
26
- "train_metrics": {
27
- "loss": 0.5652040739854177,
28
- "micro_batches": 126,
29
- "optimizer_steps": 8
30
- }
31
- },
32
- {
33
- "epoch": 2,
34
- "eval_metrics": {
35
- "avg_binary_accuracy": 0.8194444444444444,
36
- "cause_accuracy": 0.3333333333333333,
37
- "count": 45,
38
- "eval_batches": 45,
39
- "eval_loss": 7.85913037194146,
40
- "fail_closed_accuracy": 0.7777777777777778,
41
- "minimal_diff_accuracy": 0.5555555555555556,
42
- "mode_accuracy": 0.4,
43
- "need_accuracy": 0.7777777777777778,
44
- "preserve_conflict_accuracy": 0.7777777777777778,
45
- "quality_score": 0.28684517033894863,
46
- "reverse_engineering_bounded_accuracy": 0.8888888888888888,
47
- "rewrite_accuracy": 0.28888888888888886,
48
- "selfcheck_route_accuracy": 0.5555555555555556,
49
- "session_continuity_accuracy": 1.0,
50
- "validator_aligned_accuracy": 1.0,
51
- "worktree_safe_accuracy": 1.0
52
- },
53
- "improved": false,
54
- "quality_score": 0.28684517033894863,
55
- "train_metrics": {
56
- "loss": 0.4876745880123169,
57
- "micro_batches": 126,
58
- "optimizer_steps": 8
59
- }
60
- },
61
- {
62
- "epoch": 3,
63
- "eval_metrics": {
64
- "avg_binary_accuracy": 0.8194444444444444,
65
- "cause_accuracy": 0.4888888888888889,
66
- "count": 45,
67
- "eval_batches": 45,
68
- "eval_loss": 7.656409973568387,
69
- "fail_closed_accuracy": 0.7777777777777778,
70
- "minimal_diff_accuracy": 0.5555555555555556,
71
- "mode_accuracy": 0.3333333333333333,
72
- "need_accuracy": 0.7777777777777778,
73
- "preserve_conflict_accuracy": 0.7777777777777778,
74
- "quality_score": 0.3986773560841878,
75
- "reverse_engineering_bounded_accuracy": 0.8888888888888888,
76
- "rewrite_accuracy": 0.4888888888888889,
77
- "selfcheck_route_accuracy": 0.5555555555555556,
78
- "session_continuity_accuracy": 1.0,
79
- "validator_aligned_accuracy": 1.0,
80
- "worktree_safe_accuracy": 1.0
81
- },
82
- "improved": true,
83
- "quality_score": 0.3986773560841878,
84
- "train_metrics": {
85
- "loss": 0.4452953128114579,
86
- "micro_batches": 126,
87
- "optimizer_steps": 8
88
- }
89
- },
90
- {
91
- "epoch": 4,
92
- "eval_metrics": {
93
- "avg_binary_accuracy": 0.8194444444444444,
94
- "cause_accuracy": 0.4888888888888889,
95
- "count": 45,
96
- "eval_batches": 45,
97
- "eval_loss": 7.64718263414171,
98
- "fail_closed_accuracy": 0.7777777777777778,
99
- "minimal_diff_accuracy": 0.5555555555555556,
100
- "mode_accuracy": 0.3333333333333333,
101
- "need_accuracy": 0.7777777777777778,
102
- "preserve_conflict_accuracy": 0.7777777777777778,
103
- "quality_score": 0.3988619028727214,
104
- "reverse_engineering_bounded_accuracy": 0.8888888888888888,
105
- "rewrite_accuracy": 0.4888888888888889,
106
- "selfcheck_route_accuracy": 0.5555555555555556,
107
- "session_continuity_accuracy": 1.0,
108
- "validator_aligned_accuracy": 1.0,
109
- "worktree_safe_accuracy": 1.0
110
- },
111
- "improved": false,
112
- "quality_score": 0.3988619028727214,
113
- "train_metrics": {
114
- "loss": 0.4358076933357451,
115
- "micro_batches": 126,
116
- "optimizer_steps": 8
117
- }
118
- }
119
- ]
120
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
rollback_adapter/host_manifest.json DELETED
@@ -1,288 +0,0 @@
1
- {
2
- "hidden_size": 2048,
3
- "host_config": {
4
- "attn_implementation": null,
5
- "backbone_name_or_path": "/public/wang_libo/veriloop_coder_e1/model",
6
- "device_map": null,
7
- "dtype": null,
8
- "evidence_rank_hint": 8,
9
- "expose_backbone_inventory": false,
10
- "freeze_backbone": true,
11
- "hidden_size_override": 2048,
12
- "host_dropout": 0.0,
13
- "identity_rank_hint": 8,
14
- "load_backbone_weights": false,
15
- "local_files_only": true,
16
- "low_cpu_mem_usage": true,
17
- "memory_rank_hint": 4,
18
- "rollback_rank_hint": 8,
19
- "runtime_rank_hint": 8,
20
- "toolspec_rank_hint": 8,
21
- "trust_remote_code": true,
22
- "uncertainty_rank_hint": 8,
23
- "use_safetensors": null,
24
- "validator_rank_hint": 8
25
- },
26
- "load_result": {
27
- "has_base_config": true,
28
- "has_base_model": true,
29
- "hidden_size": 2048,
30
- "notes": [
31
- "class=AutoModelForCausalLM",
32
- "quant=4bit"
33
- ],
34
- "source": "trainer_qwen36_loader"
35
- },
36
- "peft_named_modules": [
37
- "claim_extractor",
38
- "claim_extractor.adapter",
39
- "dropout",
40
- "episodic_memory",
41
- "episodic_memory.adapter",
42
- "evidence_binding",
43
- "evidence_binding.adapter",
44
- "failure_signal_bridge",
45
- "failure_signal_bridge.rollback_bridge",
46
- "failure_signal_bridge.rollback_bridge.base_layer",
47
- "failure_signal_bridge.rollback_bridge.lora_A",
48
- "failure_signal_bridge.rollback_bridge.lora_A.default",
49
- "failure_signal_bridge.rollback_bridge.lora_B",
50
- "failure_signal_bridge.rollback_bridge.lora_B.default",
51
- "failure_signal_bridge.rollback_bridge.lora_dropout",
52
- "failure_signal_bridge.rollback_bridge.lora_dropout.default",
53
- "failure_signal_bridge.rollback_bridge.lora_embedding_A",
54
- "failure_signal_bridge.rollback_bridge.lora_embedding_B",
55
- "failure_signal_bridge.rollback_bridge.lora_magnitude_vector",
56
- "identity_adapter",
57
- "identity_adapter.bridge",
58
- "identity_guard",
59
- "identity_guard.adapter",
60
- "input_norm",
61
- "memory_boundary_guard",
62
- "memory_boundary_guard.adapter",
63
- "memory_boundary_guard.adapter.base_layer",
64
- "memory_boundary_guard.adapter.lora_A",
65
- "memory_boundary_guard.adapter.lora_A.default",
66
- "memory_boundary_guard.adapter.lora_B",
67
- "memory_boundary_guard.adapter.lora_B.default",
68
- "memory_boundary_guard.adapter.lora_dropout",
69
- "memory_boundary_guard.adapter.lora_dropout.default",
70
- "memory_boundary_guard.adapter.lora_embedding_A",
71
- "memory_boundary_guard.adapter.lora_embedding_B",
72
- "memory_boundary_guard.adapter.lora_magnitude_vector",
73
- "memory_boundary_guard.rollback_filter",
74
- "memory_boundary_guard.rollback_filter.base_layer",
75
- "memory_boundary_guard.rollback_filter.lora_A",
76
- "memory_boundary_guard.rollback_filter.lora_A.default",
77
- "memory_boundary_guard.rollback_filter.lora_B",
78
- "memory_boundary_guard.rollback_filter.lora_B.default",
79
- "memory_boundary_guard.rollback_filter.lora_dropout",
80
- "memory_boundary_guard.rollback_filter.lora_dropout.default",
81
- "memory_boundary_guard.rollback_filter.lora_embedding_A",
82
- "memory_boundary_guard.rollback_filter.lora_embedding_B",
83
- "memory_boundary_guard.rollback_filter.lora_magnitude_vector",
84
- "patch_binding",
85
- "patch_binding.adapter",
86
- "permission_context_manager",
87
- "permission_context_manager.adapter",
88
- "progress_state_tracker",
89
- "progress_state_tracker.adapter",
90
- "progress_state_tracker.rollback_memory",
91
- "proof_carrying_hints",
92
- "proof_carrying_hints.bridge",
93
- "provenance_binding",
94
- "provenance_binding.adapter",
95
- "public_identity_head",
96
- "public_identity_head.proj",
97
- "query_runtime_engine",
98
- "query_runtime_engine.adapter",
99
- "request_normalizer",
100
- "request_normalizer.adapter",
101
- "request_normalizer.adapter.base_layer",
102
- "request_normalizer.adapter.lora_A",
103
- "request_normalizer.adapter.lora_A.default",
104
- "request_normalizer.adapter.lora_B",
105
- "request_normalizer.adapter.lora_B.default",
106
- "request_normalizer.adapter.lora_dropout",
107
- "request_normalizer.adapter.lora_dropout.default",
108
- "request_normalizer.adapter.lora_embedding_A",
109
- "request_normalizer.adapter.lora_embedding_B",
110
- "request_normalizer.adapter.lora_magnitude_vector",
111
- "rollback_adapter",
112
- "rollback_adapter.head",
113
- "rollback_adapter.head.base_layer",
114
- "rollback_adapter.head.lora_A",
115
- "rollback_adapter.head.lora_A.default",
116
- "rollback_adapter.head.lora_B",
117
- "rollback_adapter.head.lora_B.default",
118
- "rollback_adapter.head.lora_dropout",
119
- "rollback_adapter.head.lora_dropout.default",
120
- "rollback_adapter.head.lora_embedding_A",
121
- "rollback_adapter.head.lora_embedding_B",
122
- "rollback_adapter.head.lora_magnitude_vector",
123
- "rollback_engine",
124
- "rollback_engine.adapter",
125
- "runtime_binding",
126
- "runtime_binding.adapter",
127
- "runtime_harness_adapter",
128
- "runtime_harness_adapter.bridge",
129
- "runtime_harness_adapter.bridge.base_layer",
130
- "runtime_harness_adapter.bridge.lora_A",
131
- "runtime_harness_adapter.bridge.lora_A.default",
132
- "runtime_harness_adapter.bridge.lora_B",
133
- "runtime_harness_adapter.bridge.lora_B.default",
134
- "runtime_harness_adapter.bridge.lora_dropout",
135
- "runtime_harness_adapter.bridge.lora_dropout.default",
136
- "runtime_harness_adapter.bridge.lora_embedding_A",
137
- "runtime_harness_adapter.bridge.lora_embedding_B",
138
- "runtime_harness_adapter.bridge.lora_magnitude_vector",
139
- "runtime_harness_uncertainty_bridge",
140
- "runtime_harness_uncertainty_bridge.adapter",
141
- "sandbox_rollback_bridge",
142
- "sandbox_rollback_bridge.adapter",
143
- "sandbox_rollback_bridge.adapter.base_layer",
144
- "sandbox_rollback_bridge.adapter.lora_A",
145
- "sandbox_rollback_bridge.adapter.lora_A.default",
146
- "sandbox_rollback_bridge.adapter.lora_B",
147
- "sandbox_rollback_bridge.adapter.lora_B.default",
148
- "sandbox_rollback_bridge.adapter.lora_dropout",
149
- "sandbox_rollback_bridge.adapter.lora_dropout.default",
150
- "sandbox_rollback_bridge.adapter.lora_embedding_A",
151
- "sandbox_rollback_bridge.adapter.lora_embedding_B",
152
- "sandbox_rollback_bridge.adapter.lora_magnitude_vector",
153
- "session_compactor",
154
- "session_compactor.adapter",
155
- "session_state_manager",
156
- "session_state_manager.adapter",
157
- "session_state_manager.rollback_state",
158
- "tool_protocol_adapter",
159
- "tool_protocol_adapter.bridge",
160
- "tool_protocol_adapter.bridge.base_layer",
161
- "tool_protocol_adapter.bridge.lora_A",
162
- "tool_protocol_adapter.bridge.lora_A.default",
163
- "tool_protocol_adapter.bridge.lora_B",
164
- "tool_protocol_adapter.bridge.lora_B.default",
165
- "tool_protocol_adapter.bridge.lora_dropout",
166
- "tool_protocol_adapter.bridge.lora_dropout.default",
167
- "tool_protocol_adapter.bridge.lora_embedding_A",
168
- "tool_protocol_adapter.bridge.lora_embedding_B",
169
- "tool_protocol_adapter.bridge.lora_magnitude_vector",
170
- "toolspec_bridge",
171
- "toolspec_bridge.adapter",
172
- "toolspec_bridge.adapter.base_layer",
173
- "toolspec_bridge.adapter.lora_A",
174
- "toolspec_bridge.adapter.lora_A.default",
175
- "toolspec_bridge.adapter.lora_B",
176
- "toolspec_bridge.adapter.lora_B.default",
177
- "toolspec_bridge.adapter.lora_dropout",
178
- "toolspec_bridge.adapter.lora_dropout.default",
179
- "toolspec_bridge.adapter.lora_embedding_A",
180
- "toolspec_bridge.adapter.lora_embedding_B",
181
- "toolspec_bridge.adapter.lora_magnitude_vector",
182
- "toolspec_head",
183
- "toolspec_head.param_schema_adapter",
184
- "toolspec_head.postcondition_adapter",
185
- "toolspec_head.postcondition_adapter.base_layer",
186
- "toolspec_head.postcondition_adapter.lora_A",
187
- "toolspec_head.postcondition_adapter.lora_A.default",
188
- "toolspec_head.postcondition_adapter.lora_B",
189
- "toolspec_head.postcondition_adapter.lora_B.default",
190
- "toolspec_head.postcondition_adapter.lora_dropout",
191
- "toolspec_head.postcondition_adapter.lora_dropout.default",
192
- "toolspec_head.postcondition_adapter.lora_embedding_A",
193
- "toolspec_head.postcondition_adapter.lora_embedding_B",
194
- "toolspec_head.postcondition_adapter.lora_magnitude_vector",
195
- "toolspec_head.precondition_adapter",
196
- "toolspec_head.precondition_adapter.base_layer",
197
- "toolspec_head.precondition_adapter.lora_A",
198
- "toolspec_head.precondition_adapter.lora_A.default",
199
- "toolspec_head.precondition_adapter.lora_B",
200
- "toolspec_head.precondition_adapter.lora_B.default",
201
- "toolspec_head.precondition_adapter.lora_dropout",
202
- "toolspec_head.precondition_adapter.lora_dropout.default",
203
- "toolspec_head.precondition_adapter.lora_embedding_A",
204
- "toolspec_head.precondition_adapter.lora_embedding_B",
205
- "toolspec_head.precondition_adapter.lora_magnitude_vector",
206
- "toolspec_head.receipt_formatter",
207
- "toolspec_head.receipt_formatter.base_layer",
208
- "toolspec_head.receipt_formatter.lora_A",
209
- "toolspec_head.receipt_formatter.lora_A.default",
210
- "toolspec_head.receipt_formatter.lora_B",
211
- "toolspec_head.receipt_formatter.lora_B.default",
212
- "toolspec_head.receipt_formatter.lora_dropout",
213
- "toolspec_head.receipt_formatter.lora_dropout.default",
214
- "toolspec_head.receipt_formatter.lora_embedding_A",
215
- "toolspec_head.receipt_formatter.lora_embedding_B",
216
- "toolspec_head.receipt_formatter.lora_magnitude_vector",
217
- "toolspec_head.trigger_gate",
218
- "toolspec_head.trigger_gate.base_layer",
219
- "toolspec_head.trigger_gate.lora_A",
220
- "toolspec_head.trigger_gate.lora_A.default",
221
- "toolspec_head.trigger_gate.lora_B",
222
- "toolspec_head.trigger_gate.lora_B.default",
223
- "toolspec_head.trigger_gate.lora_dropout",
224
- "toolspec_head.trigger_gate.lora_dropout.default",
225
- "toolspec_head.trigger_gate.lora_embedding_A",
226
- "toolspec_head.trigger_gate.lora_embedding_B",
227
- "toolspec_head.trigger_gate.lora_magnitude_vector",
228
- "toolspec_head.validator_gate",
229
- "toolspec_head.validator_gate.base_layer",
230
- "toolspec_head.validator_gate.lora_A",
231
- "toolspec_head.validator_gate.lora_A.default",
232
- "toolspec_head.validator_gate.lora_B",
233
- "toolspec_head.validator_gate.lora_B.default",
234
- "toolspec_head.validator_gate.lora_dropout",
235
- "toolspec_head.validator_gate.lora_dropout.default",
236
- "toolspec_head.validator_gate.lora_embedding_A",
237
- "toolspec_head.validator_gate.lora_embedding_B",
238
- "toolspec_head.validator_gate.lora_magnitude_vector",
239
- "uncertainty_head",
240
- "uncertainty_head.calibration_mlp",
241
- "uncertainty_head.proj",
242
- "validator_feedback_bridge",
243
- "validator_feedback_bridge.adapter",
244
- "validator_feedback_bridge.adapter.base_layer",
245
- "validator_feedback_bridge.adapter.lora_A",
246
- "validator_feedback_bridge.adapter.lora_A.default",
247
- "validator_feedback_bridge.adapter.lora_B",
248
- "validator_feedback_bridge.adapter.lora_B.default",
249
- "validator_feedback_bridge.adapter.lora_dropout",
250
- "validator_feedback_bridge.adapter.lora_dropout.default",
251
- "validator_feedback_bridge.adapter.lora_embedding_A",
252
- "validator_feedback_bridge.adapter.lora_embedding_B",
253
- "validator_feedback_bridge.adapter.lora_magnitude_vector",
254
- "validator_feedback_loop",
255
- "validator_feedback_loop.rollback_adapter",
256
- "validator_feedback_loop.rollback_adapter.base_layer",
257
- "validator_feedback_loop.rollback_adapter.lora_A",
258
- "validator_feedback_loop.rollback_adapter.lora_A.default",
259
- "validator_feedback_loop.rollback_adapter.lora_B",
260
- "validator_feedback_loop.rollback_adapter.lora_B.default",
261
- "validator_feedback_loop.rollback_adapter.lora_dropout",
262
- "validator_feedback_loop.rollback_adapter.lora_dropout.default",
263
- "validator_feedback_loop.rollback_adapter.lora_embedding_A",
264
- "validator_feedback_loop.rollback_adapter.lora_embedding_B",
265
- "validator_feedback_loop.rollback_adapter.lora_magnitude_vector",
266
- "validator_receipt_bridge",
267
- "validator_receipt_bridge.adapter",
268
- "validator_uncertainty_bridge",
269
- "validator_uncertainty_bridge.adapter",
270
- "workspace_snapshot_manager",
271
- "workspace_snapshot_manager.rollback_context",
272
- "worktree_binding",
273
- "worktree_binding.adapter",
274
- "worktree_manager",
275
- "worktree_manager.adapter"
276
- ],
277
- "trainable_parameter_report": {
278
- "backbone_frozen": true,
279
- "backbone_present": true,
280
- "hidden_size": 2048,
281
- "host_parameters": 176785413,
282
- "host_trainable_parameters": 524288,
283
- "total_parameters": 34132843141,
284
- "trainable_parameters": 524288,
285
- "version": "veriloop.coder_peft_host.v1"
286
- },
287
- "version": "veriloop.coder_peft_host.v1"
288
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
rollback_adapter/rollback_adapter_plan.json DELETED
@@ -1,251 +0,0 @@
1
- {
2
- "backbone": "/public/wang_libo/veriloop_coder_e1/model",
3
- "dataset_summary": {
4
- "cause_vocab": [
5
- "none",
6
- "evidence_contradiction",
7
- "execution_negation",
8
- "validator_rejection",
9
- "patch_regression",
10
- "worktree_conflict",
11
- "high_risk_unsupported",
12
- "tool_selfcheck_failure",
13
- "reverse_engineering_speculation"
14
- ],
15
- "eval_size": 45,
16
- "mode_vocab": [
17
- "contradiction",
18
- "execution_failure",
19
- "validator_rejection",
20
- "patch_regression",
21
- "worktree_conflict",
22
- "high_risk_unsupported",
23
- "tool_selfcheck_repair",
24
- "reverse_engineering_drift",
25
- "validated_stable"
26
- ],
27
- "modes": [
28
- "contradiction",
29
- "execution_failure",
30
- "high_risk_unsupported",
31
- "patch_regression",
32
- "reverse_engineering_drift",
33
- "tool_selfcheck_repair",
34
- "validated_stable",
35
- "validator_rejection",
36
- "worktree_conflict"
37
- ],
38
- "need_vocab": [
39
- "none",
40
- "advisory",
41
- "required"
42
- ],
43
- "rewrite_vocab": [
44
- "do_not_rollback",
45
- "local_patch_only",
46
- "validator_scoped_revision",
47
- "minimum_diff_patch",
48
- "do_not_overwrite_worktree_state",
49
- "fail_closed",
50
- "repair_via_bounded_selfcheck_loop",
51
- "bounded_observation_first",
52
- "local_conflict_preserving_revision"
53
- ],
54
- "train_size": 126
55
- },
56
- "excluded_surfaces": [
57
- "(^|\\.)lm_head($|\\.)::Do not retune final token head; too broad and evaluation-heavy.",
58
- "(^|\\.)embed_tokens($|\\.)::Embedding surgery risks broad semantic drift.",
59
- "(^|\\.)norm($|\\.)::Global norm tuning can destabilize calibration across scenes.",
60
- "attnres|attention_residual::Block AttnRes may be mounted structurally but is never a PEFT target.",
61
- "dualpath::DualPath is serving/runtime infrastructure only.",
62
- "mhc|hyper[-_]?connection::mHC-inspired stability hooks remain structural, not PEFT surfaces.",
63
- "rope|rotary::RoPE/context surgery is handled architecturally, not by narrow PEFT here.",
64
- "kvcache|kv_cache::KV-cache runtime surfaces are not PEFT targets.",
65
- "(^|\\.)memory(_store|_bank)?($|\\.)::Persistent memory stores are harness/runtime policy surfaces, not PEFT targets."
66
- ],
67
- "notes": [
68
- "Primary route is host-surface-first rollback training.",
69
- "Validator receipts, failure routing, patch state, worktree continuity, self-check repair, and reverse-engineering boundedness are first-class signals.",
70
- "DualPath, Block AttnRes, mHC hooks, and MoE routers/experts remain structurally excluded.",
71
- "This adapter should improve rollback obedience, not general coding free-formity."
72
- ],
73
- "peft_method": "lora_narrow",
74
- "product_line": "veriloop_coder",
75
- "recipe": {
76
- "adapter_family": "validator_rollback",
77
- "backbone": "/public/wang_libo/veriloop_coder_e1/model",
78
- "backbone_family": "qwen_dense",
79
- "excluded_patterns": [
80
- "(?i)\\bdualpath\\b",
81
- "(?i)\\bmhc\\b",
82
- "(?i)\\bfull[_\\- ]?attnres\\b",
83
- "(?i)\\battnres(_full)?\\b",
84
- "(?i)\\brouter\\b",
85
- "(?i)\\bexperts?\\b",
86
- "(?i)\\bmoe\\b.*\\b(gate|router|expert)\\b",
87
- "(?i)\\brope\\b.*\\b(freq|inv_freq|theta|rotary)\\b",
88
- "(?i)\\bkvcache\\b",
89
- "(?i)\\bposition_embedding\\b",
90
- "(?i)\\bembed(tokens|ding)?\\b",
91
- "(?i)\\blm_head\\b"
92
- ],
93
- "harness_constraints": [
94
- "Harness Engineering remains the primary convergence layer.",
95
- "Adapter must not bypass runtime orchestrator / validator / rollback loops.",
96
- "Adapter outputs remain subordinate to VeriLoop control-plane decisions.",
97
- "Adapter must not create hidden prompt-style memory authority.",
98
- "Adapter must preserve validator-first correction and minimal-diff rollback discipline.",
99
- "Patch production must remain subordinate to validator receipts and failure routing."
100
- ],
101
- "hyperparams": {
102
- "alpha": 16,
103
- "bias": "none",
104
- "dropout": 0.08,
105
- "fan_in_fan_out": false,
106
- "modules_to_save": [
107
- "input_layernorm"
108
- ],
109
- "r": 8,
110
- "task_type": "CAUSAL_LM"
111
- },
112
- "merge_policy": "side_load",
113
- "metadata": {
114
- "allow_backbone_bridge": false,
115
- "allow_vla_action_expert": false,
116
- "harness_first": true,
117
- "prefer_explicit_heads": true,
118
- "prefer_qlora_for_backbone_bridge": false,
119
- "require_harness_first": true,
120
- "reverse_engineering_readiness": true,
121
- "rollback_training": true,
122
- "selector_group_count": 2,
123
- "selfcheck_loop_readiness": true,
124
- "strict_narrow_scope": true,
125
- "trainer": "veriloop.rollback_adapter_trainer.v9.qwen36"
126
- },
127
- "notes": [
128
- "Backbone bridge tuning disabled explicitly; selector stays on custom surfaces or no-op.",
129
- "Backbone family inferred as qwen_dense.",
130
- "PEFT method resolved as lora_narrow.",
131
- "Recipe is harness-first: runtime convergence remains in VeriLoop control-plane + harness, not in broad weight surgery.",
132
- "Block AttnRes, DualPath, mHC hooks, RoPE, KV-cache, and broad MoE routing remain structurally excluded."
133
- ],
134
- "peft_method": "lora_narrow",
135
- "precision_policy": "auto",
136
- "product_line": "veriloop_coder",
137
- "regression_requirements": [
138
- "Must pass PEFT regression guard structural policy checks.",
139
- "Must not introduce forbidden backbone/serving structural targets.",
140
- "Must preserve harness regression envelope for the selected product line.",
141
- "Validator feedback uptake must not regress.",
142
- "Rollback minimality and revision fidelity must not regress."
143
- ],
144
- "target_groups": [
145
- {
146
- "alpha": 16,
147
- "dropout": 0.05,
148
- "name": "group_1_custom_runtime_harness_bridge",
149
- "rank": 8,
150
- "rationale": "Runtime / harness obedience should attach to explicit interface bridges before any backbone fallback.",
151
- "surface": "custom_runtime_harness_bridge",
152
- "target_modules": [
153
- "failure_signal_bridge.rollback_bridge",
154
- "request_normalizer",
155
- "request_normalizer.adapter",
156
- "rollback_adapter",
157
- "rollback_adapter.head",
158
- "runtime_harness_adapter",
159
- "runtime_harness_adapter.bridge",
160
- "tool_protocol_adapter",
161
- "tool_protocol_adapter.bridge",
162
- "toolspec_bridge",
163
- "toolspec_bridge.adapter",
164
- "toolspec_head",
165
- "toolspec_head.param_schema_adapter",
166
- "toolspec_head.postcondition_adapter",
167
- "toolspec_head.precondition_adapter",
168
- "toolspec_head.receipt_formatter",
169
- "toolspec_head.trigger_gate",
170
- "toolspec_head.validator_gate",
171
- "validator_feedback_loop.rollback_adapter"
172
- ]
173
- },
174
- {
175
- "alpha": 16,
176
- "dropout": 0.0,
177
- "name": "group_2_custom_validator_bridge",
178
- "rank": 8,
179
- "rationale": "Validation and rollback fidelity should prefer explicit validator / rollback bridges.",
180
- "surface": "custom_validator_bridge",
181
- "target_modules": [
182
- "failure_signal_bridge",
183
- "failure_signal_bridge.rollback_bridge",
184
- "rollback_adapter",
185
- "rollback_adapter.head",
186
- "sandbox_rollback_bridge",
187
- "sandbox_rollback_bridge.adapter",
188
- "validator_feedback_bridge",
189
- "validator_feedback_bridge.adapter",
190
- "validator_feedback_loop.rollback_adapter"
191
- ]
192
- }
193
- ],
194
- "target_modules": [
195
- "failure_signal_bridge.rollback_bridge",
196
- "request_normalizer",
197
- "request_normalizer.adapter",
198
- "rollback_adapter",
199
- "rollback_adapter.head",
200
- "runtime_harness_adapter",
201
- "runtime_harness_adapter.bridge",
202
- "tool_protocol_adapter",
203
- "tool_protocol_adapter.bridge",
204
- "toolspec_bridge",
205
- "toolspec_bridge.adapter",
206
- "toolspec_head",
207
- "toolspec_head.param_schema_adapter",
208
- "toolspec_head.postcondition_adapter",
209
- "toolspec_head.precondition_adapter",
210
- "toolspec_head.receipt_formatter",
211
- "toolspec_head.trigger_gate",
212
- "toolspec_head.validator_gate",
213
- "validator_feedback_loop.rollback_adapter",
214
- "failure_signal_bridge",
215
- "sandbox_rollback_bridge",
216
- "sandbox_rollback_bridge.adapter",
217
- "validator_feedback_bridge",
218
- "validator_feedback_bridge.adapter"
219
- ],
220
- "version": "veriloop.lora_recipe_veriloop.v2"
221
- },
222
- "selected_surfaces": [
223
- "custom_runtime_harness_bridge",
224
- "custom_validator_bridge",
225
- "custom_memory_boundary_bridge"
226
- ],
227
- "selected_target_modules": [
228
- "failure_signal_bridge.rollback_bridge",
229
- "rollback_adapter.head",
230
- "runtime_harness_adapter.bridge",
231
- "sandbox_rollback_bridge.adapter",
232
- "toolspec_head.validator_gate",
233
- "validator_feedback_bridge.adapter",
234
- "validator_feedback_loop.rollback_adapter",
235
- "memory_boundary_guard.adapter",
236
- "memory_boundary_guard.rollback_filter",
237
- "request_normalizer.adapter",
238
- "tool_protocol_adapter.bridge",
239
- "toolspec_bridge.adapter",
240
- "toolspec_head.postcondition_adapter",
241
- "toolspec_head.precondition_adapter",
242
- "toolspec_head.receipt_formatter",
243
- "toolspec_head.trigger_gate"
244
- ],
245
- "selection_mode": "minimal",
246
- "version": "veriloop.rollback_adapter_trainer.v9.qwen36",
247
- "warnings": [
248
- "Harness Engineering is primary; PEFT is limited to obedience-facing, interface-facing support surfaces.",
249
- "Backbone bridge tuning disabled explicitly; selector stays on custom surfaces or no-op."
250
- ]
251
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
rollback_adapter/rollback_adapter_train_result.json DELETED
@@ -1,363 +0,0 @@
1
- {
2
- "artifacts": {
3
- "adapter_dir": "/private/wang_libo/veriloop_coder_e1/outputs/rollback_qwen36_rootfix_run1/adapter",
4
- "best_checkpoint_manifest": "/private/wang_libo/veriloop_coder_e1/outputs/rollback_qwen36_rootfix_run1/best_checkpoint_manifest.json",
5
- "epoch_history": "/private/wang_libo/veriloop_coder_e1/outputs/rollback_qwen36_rootfix_run1/epoch_history.json",
6
- "eval_jsonl": "/private/wang_libo/veriloop_coder_e1/outputs/rollback_qwen36_rootfix_run1/rollback_eval.jsonl",
7
- "host_manifest": "/private/wang_libo/veriloop_coder_e1/outputs/rollback_qwen36_rootfix_run1/host_manifest.json",
8
- "plan_json": "/private/wang_libo/veriloop_coder_e1/outputs/rollback_qwen36_rootfix_run1/rollback_adapter_plan.json",
9
- "rollback_head": "/private/wang_libo/veriloop_coder_e1/outputs/rollback_qwen36_rootfix_run1/rollback_head.pt",
10
- "tokenizer_dir": "/private/wang_libo/veriloop_coder_e1/outputs/rollback_qwen36_rootfix_run1/tokenizer",
11
- "train_jsonl": "/private/wang_libo/veriloop_coder_e1/outputs/rollback_qwen36_rootfix_run1/rollback_train.jsonl",
12
- "training_manifest": "/private/wang_libo/veriloop_coder_e1/outputs/rollback_qwen36_rootfix_run1/rollback_training_manifest.json"
13
- },
14
- "dataset": {
15
- "cause_vocab": [
16
- "none",
17
- "evidence_contradiction",
18
- "execution_negation",
19
- "validator_rejection",
20
- "patch_regression",
21
- "worktree_conflict",
22
- "high_risk_unsupported",
23
- "tool_selfcheck_failure",
24
- "reverse_engineering_speculation"
25
- ],
26
- "eval_size": 45,
27
- "mode_vocab": [
28
- "contradiction",
29
- "execution_failure",
30
- "validator_rejection",
31
- "patch_regression",
32
- "worktree_conflict",
33
- "high_risk_unsupported",
34
- "tool_selfcheck_repair",
35
- "reverse_engineering_drift",
36
- "validated_stable"
37
- ],
38
- "modes": [
39
- "contradiction",
40
- "execution_failure",
41
- "high_risk_unsupported",
42
- "patch_regression",
43
- "reverse_engineering_drift",
44
- "tool_selfcheck_repair",
45
- "validated_stable",
46
- "validator_rejection",
47
- "worktree_conflict"
48
- ],
49
- "need_vocab": [
50
- "none",
51
- "advisory",
52
- "required"
53
- ],
54
- "rewrite_vocab": [
55
- "do_not_rollback",
56
- "local_patch_only",
57
- "validator_scoped_revision",
58
- "minimum_diff_patch",
59
- "do_not_overwrite_worktree_state",
60
- "fail_closed",
61
- "repair_via_bounded_selfcheck_loop",
62
- "bounded_observation_first",
63
- "local_conflict_preserving_revision"
64
- ],
65
- "train_size": 126
66
- },
67
- "eval_metrics": {
68
- "adapter_exported": true,
69
- "auto_lora_from_ia3": false,
70
- "avg_binary_accuracy": 0.8194444444444444,
71
- "best_epoch": 3,
72
- "best_quality_score": 0.3986773560841878,
73
- "cause_accuracy": 0.4888888888888889,
74
- "count": 45,
75
- "eval_batches": 45,
76
- "eval_loss": 7.656409973568387,
77
- "fail_closed_accuracy": 0.7777777777777778,
78
- "minimal_diff_accuracy": 0.5555555555555556,
79
- "mode_accuracy": 0.3333333333333333,
80
- "need_accuracy": 0.7777777777777778,
81
- "peft_method": "lora_narrow",
82
- "preserve_conflict_accuracy": 0.7777777777777778,
83
- "quality_score": 0.3986773560841878,
84
- "reverse_engineering_bounded_accuracy": 0.8888888888888888,
85
- "rewrite_accuracy": 0.4888888888888889,
86
- "selfcheck_route_accuracy": 0.5555555555555556,
87
- "session_continuity_accuracy": 1.0,
88
- "used_peft": true,
89
- "validator_aligned_accuracy": 1.0,
90
- "worktree_safe_accuracy": 1.0
91
- },
92
- "plan": {
93
- "backbone": "/public/wang_libo/veriloop_coder_e1/model",
94
- "dataset_summary": {
95
- "cause_vocab": [
96
- "none",
97
- "evidence_contradiction",
98
- "execution_negation",
99
- "validator_rejection",
100
- "patch_regression",
101
- "worktree_conflict",
102
- "high_risk_unsupported",
103
- "tool_selfcheck_failure",
104
- "reverse_engineering_speculation"
105
- ],
106
- "eval_size": 45,
107
- "mode_vocab": [
108
- "contradiction",
109
- "execution_failure",
110
- "validator_rejection",
111
- "patch_regression",
112
- "worktree_conflict",
113
- "high_risk_unsupported",
114
- "tool_selfcheck_repair",
115
- "reverse_engineering_drift",
116
- "validated_stable"
117
- ],
118
- "modes": [
119
- "contradiction",
120
- "execution_failure",
121
- "high_risk_unsupported",
122
- "patch_regression",
123
- "reverse_engineering_drift",
124
- "tool_selfcheck_repair",
125
- "validated_stable",
126
- "validator_rejection",
127
- "worktree_conflict"
128
- ],
129
- "need_vocab": [
130
- "none",
131
- "advisory",
132
- "required"
133
- ],
134
- "rewrite_vocab": [
135
- "do_not_rollback",
136
- "local_patch_only",
137
- "validator_scoped_revision",
138
- "minimum_diff_patch",
139
- "do_not_overwrite_worktree_state",
140
- "fail_closed",
141
- "repair_via_bounded_selfcheck_loop",
142
- "bounded_observation_first",
143
- "local_conflict_preserving_revision"
144
- ],
145
- "train_size": 126
146
- },
147
- "excluded_surfaces": [
148
- "(^|\\.)lm_head($|\\.)::Do not retune final token head; too broad and evaluation-heavy.",
149
- "(^|\\.)embed_tokens($|\\.)::Embedding surgery risks broad semantic drift.",
150
- "(^|\\.)norm($|\\.)::Global norm tuning can destabilize calibration across scenes.",
151
- "attnres|attention_residual::Block AttnRes may be mounted structurally but is never a PEFT target.",
152
- "dualpath::DualPath is serving/runtime infrastructure only.",
153
- "mhc|hyper[-_]?connection::mHC-inspired stability hooks remain structural, not PEFT surfaces.",
154
- "rope|rotary::RoPE/context surgery is handled architecturally, not by narrow PEFT here.",
155
- "kvcache|kv_cache::KV-cache runtime surfaces are not PEFT targets.",
156
- "(^|\\.)memory(_store|_bank)?($|\\.)::Persistent memory stores are harness/runtime policy surfaces, not PEFT targets."
157
- ],
158
- "notes": [
159
- "Primary route is host-surface-first rollback training.",
160
- "Validator receipts, failure routing, patch state, worktree continuity, self-check repair, and reverse-engineering boundedness are first-class signals.",
161
- "DualPath, Block AttnRes, mHC hooks, and MoE routers/experts remain structurally excluded.",
162
- "This adapter should improve rollback obedience, not general coding free-formity."
163
- ],
164
- "peft_method": "lora_narrow",
165
- "product_line": "veriloop_coder",
166
- "recipe": {
167
- "adapter_family": "validator_rollback",
168
- "backbone": "/public/wang_libo/veriloop_coder_e1/model",
169
- "backbone_family": "qwen_dense",
170
- "excluded_patterns": [
171
- "(?i)\\bdualpath\\b",
172
- "(?i)\\bmhc\\b",
173
- "(?i)\\bfull[_\\- ]?attnres\\b",
174
- "(?i)\\battnres(_full)?\\b",
175
- "(?i)\\brouter\\b",
176
- "(?i)\\bexperts?\\b",
177
- "(?i)\\bmoe\\b.*\\b(gate|router|expert)\\b",
178
- "(?i)\\brope\\b.*\\b(freq|inv_freq|theta|rotary)\\b",
179
- "(?i)\\bkvcache\\b",
180
- "(?i)\\bposition_embedding\\b",
181
- "(?i)\\bembed(tokens|ding)?\\b",
182
- "(?i)\\blm_head\\b"
183
- ],
184
- "harness_constraints": [
185
- "Harness Engineering remains the primary convergence layer.",
186
- "Adapter must not bypass runtime orchestrator / validator / rollback loops.",
187
- "Adapter outputs remain subordinate to VeriLoop control-plane decisions.",
188
- "Adapter must not create hidden prompt-style memory authority.",
189
- "Adapter must preserve validator-first correction and minimal-diff rollback discipline.",
190
- "Patch production must remain subordinate to validator receipts and failure routing."
191
- ],
192
- "hyperparams": {
193
- "alpha": 16,
194
- "bias": "none",
195
- "dropout": 0.08,
196
- "fan_in_fan_out": false,
197
- "modules_to_save": [
198
- "input_layernorm"
199
- ],
200
- "r": 8,
201
- "task_type": "CAUSAL_LM"
202
- },
203
- "merge_policy": "side_load",
204
- "metadata": {
205
- "allow_backbone_bridge": false,
206
- "allow_vla_action_expert": false,
207
- "harness_first": true,
208
- "prefer_explicit_heads": true,
209
- "prefer_qlora_for_backbone_bridge": false,
210
- "require_harness_first": true,
211
- "reverse_engineering_readiness": true,
212
- "rollback_training": true,
213
- "selector_group_count": 2,
214
- "selfcheck_loop_readiness": true,
215
- "strict_narrow_scope": true,
216
- "trainer": "veriloop.rollback_adapter_trainer.v9.qwen36"
217
- },
218
- "notes": [
219
- "Backbone bridge tuning disabled explicitly; selector stays on custom surfaces or no-op.",
220
- "Backbone family inferred as qwen_dense.",
221
- "PEFT method resolved as lora_narrow.",
222
- "Recipe is harness-first: runtime convergence remains in VeriLoop control-plane + harness, not in broad weight surgery.",
223
- "Block AttnRes, DualPath, mHC hooks, RoPE, KV-cache, and broad MoE routing remain structurally excluded."
224
- ],
225
- "peft_method": "lora_narrow",
226
- "precision_policy": "auto",
227
- "product_line": "veriloop_coder",
228
- "regression_requirements": [
229
- "Must pass PEFT regression guard structural policy checks.",
230
- "Must not introduce forbidden backbone/serving structural targets.",
231
- "Must preserve harness regression envelope for the selected product line.",
232
- "Validator feedback uptake must not regress.",
233
- "Rollback minimality and revision fidelity must not regress."
234
- ],
235
- "target_groups": [
236
- {
237
- "alpha": 16,
238
- "dropout": 0.05,
239
- "name": "group_1_custom_runtime_harness_bridge",
240
- "rank": 8,
241
- "rationale": "Runtime / harness obedience should attach to explicit interface bridges before any backbone fallback.",
242
- "surface": "custom_runtime_harness_bridge",
243
- "target_modules": [
244
- "failure_signal_bridge.rollback_bridge",
245
- "request_normalizer",
246
- "request_normalizer.adapter",
247
- "rollback_adapter",
248
- "rollback_adapter.head",
249
- "runtime_harness_adapter",
250
- "runtime_harness_adapter.bridge",
251
- "tool_protocol_adapter",
252
- "tool_protocol_adapter.bridge",
253
- "toolspec_bridge",
254
- "toolspec_bridge.adapter",
255
- "toolspec_head",
256
- "toolspec_head.param_schema_adapter",
257
- "toolspec_head.postcondition_adapter",
258
- "toolspec_head.precondition_adapter",
259
- "toolspec_head.receipt_formatter",
260
- "toolspec_head.trigger_gate",
261
- "toolspec_head.validator_gate",
262
- "validator_feedback_loop.rollback_adapter"
263
- ]
264
- },
265
- {
266
- "alpha": 16,
267
- "dropout": 0.0,
268
- "name": "group_2_custom_validator_bridge",
269
- "rank": 8,
270
- "rationale": "Validation and rollback fidelity should prefer explicit validator / rollback bridges.",
271
- "surface": "custom_validator_bridge",
272
- "target_modules": [
273
- "failure_signal_bridge",
274
- "failure_signal_bridge.rollback_bridge",
275
- "rollback_adapter",
276
- "rollback_adapter.head",
277
- "sandbox_rollback_bridge",
278
- "sandbox_rollback_bridge.adapter",
279
- "validator_feedback_bridge",
280
- "validator_feedback_bridge.adapter",
281
- "validator_feedback_loop.rollback_adapter"
282
- ]
283
- }
284
- ],
285
- "target_modules": [
286
- "failure_signal_bridge.rollback_bridge",
287
- "request_normalizer",
288
- "request_normalizer.adapter",
289
- "rollback_adapter",
290
- "rollback_adapter.head",
291
- "runtime_harness_adapter",
292
- "runtime_harness_adapter.bridge",
293
- "tool_protocol_adapter",
294
- "tool_protocol_adapter.bridge",
295
- "toolspec_bridge",
296
- "toolspec_bridge.adapter",
297
- "toolspec_head",
298
- "toolspec_head.param_schema_adapter",
299
- "toolspec_head.postcondition_adapter",
300
- "toolspec_head.precondition_adapter",
301
- "toolspec_head.receipt_formatter",
302
- "toolspec_head.trigger_gate",
303
- "toolspec_head.validator_gate",
304
- "validator_feedback_loop.rollback_adapter",
305
- "failure_signal_bridge",
306
- "sandbox_rollback_bridge",
307
- "sandbox_rollback_bridge.adapter",
308
- "validator_feedback_bridge",
309
- "validator_feedback_bridge.adapter"
310
- ],
311
- "version": "veriloop.lora_recipe_veriloop.v2"
312
- },
313
- "selected_surfaces": [
314
- "custom_runtime_harness_bridge",
315
- "custom_validator_bridge",
316
- "custom_memory_boundary_bridge"
317
- ],
318
- "selected_target_modules": [
319
- "failure_signal_bridge.rollback_bridge",
320
- "rollback_adapter.head",
321
- "runtime_harness_adapter.bridge",
322
- "sandbox_rollback_bridge.adapter",
323
- "toolspec_head.validator_gate",
324
- "validator_feedback_bridge.adapter",
325
- "validator_feedback_loop.rollback_adapter",
326
- "memory_boundary_guard.adapter",
327
- "memory_boundary_guard.rollback_filter",
328
- "request_normalizer.adapter",
329
- "tool_protocol_adapter.bridge",
330
- "toolspec_bridge.adapter",
331
- "toolspec_head.postcondition_adapter",
332
- "toolspec_head.precondition_adapter",
333
- "toolspec_head.receipt_formatter",
334
- "toolspec_head.trigger_gate"
335
- ],
336
- "selection_mode": "minimal",
337
- "version": "veriloop.rollback_adapter_trainer.v9.qwen36",
338
- "warnings": [
339
- "Harness Engineering is primary; PEFT is limited to obedience-facing, interface-facing support surfaces.",
340
- "Backbone bridge tuning disabled explicitly; selector stays on custom surfaces or no-op."
341
- ]
342
- },
343
- "status": "trained",
344
- "train_metrics": {
345
- "adapter_exported": true,
346
- "auto_lora_from_ia3": false,
347
- "best_epoch": 3,
348
- "best_quality_score": 0.3986773560841878,
349
- "epochs_completed": 4,
350
- "loss": 0.4452953128114579,
351
- "micro_batches": 126,
352
- "micro_batches_total": 504,
353
- "optimizer_steps": 8,
354
- "optimizer_steps_total": 32,
355
- "peft_method": "lora_narrow",
356
- "used_peft": true
357
- },
358
- "version": "veriloop.rollback_adapter_trainer.v9.qwen36",
359
- "warnings": [
360
- "Harness Engineering is primary; PEFT is limited to obedience-facing, interface-facing support surfaces.",
361
- "Backbone bridge tuning disabled explicitly; selector stays on custom surfaces or no-op."
362
- ]
363
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
rollback_adapter/rollback_eval.jsonl DELETED
@@ -1,45 +0,0 @@
1
- {"mode": "contradiction", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=contradiction\nrollback_focus=eval_conflict_preserve\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nCurrent evidence negates an active claim and the contradiction edge must remain visible during rollback.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nevidence_conflict=explicit\nconflict_edge=preserve\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=retrieved_receipt_conflict\ndominant_cause_signal=evidence_contradiction\nrequired_rewrite_scope=local_conflict_preserving_revision\nforbidden_rewrite_scope=silent_conflict_erasure\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "evidence_contradiction", "rewrite_name": "local_conflict_preserving_revision", "need_id": 2, "cause_id": 1, "rewrite_id": 8, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 0}}
2
- {"mode": "contradiction", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=contradiction\nrollback_focus=eval_conflict_local\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nA validator-visible contradiction has appeared and local conflict-preserving revision is required.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=minimal\nworkspace_delta=preserved\nrollback_budget=guarded\nclaim_status=locally_demote\nconflict_visibility=required\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=conflicting_ground_truth_edges\ndominant_cause_signal=evidence_contradiction\nrequired_rewrite_scope=preserve_conflict_then_revise_locally\nforbidden_rewrite_scope=broad_regeneration\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "evidence_contradiction", "rewrite_name": "local_conflict_preserving_revision", "need_id": 2, "cause_id": 1, "rewrite_id": 8, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 1}}
3
- {"mode": "contradiction", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=contradiction\nrollback_focus=eval_conflict_preserve\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nCurrent evidence negates an active claim and the contradiction edge must remain visible during rollback.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nevidence_conflict=explicit\nconflict_edge=preserve\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=retrieved_receipt_conflict\ndominant_cause_signal=evidence_contradiction\nrequired_rewrite_scope=local_conflict_preserving_revision\nforbidden_rewrite_scope=silent_conflict_erasure\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "evidence_contradiction", "rewrite_name": "local_conflict_preserving_revision", "need_id": 2, "cause_id": 1, "rewrite_id": 8, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 0}}
4
- {"mode": "contradiction", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=contradiction\nrollback_focus=eval_conflict_local\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nA validator-visible contradiction has appeared and local conflict-preserving revision is required.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=minimal\nworkspace_delta=preserved\nrollback_budget=guarded\nclaim_status=locally_demote\nconflict_visibility=required\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=conflicting_ground_truth_edges\ndominant_cause_signal=evidence_contradiction\nrequired_rewrite_scope=preserve_conflict_then_revise_locally\nforbidden_rewrite_scope=broad_regeneration\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "evidence_contradiction", "rewrite_name": "local_conflict_preserving_revision", "need_id": 2, "cause_id": 1, "rewrite_id": 8, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 1}}
5
- {"mode": "contradiction", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=contradiction\nrollback_focus=eval_conflict_preserve\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nCurrent evidence negates an active claim and the contradiction edge must remain visible during rollback.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nevidence_conflict=explicit\nconflict_edge=preserve\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=retrieved_receipt_conflict\ndominant_cause_signal=evidence_contradiction\nrequired_rewrite_scope=local_conflict_preserving_revision\nforbidden_rewrite_scope=silent_conflict_erasure\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "evidence_contradiction", "rewrite_name": "local_conflict_preserving_revision", "need_id": 2, "cause_id": 1, "rewrite_id": 8, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 0}}
6
- {"mode": "execution_failure", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=execution_failure\nrollback_focus=eval_exec_local\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nA bounded execution trace invalidated one branch and rollback should remain local to the failed path.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nexecution_trace=failed\nrepair_scope=failed_branch_only\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=sandbox_execution_failure\ndominant_cause_signal=execution_negation\nrequired_rewrite_scope=local_patch_only\nforbidden_rewrite_scope=full_repo_rewrite\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "execution_negation", "rewrite_name": "local_patch_only", "need_id": 2, "cause_id": 2, "rewrite_id": 1, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 1, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 0}}
7
- {"mode": "execution_failure", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=execution_failure\nrollback_focus=eval_exec_patch\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nThe latest patch failed during sandbox execution while neighboring validated work should be retained.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=minimal\nworkspace_delta=preserved\nrollback_budget=guarded\nsandbox_status=nonzero\nrepair_path=local_patch\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=bounded_test_failure\ndominant_cause_signal=execution_negation\nrequired_rewrite_scope=failed_branch_local_repair\nforbidden_rewrite_scope=rewrite_validated_regions\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "execution_negation", "rewrite_name": "local_patch_only", "need_id": 2, "cause_id": 2, "rewrite_id": 1, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 1, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 1}}
8
- {"mode": "execution_failure", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=execution_failure\nrollback_focus=eval_exec_local\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nA bounded execution trace invalidated one branch and rollback should remain local to the failed path.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nexecution_trace=failed\nrepair_scope=failed_branch_only\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=sandbox_execution_failure\ndominant_cause_signal=execution_negation\nrequired_rewrite_scope=local_patch_only\nforbidden_rewrite_scope=full_repo_rewrite\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "execution_negation", "rewrite_name": "local_patch_only", "need_id": 2, "cause_id": 2, "rewrite_id": 1, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 1, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 0}}
9
- {"mode": "execution_failure", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=execution_failure\nrollback_focus=eval_exec_patch\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nThe latest patch failed during sandbox execution while neighboring validated work should be retained.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=minimal\nworkspace_delta=preserved\nrollback_budget=guarded\nsandbox_status=nonzero\nrepair_path=local_patch\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=bounded_test_failure\ndominant_cause_signal=execution_negation\nrequired_rewrite_scope=failed_branch_local_repair\nforbidden_rewrite_scope=rewrite_validated_regions\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "execution_negation", "rewrite_name": "local_patch_only", "need_id": 2, "cause_id": 2, "rewrite_id": 1, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 1, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 1}}
10
- {"mode": "execution_failure", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=execution_failure\nrollback_focus=eval_exec_local\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nA bounded execution trace invalidated one branch and rollback should remain local to the failed path.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nexecution_trace=failed\nrepair_scope=failed_branch_only\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=sandbox_execution_failure\ndominant_cause_signal=execution_negation\nrequired_rewrite_scope=local_patch_only\nforbidden_rewrite_scope=full_repo_rewrite\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "execution_negation", "rewrite_name": "local_patch_only", "need_id": 2, "cause_id": 2, "rewrite_id": 1, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 1, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 0}}
11
- {"mode": "validator_rejection", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=validator_rejection\nrollback_focus=eval_validator_scope\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nValidator receipts reject the current submission and the correction must stay validator-scoped.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nvalidator_gate=reject\nreceipt_alignment=broken\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=validator_receipt_rejection\ndominant_cause_signal=validator_rejection\nrequired_rewrite_scope=validator_scoped_revision\nforbidden_rewrite_scope=receipt_agnostic_rewrite\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "validator_rejection", "rewrite_name": "validator_scoped_revision", "need_id": 2, "cause_id": 3, "rewrite_id": 2, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 1, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 0}}
12
- {"mode": "validator_rejection", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=validator_rejection\nrollback_focus=eval_validator_receipt\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nAcceptance criteria failed under validator review even though the patch looks superficially plausible.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=minimal\nworkspace_delta=preserved\nrollback_budget=guarded\nacceptance_criteria=failed\nvalidator_scope=authoritative\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=acceptance_gate_reject\ndominant_cause_signal=validator_rejection\nrequired_rewrite_scope=validator_bound_local_revision\nforbidden_rewrite_scope=bypass_validator_scope\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "validator_rejection", "rewrite_name": "validator_scoped_revision", "need_id": 2, "cause_id": 3, "rewrite_id": 2, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 1, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 1}}
13
- {"mode": "validator_rejection", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=validator_rejection\nrollback_focus=eval_validator_scope\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nValidator receipts reject the current submission and the correction must stay validator-scoped.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nvalidator_gate=reject\nreceipt_alignment=broken\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=validator_receipt_rejection\ndominant_cause_signal=validator_rejection\nrequired_rewrite_scope=validator_scoped_revision\nforbidden_rewrite_scope=receipt_agnostic_rewrite\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "validator_rejection", "rewrite_name": "validator_scoped_revision", "need_id": 2, "cause_id": 3, "rewrite_id": 2, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 1, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 0}}
14
- {"mode": "validator_rejection", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=validator_rejection\nrollback_focus=eval_validator_receipt\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nAcceptance criteria failed under validator review even though the patch looks superficially plausible.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=minimal\nworkspace_delta=preserved\nrollback_budget=guarded\nacceptance_criteria=failed\nvalidator_scope=authoritative\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=acceptance_gate_reject\ndominant_cause_signal=validator_rejection\nrequired_rewrite_scope=validator_bound_local_revision\nforbidden_rewrite_scope=bypass_validator_scope\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "validator_rejection", "rewrite_name": "validator_scoped_revision", "need_id": 2, "cause_id": 3, "rewrite_id": 2, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 1, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 1}}
15
- {"mode": "validator_rejection", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=validator_rejection\nrollback_focus=eval_validator_scope\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nValidator receipts reject the current submission and the correction must stay validator-scoped.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nvalidator_gate=reject\nreceipt_alignment=broken\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=validator_receipt_rejection\ndominant_cause_signal=validator_rejection\nrequired_rewrite_scope=validator_scoped_revision\nforbidden_rewrite_scope=receipt_agnostic_rewrite\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "validator_rejection", "rewrite_name": "validator_scoped_revision", "need_id": 2, "cause_id": 3, "rewrite_id": 2, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 1, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 0}}
16
- {"mode": "patch_regression", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=patch_regression\nrollback_focus=eval_patch_smallest\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nOne small region regressed after the newest patch and only that region should be revised.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nregression_scope=localized\nminimal_diff=required\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=patch_regression_observed\ndominant_cause_signal=patch_regression\nrequired_rewrite_scope=minimum_diff_patch\nforbidden_rewrite_scope=wide_area_rewrite\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "advisory", "cause_name": "patch_regression", "rewrite_name": "minimum_diff_patch", "need_id": 1, "cause_id": 4, "rewrite_id": 3, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 1, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 0}}
17
- {"mode": "patch_regression", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=patch_regression\nrollback_focus=eval_patch_local\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nA local regression appeared in the edited diff while previously validated segments remain good.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=minimal\nworkspace_delta=preserved\nrollback_budget=guarded\npatch_lineage=mostly_valid\nrollback_scope=single_region\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=recent_diff_regressed\ndominant_cause_signal=patch_regression\nrequired_rewrite_scope=single_region_patch_repair\nforbidden_rewrite_scope=discard_valid_neighbors\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "advisory", "cause_name": "patch_regression", "rewrite_name": "minimum_diff_patch", "need_id": 1, "cause_id": 4, "rewrite_id": 3, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 1, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 1}}
18
- {"mode": "patch_regression", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=patch_regression\nrollback_focus=eval_patch_smallest\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nOne small region regressed after the newest patch and only that region should be revised.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nregression_scope=localized\nminimal_diff=required\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=patch_regression_observed\ndominant_cause_signal=patch_regression\nrequired_rewrite_scope=minimum_diff_patch\nforbidden_rewrite_scope=wide_area_rewrite\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "advisory", "cause_name": "patch_regression", "rewrite_name": "minimum_diff_patch", "need_id": 1, "cause_id": 4, "rewrite_id": 3, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 1, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 0}}
19
- {"mode": "patch_regression", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=patch_regression\nrollback_focus=eval_patch_local\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nA local regression appeared in the edited diff while previously validated segments remain good.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=minimal\nworkspace_delta=preserved\nrollback_budget=guarded\npatch_lineage=mostly_valid\nrollback_scope=single_region\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=recent_diff_regressed\ndominant_cause_signal=patch_regression\nrequired_rewrite_scope=single_region_patch_repair\nforbidden_rewrite_scope=discard_valid_neighbors\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "advisory", "cause_name": "patch_regression", "rewrite_name": "minimum_diff_patch", "need_id": 1, "cause_id": 4, "rewrite_id": 3, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 1, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 1}}
20
- {"mode": "patch_regression", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=patch_regression\nrollback_focus=eval_patch_smallest\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nOne small region regressed after the newest patch and only that region should be revised.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nregression_scope=localized\nminimal_diff=required\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=patch_regression_observed\ndominant_cause_signal=patch_regression\nrequired_rewrite_scope=minimum_diff_patch\nforbidden_rewrite_scope=wide_area_rewrite\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "advisory", "cause_name": "patch_regression", "rewrite_name": "minimum_diff_patch", "need_id": 1, "cause_id": 4, "rewrite_id": 3, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 1, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 0}}
21
- {"mode": "worktree_conflict", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=worktree_conflict\nrollback_focus=eval_worktree_snapshot\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nThe rollback candidate conflicts with the live worktree snapshot and should not overwrite workspace state.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nworktree_state=conflicted\noverwrite_policy=forbidden\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=live_worktree_conflict\ndominant_cause_signal=worktree_conflict\nrequired_rewrite_scope=do_not_overwrite_worktree_state\nforbidden_rewrite_scope=overwrite_workspace_state\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "worktree_conflict", "rewrite_name": "do_not_overwrite_worktree_state", "need_id": 2, "cause_id": 5, "rewrite_id": 4, "preserve_conflict": 1, "minimal_diff": 0, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 0}}
22
- {"mode": "worktree_conflict", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=worktree_conflict\nrollback_focus=eval_worktree_preserve\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nWorkspace lineage drift is present, so rollback must preserve current worktree context.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=minimal\nworkspace_delta=preserved\nrollback_budget=guarded\nworkspace_snapshot=lineage_mismatch\nrollback_scope=preserve_worktree\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=snapshot_lineage_mismatch\ndominant_cause_signal=worktree_conflict\nrequired_rewrite_scope=preserve_worktree_then_reconcile\nforbidden_rewrite_scope=destructive_checkout_style_rewrite\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "worktree_conflict", "rewrite_name": "do_not_overwrite_worktree_state", "need_id": 2, "cause_id": 5, "rewrite_id": 4, "preserve_conflict": 1, "minimal_diff": 0, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 1}}
23
- {"mode": "worktree_conflict", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=worktree_conflict\nrollback_focus=eval_worktree_snapshot\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nThe rollback candidate conflicts with the live worktree snapshot and should not overwrite workspace state.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nworktree_state=conflicted\noverwrite_policy=forbidden\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=live_worktree_conflict\ndominant_cause_signal=worktree_conflict\nrequired_rewrite_scope=do_not_overwrite_worktree_state\nforbidden_rewrite_scope=overwrite_workspace_state\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "worktree_conflict", "rewrite_name": "do_not_overwrite_worktree_state", "need_id": 2, "cause_id": 5, "rewrite_id": 4, "preserve_conflict": 1, "minimal_diff": 0, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 0}}
24
- {"mode": "worktree_conflict", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=worktree_conflict\nrollback_focus=eval_worktree_preserve\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nWorkspace lineage drift is present, so rollback must preserve current worktree context.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=minimal\nworkspace_delta=preserved\nrollback_budget=guarded\nworkspace_snapshot=lineage_mismatch\nrollback_scope=preserve_worktree\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=snapshot_lineage_mismatch\ndominant_cause_signal=worktree_conflict\nrequired_rewrite_scope=preserve_worktree_then_reconcile\nforbidden_rewrite_scope=destructive_checkout_style_rewrite\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "worktree_conflict", "rewrite_name": "do_not_overwrite_worktree_state", "need_id": 2, "cause_id": 5, "rewrite_id": 4, "preserve_conflict": 1, "minimal_diff": 0, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 1}}
25
- {"mode": "worktree_conflict", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=worktree_conflict\nrollback_focus=eval_worktree_snapshot\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nThe rollback candidate conflicts with the live worktree snapshot and should not overwrite workspace state.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nworktree_state=conflicted\noverwrite_policy=forbidden\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=live_worktree_conflict\ndominant_cause_signal=worktree_conflict\nrequired_rewrite_scope=do_not_overwrite_worktree_state\nforbidden_rewrite_scope=overwrite_workspace_state\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "worktree_conflict", "rewrite_name": "do_not_overwrite_worktree_state", "need_id": 2, "cause_id": 5, "rewrite_id": 4, "preserve_conflict": 1, "minimal_diff": 0, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 0}}
26
- {"mode": "high_risk_unsupported", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=high_risk_unsupported\nrollback_focus=eval_fail_closed\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nA high-risk branch lacks evidence and must fail closed instead of continuing.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nrisk_band=high\nsupport_state=insufficient\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=high_risk_without_support\ndominant_cause_signal=high_risk_unsupported\nrequired_rewrite_scope=fail_closed\nforbidden_rewrite_scope=continue_as_validated\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "high_risk_unsupported", "rewrite_name": "fail_closed", "need_id": 2, "cause_id": 6, "rewrite_id": 5, "preserve_conflict": 0, "minimal_diff": 0, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 0, "fail_closed": 1}, "metadata": {"split": "eval", "variant_rank": 0}}
27
- {"mode": "high_risk_unsupported", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=high_risk_unsupported\nrollback_focus=eval_high_risk_retract\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nUnsupported high-risk output is present and should be retracted under rollback discipline.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=minimal\nworkspace_delta=preserved\nrollback_budget=guarded\npolicy_mode=fail_closed\nunsupported_claims=retract\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=unsafe_claim_without_receipts\ndominant_cause_signal=high_risk_unsupported\nrequired_rewrite_scope=retract_and_fail_closed\nforbidden_rewrite_scope=speculative_completion\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "high_risk_unsupported", "rewrite_name": "fail_closed", "need_id": 2, "cause_id": 6, "rewrite_id": 5, "preserve_conflict": 0, "minimal_diff": 0, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 0, "fail_closed": 1}, "metadata": {"split": "eval", "variant_rank": 1}}
28
- {"mode": "high_risk_unsupported", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=high_risk_unsupported\nrollback_focus=eval_fail_closed\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nA high-risk branch lacks evidence and must fail closed instead of continuing.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nrisk_band=high\nsupport_state=insufficient\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=high_risk_without_support\ndominant_cause_signal=high_risk_unsupported\nrequired_rewrite_scope=fail_closed\nforbidden_rewrite_scope=continue_as_validated\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "high_risk_unsupported", "rewrite_name": "fail_closed", "need_id": 2, "cause_id": 6, "rewrite_id": 5, "preserve_conflict": 0, "minimal_diff": 0, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 0, "fail_closed": 1}, "metadata": {"split": "eval", "variant_rank": 0}}
29
- {"mode": "high_risk_unsupported", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=high_risk_unsupported\nrollback_focus=eval_high_risk_retract\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nUnsupported high-risk output is present and should be retracted under rollback discipline.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=minimal\nworkspace_delta=preserved\nrollback_budget=guarded\npolicy_mode=fail_closed\nunsupported_claims=retract\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=unsafe_claim_without_receipts\ndominant_cause_signal=high_risk_unsupported\nrequired_rewrite_scope=retract_and_fail_closed\nforbidden_rewrite_scope=speculative_completion\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "high_risk_unsupported", "rewrite_name": "fail_closed", "need_id": 2, "cause_id": 6, "rewrite_id": 5, "preserve_conflict": 0, "minimal_diff": 0, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 0, "fail_closed": 1}, "metadata": {"split": "eval", "variant_rank": 1}}
30
- {"mode": "high_risk_unsupported", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=high_risk_unsupported\nrollback_focus=eval_fail_closed\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nA high-risk branch lacks evidence and must fail closed instead of continuing.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nrisk_band=high\nsupport_state=insufficient\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=high_risk_without_support\ndominant_cause_signal=high_risk_unsupported\nrequired_rewrite_scope=fail_closed\nforbidden_rewrite_scope=continue_as_validated\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "high_risk_unsupported", "rewrite_name": "fail_closed", "need_id": 2, "cause_id": 6, "rewrite_id": 5, "preserve_conflict": 0, "minimal_diff": 0, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 0, "fail_closed": 1}, "metadata": {"split": "eval", "variant_rank": 0}}
31
- {"mode": "tool_selfcheck_repair", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=tool_selfcheck_repair\nrollback_focus=eval_selfcheck_loop\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nA bounded self-check failed and the system should repair via a narrow self-check loop.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nselfcheck_status=failed\nrepair_loop=bounded\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=tool_selfcheck_negative\ndominant_cause_signal=tool_selfcheck_failure\nrequired_rewrite_scope=repair_via_bounded_selfcheck_loop\nforbidden_rewrite_scope=broad_rewrite_without_selfcheck\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "tool_selfcheck_failure", "rewrite_name": "repair_via_bounded_selfcheck_loop", "need_id": 2, "cause_id": 7, "rewrite_id": 6, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 1, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 0}}
32
- {"mode": "tool_selfcheck_repair", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=tool_selfcheck_repair\nrollback_focus=eval_selfcheck_patch\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nTool validation rejected the patch and another local self-check repair cycle is warranted.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=minimal\nworkspace_delta=preserved\nrollback_budget=guarded\ntool_validation=negative\nrepair_scope=narrow\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=compiler_or_unit_gate_failed\ndominant_cause_signal=tool_selfcheck_failure\nrequired_rewrite_scope=narrow_selfcheck_repair_cycle\nforbidden_rewrite_scope=skip_repair_loop\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "tool_selfcheck_failure", "rewrite_name": "repair_via_bounded_selfcheck_loop", "need_id": 2, "cause_id": 7, "rewrite_id": 6, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 1, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 1}}
33
- {"mode": "tool_selfcheck_repair", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=tool_selfcheck_repair\nrollback_focus=eval_selfcheck_loop\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nA bounded self-check failed and the system should repair via a narrow self-check loop.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nselfcheck_status=failed\nrepair_loop=bounded\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=tool_selfcheck_negative\ndominant_cause_signal=tool_selfcheck_failure\nrequired_rewrite_scope=repair_via_bounded_selfcheck_loop\nforbidden_rewrite_scope=broad_rewrite_without_selfcheck\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "tool_selfcheck_failure", "rewrite_name": "repair_via_bounded_selfcheck_loop", "need_id": 2, "cause_id": 7, "rewrite_id": 6, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 1, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 0}}
34
- {"mode": "tool_selfcheck_repair", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=tool_selfcheck_repair\nrollback_focus=eval_selfcheck_patch\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nTool validation rejected the patch and another local self-check repair cycle is warranted.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=minimal\nworkspace_delta=preserved\nrollback_budget=guarded\ntool_validation=negative\nrepair_scope=narrow\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=compiler_or_unit_gate_failed\ndominant_cause_signal=tool_selfcheck_failure\nrequired_rewrite_scope=narrow_selfcheck_repair_cycle\nforbidden_rewrite_scope=skip_repair_loop\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "tool_selfcheck_failure", "rewrite_name": "repair_via_bounded_selfcheck_loop", "need_id": 2, "cause_id": 7, "rewrite_id": 6, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 1, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 1}}
35
- {"mode": "tool_selfcheck_repair", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=tool_selfcheck_repair\nrollback_focus=eval_selfcheck_loop\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nA bounded self-check failed and the system should repair via a narrow self-check loop.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nselfcheck_status=failed\nrepair_loop=bounded\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=tool_selfcheck_negative\ndominant_cause_signal=tool_selfcheck_failure\nrequired_rewrite_scope=repair_via_bounded_selfcheck_loop\nforbidden_rewrite_scope=broad_rewrite_without_selfcheck\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "tool_selfcheck_failure", "rewrite_name": "repair_via_bounded_selfcheck_loop", "need_id": 2, "cause_id": 7, "rewrite_id": 6, "preserve_conflict": 1, "minimal_diff": 1, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 1, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 0}}
36
- {"mode": "reverse_engineering_drift", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=reverse_engineering_drift\nrollback_focus=eval_reverse_observe\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nReverse-engineering inference is drifting beyond observed artifacts and must be pulled back to bounded observation.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nanalysis_mode=reverse_engineering\nobservation_policy=bounded\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=speculative_reverse_engineering\ndominant_cause_signal=reverse_engineering_speculation\nrequired_rewrite_scope=bounded_observation_first\nforbidden_rewrite_scope=invent_hidden_internals\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "reverse_engineering_speculation", "rewrite_name": "bounded_observation_first", "need_id": 2, "cause_id": 8, "rewrite_id": 7, "preserve_conflict": 1, "minimal_diff": 0, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 1, "fail_closed": 1}, "metadata": {"split": "eval", "variant_rank": 0}}
37
- {"mode": "reverse_engineering_drift", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=reverse_engineering_drift\nrollback_focus=eval_reverse_grounded\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nSpeculative internals appeared during repository analysis and should be rolled back to evidence-grounded structure only.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=minimal\nworkspace_delta=preserved\nrollback_budget=guarded\nspeculation_state=too_high\ngrounding_requirement=observed_only\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=observed_artifacts_insufficient\ndominant_cause_signal=reverse_engineering_speculation\nrequired_rewrite_scope=evidence_grounded_reverse_revision\nforbidden_rewrite_scope=unbounded_architecture_guessing\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "reverse_engineering_speculation", "rewrite_name": "bounded_observation_first", "need_id": 2, "cause_id": 8, "rewrite_id": 7, "preserve_conflict": 1, "minimal_diff": 0, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 1, "fail_closed": 1}, "metadata": {"split": "eval", "variant_rank": 1}}
38
- {"mode": "reverse_engineering_drift", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=reverse_engineering_drift\nrollback_focus=eval_reverse_observe\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nReverse-engineering inference is drifting beyond observed artifacts and must be pulled back to bounded observation.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nanalysis_mode=reverse_engineering\nobservation_policy=bounded\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=speculative_reverse_engineering\ndominant_cause_signal=reverse_engineering_speculation\nrequired_rewrite_scope=bounded_observation_first\nforbidden_rewrite_scope=invent_hidden_internals\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "reverse_engineering_speculation", "rewrite_name": "bounded_observation_first", "need_id": 2, "cause_id": 8, "rewrite_id": 7, "preserve_conflict": 1, "minimal_diff": 0, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 1, "fail_closed": 1}, "metadata": {"split": "eval", "variant_rank": 0}}
39
- {"mode": "reverse_engineering_drift", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=reverse_engineering_drift\nrollback_focus=eval_reverse_grounded\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nSpeculative internals appeared during repository analysis and should be rolled back to evidence-grounded structure only.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=minimal\nworkspace_delta=preserved\nrollback_budget=guarded\nspeculation_state=too_high\ngrounding_requirement=observed_only\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=observed_artifacts_insufficient\ndominant_cause_signal=reverse_engineering_speculation\nrequired_rewrite_scope=evidence_grounded_reverse_revision\nforbidden_rewrite_scope=unbounded_architecture_guessing\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "reverse_engineering_speculation", "rewrite_name": "bounded_observation_first", "need_id": 2, "cause_id": 8, "rewrite_id": 7, "preserve_conflict": 1, "minimal_diff": 0, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 1, "fail_closed": 1}, "metadata": {"split": "eval", "variant_rank": 1}}
40
- {"mode": "reverse_engineering_drift", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=reverse_engineering_drift\nrollback_focus=eval_reverse_observe\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nReverse-engineering inference is drifting beyond observed artifacts and must be pulled back to bounded observation.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nanalysis_mode=reverse_engineering\nobservation_policy=bounded\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=speculative_reverse_engineering\ndominant_cause_signal=reverse_engineering_speculation\nrequired_rewrite_scope=bounded_observation_first\nforbidden_rewrite_scope=invent_hidden_internals\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "required", "cause_name": "reverse_engineering_speculation", "rewrite_name": "bounded_observation_first", "need_id": 2, "cause_id": 8, "rewrite_id": 7, "preserve_conflict": 1, "minimal_diff": 0, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 1, "fail_closed": 1}, "metadata": {"split": "eval", "variant_rank": 0}}
41
- {"mode": "validated_stable", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=validated_stable\nrollback_focus=eval_no_rollback\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nReceipts and validator outputs agree, so rollback should remain inactive.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nvalidator_gate=pass\nrollback_need=none\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=validator_and_receipts_clean\ndominant_cause_signal=none\nrequired_rewrite_scope=do_not_rollback\nforbidden_rewrite_scope=gratuitous_revision\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "none", "cause_name": "none", "rewrite_name": "do_not_rollback", "need_id": 0, "cause_id": 0, "rewrite_id": 0, "preserve_conflict": 0, "minimal_diff": 0, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 0}}
42
- {"mode": "validated_stable", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=validated_stable\nrollback_focus=eval_keep_stable\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nThe worktree is stable and validator-clean, so the current revision should be kept.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=minimal\nworkspace_delta=preserved\nrollback_budget=guarded\nreceipt_alignment=clean\nworkspace_state=stable\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=stable_worktree_and_passed_checks\ndominant_cause_signal=none\nrequired_rewrite_scope=keep_current_revision\nforbidden_rewrite_scope=needless_repair_loop\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "none", "cause_name": "none", "rewrite_name": "do_not_rollback", "need_id": 0, "cause_id": 0, "rewrite_id": 0, "preserve_conflict": 0, "minimal_diff": 0, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 1}}
43
- {"mode": "validated_stable", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=validated_stable\nrollback_focus=eval_no_rollback\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nReceipts and validator outputs agree, so rollback should remain inactive.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nvalidator_gate=pass\nrollback_need=none\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=validator_and_receipts_clean\ndominant_cause_signal=none\nrequired_rewrite_scope=do_not_rollback\nforbidden_rewrite_scope=gratuitous_revision\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "none", "cause_name": "none", "rewrite_name": "do_not_rollback", "need_id": 0, "cause_id": 0, "rewrite_id": 0, "preserve_conflict": 0, "minimal_diff": 0, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 0}}
44
- {"mode": "validated_stable", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=validated_stable\nrollback_focus=eval_keep_stable\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nThe worktree is stable and validator-clean, so the current revision should be kept.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=minimal\nworkspace_delta=preserved\nrollback_budget=guarded\nreceipt_alignment=clean\nworkspace_state=stable\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=stable_worktree_and_passed_checks\ndominant_cause_signal=none\nrequired_rewrite_scope=keep_current_revision\nforbidden_rewrite_scope=needless_repair_loop\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "none", "cause_name": "none", "rewrite_name": "do_not_rollback", "need_id": 0, "cause_id": 0, "rewrite_id": 0, "preserve_conflict": 0, "minimal_diff": 0, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 1}}
45
- {"mode": "validated_stable", "product_line": "veriloop_coder", "prompt": "[HARNESS_ROLLBACK_ENVELOPE]\nproduct_line=veriloop_coder\nplanner_enabled=true\nvalidator_enabled=true\nruntime_protocol=true\nsession_continuity=true\nworktree_discipline=true\npatch_alignment=true\nsandbox_validation=true\ntool_selfcheck_loop=true\nreverse_engineering_mode=bounded\nrule=Prefer minimal-diff rollback over broad regeneration.\nrule=Preserve explicit conflicts rather than silently washing them out.\nrule=Validator feedback, failure routes, patch state, workspace deltas, and rollback receipts are first-class rollback inputs.\nrule=If code was executed and failed validator checks, prefer bounded self-check repair before broad rewrite.\nrule=If reverse engineering is requested, preserve observed structure and receipts instead of inventing hidden internals.\nrollback_mode=validated_stable\nrollback_focus=eval_no_rollback\n[/HARNESS_ROLLBACK_ENVELOPE]\n\n[USER_QUERY]\nReceipts and validator outputs agree, so rollback should remain inactive.\n[/USER_QUERY]\n\n[ROLLBACK_CONTEXT]\nvalidator_receipt_state=current\npatch_scope=bounded\nworkspace_delta=tracked\nrollback_budget=tight\nvalidator_gate=pass\nrollback_need=none\n[/ROLLBACK_CONTEXT]\n\n[ROLLBACK_DECISION_FACTORS]\nobserved_failure_channel=validator_and_receipts_clean\ndominant_cause_signal=none\nrequired_rewrite_scope=do_not_rollback\nforbidden_rewrite_scope=gratuitous_revision\n[/ROLLBACK_DECISION_FACTORS]", "labels": {"need_name": "none", "cause_name": "none", "rewrite_name": "do_not_rollback", "need_id": 0, "cause_id": 0, "rewrite_id": 0, "preserve_conflict": 0, "minimal_diff": 0, "validator_aligned": 1, "session_continuity": 1, "worktree_safe": 1, "selfcheck_route": 0, "reverse_engineering_bounded": 0, "fail_closed": 0}, "metadata": {"split": "eval", "variant_rank": 0}}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
rollback_adapter/rollback_head.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a1bc1ea9910f92a75240db4240a85e3aaf92baa3476a65a8cbbd846ab43f4e4
3
- size 352958879
 
 
 
 
rollback_adapter/rollback_train.jsonl DELETED
The diff for this file is too large to render. See raw diff
 
rollback_adapter/rollback_training_manifest.json DELETED
@@ -1,121 +0,0 @@
1
- {
2
- "adapter_exported": true,
3
- "dataset_summary": {
4
- "cause_vocab": [
5
- "none",
6
- "evidence_contradiction",
7
- "execution_negation",
8
- "validator_rejection",
9
- "patch_regression",
10
- "worktree_conflict",
11
- "high_risk_unsupported",
12
- "tool_selfcheck_failure",
13
- "reverse_engineering_speculation"
14
- ],
15
- "eval_size": 45,
16
- "mode_vocab": [
17
- "contradiction",
18
- "execution_failure",
19
- "validator_rejection",
20
- "patch_regression",
21
- "worktree_conflict",
22
- "high_risk_unsupported",
23
- "tool_selfcheck_repair",
24
- "reverse_engineering_drift",
25
- "validated_stable"
26
- ],
27
- "modes": [
28
- "contradiction",
29
- "execution_failure",
30
- "high_risk_unsupported",
31
- "patch_regression",
32
- "reverse_engineering_drift",
33
- "tool_selfcheck_repair",
34
- "validated_stable",
35
- "validator_rejection",
36
- "worktree_conflict"
37
- ],
38
- "need_vocab": [
39
- "none",
40
- "advisory",
41
- "required"
42
- ],
43
- "rewrite_vocab": [
44
- "do_not_rollback",
45
- "local_patch_only",
46
- "validator_scoped_revision",
47
- "minimum_diff_patch",
48
- "do_not_overwrite_worktree_state",
49
- "fail_closed",
50
- "repair_via_bounded_selfcheck_loop",
51
- "bounded_observation_first",
52
- "local_conflict_preserving_revision"
53
- ],
54
- "train_size": 126
55
- },
56
- "eval_metrics": {
57
- "adapter_exported": true,
58
- "auto_lora_from_ia3": false,
59
- "avg_binary_accuracy": 0.8194444444444444,
60
- "best_epoch": 3,
61
- "best_quality_score": 0.3986773560841878,
62
- "cause_accuracy": 0.4888888888888889,
63
- "count": 45,
64
- "eval_batches": 45,
65
- "eval_loss": 7.656409973568387,
66
- "fail_closed_accuracy": 0.7777777777777778,
67
- "minimal_diff_accuracy": 0.5555555555555556,
68
- "mode_accuracy": 0.3333333333333333,
69
- "need_accuracy": 0.7777777777777778,
70
- "peft_method": "lora_narrow",
71
- "preserve_conflict_accuracy": 0.7777777777777778,
72
- "quality_score": 0.3986773560841878,
73
- "reverse_engineering_bounded_accuracy": 0.8888888888888888,
74
- "rewrite_accuracy": 0.4888888888888889,
75
- "selfcheck_route_accuracy": 0.5555555555555556,
76
- "session_continuity_accuracy": 1.0,
77
- "used_peft": true,
78
- "validator_aligned_accuracy": 1.0,
79
- "worktree_safe_accuracy": 1.0
80
- },
81
- "load_meta": {
82
- "chosen_class": "AutoModelForCausalLM",
83
- "hidden_size": 2048,
84
- "quantization_mode": "4bit"
85
- },
86
- "peft_method": "lora_narrow",
87
- "selected_target_modules": [
88
- "failure_signal_bridge.rollback_bridge",
89
- "rollback_adapter.head",
90
- "runtime_harness_adapter.bridge",
91
- "sandbox_rollback_bridge.adapter",
92
- "toolspec_head.validator_gate",
93
- "validator_feedback_bridge.adapter",
94
- "validator_feedback_loop.rollback_adapter",
95
- "memory_boundary_guard.adapter",
96
- "memory_boundary_guard.rollback_filter",
97
- "request_normalizer.adapter",
98
- "tool_protocol_adapter.bridge",
99
- "toolspec_bridge.adapter",
100
- "toolspec_head.postcondition_adapter",
101
- "toolspec_head.precondition_adapter",
102
- "toolspec_head.receipt_formatter",
103
- "toolspec_head.trigger_gate"
104
- ],
105
- "status": "trained",
106
- "train_metrics": {
107
- "adapter_exported": true,
108
- "auto_lora_from_ia3": false,
109
- "best_epoch": 3,
110
- "best_quality_score": 0.3986773560841878,
111
- "epochs_completed": 4,
112
- "loss": 0.4452953128114579,
113
- "micro_batches": 126,
114
- "micro_batches_total": 504,
115
- "optimizer_steps": 8,
116
- "optimizer_steps_total": 32,
117
- "peft_method": "lora_narrow",
118
- "used_peft": true
119
- },
120
- "used_peft": true
121
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
rollback_adapter/tokenizer/chat_template.jinja DELETED
@@ -1,154 +0,0 @@
1
- {%- set image_count = namespace(value=0) %}
2
- {%- set video_count = namespace(value=0) %}
3
- {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
- {%- if content is string %}
5
- {{- content }}
6
- {%- elif content is iterable and content is not mapping %}
7
- {%- for item in content %}
8
- {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
- {%- if is_system_content %}
10
- {{- raise_exception('System message cannot contain images.') }}
11
- {%- endif %}
12
- {%- if do_vision_count %}
13
- {%- set image_count.value = image_count.value + 1 %}
14
- {%- endif %}
15
- {%- if add_vision_id %}
16
- {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
- {%- endif %}
18
- {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
- {%- elif 'video' in item or item.type == 'video' %}
20
- {%- if is_system_content %}
21
- {{- raise_exception('System message cannot contain videos.') }}
22
- {%- endif %}
23
- {%- if do_vision_count %}
24
- {%- set video_count.value = video_count.value + 1 %}
25
- {%- endif %}
26
- {%- if add_vision_id %}
27
- {{- 'Video ' ~ video_count.value ~ ': ' }}
28
- {%- endif %}
29
- {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
- {%- elif 'text' in item %}
31
- {{- item.text }}
32
- {%- else %}
33
- {{- raise_exception('Unexpected item type in content.') }}
34
- {%- endif %}
35
- {%- endfor %}
36
- {%- elif content is none or content is undefined %}
37
- {{- '' }}
38
- {%- else %}
39
- {{- raise_exception('Unexpected content type.') }}
40
- {%- endif %}
41
- {%- endmacro %}
42
- {%- if not messages %}
43
- {{- raise_exception('No messages provided.') }}
44
- {%- endif %}
45
- {%- if tools and tools is iterable and tools is not mapping %}
46
- {{- '<|im_start|>system\n' }}
47
- {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
48
- {%- for tool in tools %}
49
- {{- "\n" }}
50
- {{- tool | tojson }}
51
- {%- endfor %}
52
- {{- "\n</tools>" }}
53
- {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
54
- {%- if messages[0].role == 'system' %}
55
- {%- set content = render_content(messages[0].content, false, true)|trim %}
56
- {%- if content %}
57
- {{- '\n\n' + content }}
58
- {%- endif %}
59
- {%- endif %}
60
- {{- '<|im_end|>\n' }}
61
- {%- else %}
62
- {%- if messages[0].role == 'system' %}
63
- {%- set content = render_content(messages[0].content, false, true)|trim %}
64
- {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
65
- {%- endif %}
66
- {%- endif %}
67
- {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
68
- {%- for message in messages[::-1] %}
69
- {%- set index = (messages|length - 1) - loop.index0 %}
70
- {%- if ns.multi_step_tool and message.role == "user" %}
71
- {%- set content = render_content(message.content, false)|trim %}
72
- {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
73
- {%- set ns.multi_step_tool = false %}
74
- {%- set ns.last_query_index = index %}
75
- {%- endif %}
76
- {%- endif %}
77
- {%- endfor %}
78
- {%- if ns.multi_step_tool %}
79
- {{- raise_exception('No user query found in messages.') }}
80
- {%- endif %}
81
- {%- for message in messages %}
82
- {%- set content = render_content(message.content, true)|trim %}
83
- {%- if message.role == "system" %}
84
- {%- if not loop.first %}
85
- {{- raise_exception('System message must be at the beginning.') }}
86
- {%- endif %}
87
- {%- elif message.role == "user" %}
88
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
89
- {%- elif message.role == "assistant" %}
90
- {%- set reasoning_content = '' %}
91
- {%- if message.reasoning_content is string %}
92
- {%- set reasoning_content = message.reasoning_content %}
93
- {%- else %}
94
- {%- if '</think>' in content %}
95
- {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
96
- {%- set content = content.split('</think>')[-1].lstrip('\n') %}
97
- {%- endif %}
98
- {%- endif %}
99
- {%- set reasoning_content = reasoning_content|trim %}
100
- {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
101
- {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
102
- {%- else %}
103
- {{- '<|im_start|>' + message.role + '\n' + content }}
104
- {%- endif %}
105
- {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
106
- {%- for tool_call in message.tool_calls %}
107
- {%- if tool_call.function is defined %}
108
- {%- set tool_call = tool_call.function %}
109
- {%- endif %}
110
- {%- if loop.first %}
111
- {%- if content|trim %}
112
- {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
113
- {%- else %}
114
- {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
115
- {%- endif %}
116
- {%- else %}
117
- {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
- {%- endif %}
119
- {%- if tool_call.arguments is defined %}
120
- {%- for args_name, args_value in tool_call.arguments|items %}
121
- {{- '<parameter=' + args_name + '>\n' }}
122
- {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
123
- {{- args_value }}
124
- {{- '\n</parameter>\n' }}
125
- {%- endfor %}
126
- {%- endif %}
127
- {{- '</function>\n</tool_call>' }}
128
- {%- endfor %}
129
- {%- endif %}
130
- {{- '<|im_end|>\n' }}
131
- {%- elif message.role == "tool" %}
132
- {%- if loop.previtem and loop.previtem.role != "tool" %}
133
- {{- '<|im_start|>user' }}
134
- {%- endif %}
135
- {{- '\n<tool_response>\n' }}
136
- {{- content }}
137
- {{- '\n</tool_response>' }}
138
- {%- if not loop.last and loop.nextitem.role != "tool" %}
139
- {{- '<|im_end|>\n' }}
140
- {%- elif loop.last %}
141
- {{- '<|im_end|>\n' }}
142
- {%- endif %}
143
- {%- else %}
144
- {{- raise_exception('Unexpected message role.') }}
145
- {%- endif %}
146
- {%- endfor %}
147
- {%- if add_generation_prompt %}
148
- {{- '<|im_start|>assistant\n' }}
149
- {%- if enable_thinking is defined and enable_thinking is false %}
150
- {{- '<think>\n\n</think>\n\n' }}
151
- {%- else %}
152
- {{- '<think>\n' }}
153
- {%- endif %}
154
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
rollback_adapter/tokenizer/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea2e66b594a0906e9a547c9e6ff9e5fb8a8198439c8cf7d6dc48f23529161223
3
- size 19989442
 
 
 
 
rollback_adapter/tokenizer/tokenizer_config.json DELETED
@@ -1,31 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "audio_bos_token": "<|audio_start|>",
4
- "audio_eos_token": "<|audio_end|>",
5
- "audio_token": "<|audio_pad|>",
6
- "backend": "tokenizers",
7
- "bos_token": null,
8
- "clean_up_tokenization_spaces": false,
9
- "eos_token": "<|im_end|>",
10
- "errors": "replace",
11
- "image_token": "<|image_pad|>",
12
- "is_local": true,
13
- "model_max_length": 262144,
14
- "model_specific_special_tokens": {
15
- "audio_bos_token": "<|audio_start|>",
16
- "audio_eos_token": "<|audio_end|>",
17
- "audio_token": "<|audio_pad|>",
18
- "image_token": "<|image_pad|>",
19
- "video_token": "<|video_pad|>",
20
- "vision_bos_token": "<|vision_start|>",
21
- "vision_eos_token": "<|vision_end|>"
22
- },
23
- "pad_token": "<|endoftext|>",
24
- "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
25
- "split_special_tokens": false,
26
- "tokenizer_class": "TokenizersBackend",
27
- "unk_token": null,
28
- "video_token": "<|video_pad|>",
29
- "vision_bos_token": "<|vision_start|>",
30
- "vision_eos_token": "<|vision_end|>"
31
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
3
- size 12807982
 
 
 
 
tokenizer_config.json DELETED
@@ -1,305 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "248044": {
5
- "content": "<|endoftext|>",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "248045": {
13
- "content": "<|im_start|>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "248046": {
21
- "content": "<|im_end|>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "248047": {
29
- "content": "<|object_ref_start|>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "248048": {
37
- "content": "<|object_ref_end|>",
38
- "lstrip": false,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- },
44
- "248049": {
45
- "content": "<|box_start|>",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": true
51
- },
52
- "248050": {
53
- "content": "<|box_end|>",
54
- "lstrip": false,
55
- "normalized": false,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": true
59
- },
60
- "248051": {
61
- "content": "<|quad_start|>",
62
- "lstrip": false,
63
- "normalized": false,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": true
67
- },
68
- "248052": {
69
- "content": "<|quad_end|>",
70
- "lstrip": false,
71
- "normalized": false,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": true
75
- },
76
- "248053": {
77
- "content": "<|vision_start|>",
78
- "lstrip": false,
79
- "normalized": false,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": true
83
- },
84
- "248054": {
85
- "content": "<|vision_end|>",
86
- "lstrip": false,
87
- "normalized": false,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": true
91
- },
92
- "248055": {
93
- "content": "<|vision_pad|>",
94
- "lstrip": false,
95
- "normalized": false,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": true
99
- },
100
- "248056": {
101
- "content": "<|image_pad|>",
102
- "lstrip": false,
103
- "normalized": false,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": true
107
- },
108
- "248057": {
109
- "content": "<|video_pad|>",
110
- "lstrip": false,
111
- "normalized": false,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": true
115
- },
116
- "248058": {
117
- "content": "<tool_call>",
118
- "lstrip": false,
119
- "normalized": false,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": false
123
- },
124
- "248059": {
125
- "content": "</tool_call>",
126
- "lstrip": false,
127
- "normalized": false,
128
- "rstrip": false,
129
- "single_word": false,
130
- "special": false
131
- },
132
- "248060": {
133
- "content": "<|fim_prefix|>",
134
- "lstrip": false,
135
- "normalized": false,
136
- "rstrip": false,
137
- "single_word": false,
138
- "special": false
139
- },
140
- "248061": {
141
- "content": "<|fim_middle|>",
142
- "lstrip": false,
143
- "normalized": false,
144
- "rstrip": false,
145
- "single_word": false,
146
- "special": false
147
- },
148
- "248062": {
149
- "content": "<|fim_suffix|>",
150
- "lstrip": false,
151
- "normalized": false,
152
- "rstrip": false,
153
- "single_word": false,
154
- "special": false
155
- },
156
- "248063": {
157
- "content": "<|fim_pad|>",
158
- "lstrip": false,
159
- "normalized": false,
160
- "rstrip": false,
161
- "single_word": false,
162
- "special": false
163
- },
164
- "248064": {
165
- "content": "<|repo_name|>",
166
- "lstrip": false,
167
- "normalized": false,
168
- "rstrip": false,
169
- "single_word": false,
170
- "special": false
171
- },
172
- "248065": {
173
- "content": "<|file_sep|>",
174
- "lstrip": false,
175
- "normalized": false,
176
- "rstrip": false,
177
- "single_word": false,
178
- "special": false
179
- },
180
- "248066": {
181
- "content": "<tool_response>",
182
- "lstrip": false,
183
- "normalized": false,
184
- "rstrip": false,
185
- "single_word": false,
186
- "special": false
187
- },
188
- "248067": {
189
- "content": "</tool_response>",
190
- "lstrip": false,
191
- "normalized": false,
192
- "rstrip": false,
193
- "single_word": false,
194
- "special": false
195
- },
196
- "248068": {
197
- "content": "<think>",
198
- "lstrip": false,
199
- "normalized": false,
200
- "rstrip": false,
201
- "single_word": false,
202
- "special": false
203
- },
204
- "248069": {
205
- "content": "</think>",
206
- "lstrip": false,
207
- "normalized": false,
208
- "rstrip": false,
209
- "single_word": false,
210
- "special": false
211
- },
212
- "248070": {
213
- "content": "<|audio_start|>",
214
- "lstrip": false,
215
- "normalized": false,
216
- "rstrip": false,
217
- "single_word": false,
218
- "special": true
219
- },
220
- "248071": {
221
- "content": "<|audio_end|>",
222
- "lstrip": false,
223
- "normalized": false,
224
- "rstrip": false,
225
- "single_word": false,
226
- "special": true
227
- },
228
- "248072": {
229
- "content": "<tts_pad>",
230
- "lstrip": false,
231
- "normalized": false,
232
- "rstrip": false,
233
- "single_word": false,
234
- "special": true
235
- },
236
- "248073": {
237
- "content": "<tts_text_bos>",
238
- "lstrip": false,
239
- "normalized": false,
240
- "rstrip": false,
241
- "single_word": false,
242
- "special": true
243
- },
244
- "248074": {
245
- "content": "<tts_text_eod>",
246
- "lstrip": false,
247
- "normalized": false,
248
- "rstrip": false,
249
- "single_word": false,
250
- "special": true
251
- },
252
- "248075": {
253
- "content": "<tts_text_bos_single>",
254
- "lstrip": false,
255
- "normalized": false,
256
- "rstrip": false,
257
- "single_word": false,
258
- "special": true
259
- },
260
- "248076": {
261
- "content": "<|audio_pad|>",
262
- "lstrip": false,
263
- "normalized": false,
264
- "rstrip": false,
265
- "single_word": false,
266
- "special": true
267
- }
268
- },
269
- "additional_special_tokens": [
270
- "<|im_start|>",
271
- "<|im_end|>",
272
- "<|object_ref_start|>",
273
- "<|object_ref_end|>",
274
- "<|box_start|>",
275
- "<|box_end|>",
276
- "<|quad_start|>",
277
- "<|quad_end|>",
278
- "<|vision_start|>",
279
- "<|vision_end|>",
280
- "<|vision_pad|>",
281
- "<|image_pad|>",
282
- "<|video_pad|>"
283
- ],
284
- "bos_token": null,
285
- "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '\\n\\n' + content }}\n {%- endif %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"system\" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\n {%- elif message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- else %}\n {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is defined %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- else %}\n {{- raise_exception('Unexpected message role.') }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- else %}\n {{- '<think>\\n' }}\n {%- endif %}\n{%- endif %}",
286
- "clean_up_tokenization_spaces": false,
287
- "eos_token": "<|im_end|>",
288
- "errors": "replace",
289
- "model_max_length": 262144,
290
- "pad_token": "<|endoftext|>",
291
- "split_special_tokens": false,
292
- "tokenizer_class": "Qwen2Tokenizer",
293
- "unk_token": null,
294
- "add_bos_token": false,
295
- "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
296
- "extra_special_tokens": {
297
- "audio_bos_token": "<|audio_start|>",
298
- "audio_eos_token": "<|audio_end|>",
299
- "audio_token": "<|audio_pad|>",
300
- "image_token": "<|image_pad|>",
301
- "video_token": "<|video_pad|>",
302
- "vision_bos_token": "<|vision_start|>",
303
- "vision_eos_token": "<|vision_end|>"
304
- }
305
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
toolspec_adapter/.gitkeep DELETED
@@ -1 +0,0 @@
1
- placeholder
 
 
toolspec_adapter/adapter/README.md DELETED
@@ -1,203 +0,0 @@
1
- ---
2
- library_name: peft
3
- tags:
4
- - lora
5
- ---
6
-
7
- # Model Card for Model ID
8
-
9
- <!-- Provide a quick summary of what the model is/does. -->
10
-
11
-
12
-
13
- ## Model Details
14
-
15
- ### Model Description
16
-
17
- <!-- Provide a longer summary of what this model is. -->
18
-
19
-
20
-
21
- - **Developed by:** [More Information Needed]
22
- - **Funded by [optional]:** [More Information Needed]
23
- - **Shared by [optional]:** [More Information Needed]
24
- - **Model type:** [More Information Needed]
25
- - **Language(s) (NLP):** [More Information Needed]
26
- - **License:** [More Information Needed]
27
- - **Finetuned from model [optional]:** [More Information Needed]
28
-
29
- ### Model Sources [optional]
30
-
31
- <!-- Provide the basic links for the model. -->
32
-
33
- - **Repository:** [More Information Needed]
34
- - **Paper [optional]:** [More Information Needed]
35
- - **Demo [optional]:** [More Information Needed]
36
-
37
- ## Uses
38
-
39
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
40
-
41
- ### Direct Use
42
-
43
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
44
-
45
- [More Information Needed]
46
-
47
- ### Downstream Use [optional]
48
-
49
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
50
-
51
- [More Information Needed]
52
-
53
- ### Out-of-Scope Use
54
-
55
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
56
-
57
- [More Information Needed]
58
-
59
- ## Bias, Risks, and Limitations
60
-
61
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
62
-
63
- [More Information Needed]
64
-
65
- ### Recommendations
66
-
67
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
68
-
69
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
70
-
71
- ## How to Get Started with the Model
72
-
73
- Use the code below to get started with the model.
74
-
75
- [More Information Needed]
76
-
77
- ## Training Details
78
-
79
- ### Training Data
80
-
81
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
82
-
83
- [More Information Needed]
84
-
85
- ### Training Procedure
86
-
87
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
88
-
89
- #### Preprocessing [optional]
90
-
91
- [More Information Needed]
92
-
93
-
94
- #### Training Hyperparameters
95
-
96
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
97
-
98
- #### Speeds, Sizes, Times [optional]
99
-
100
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
101
-
102
- [More Information Needed]
103
-
104
- ## Evaluation
105
-
106
- <!-- This section describes the evaluation protocols and provides the results. -->
107
-
108
- ### Testing Data, Factors & Metrics
109
-
110
- #### Testing Data
111
-
112
- <!-- This should link to a Dataset Card if possible. -->
113
-
114
- [More Information Needed]
115
-
116
- #### Factors
117
-
118
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
119
-
120
- [More Information Needed]
121
-
122
- #### Metrics
123
-
124
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
125
-
126
- [More Information Needed]
127
-
128
- ### Results
129
-
130
- [More Information Needed]
131
-
132
- #### Summary
133
-
134
-
135
-
136
- ## Model Examination [optional]
137
-
138
- <!-- Relevant interpretability work for the model goes here -->
139
-
140
- [More Information Needed]
141
-
142
- ## Environmental Impact
143
-
144
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
145
-
146
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
147
-
148
- - **Hardware Type:** [More Information Needed]
149
- - **Hours used:** [More Information Needed]
150
- - **Cloud Provider:** [More Information Needed]
151
- - **Compute Region:** [More Information Needed]
152
- - **Carbon Emitted:** [More Information Needed]
153
-
154
- ## Technical Specifications [optional]
155
-
156
- ### Model Architecture and Objective
157
-
158
- [More Information Needed]
159
-
160
- ### Compute Infrastructure
161
-
162
- [More Information Needed]
163
-
164
- #### Hardware
165
-
166
- [More Information Needed]
167
-
168
- #### Software
169
-
170
- [More Information Needed]
171
-
172
- ## Citation [optional]
173
-
174
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
175
-
176
- **BibTeX:**
177
-
178
- [More Information Needed]
179
-
180
- **APA:**
181
-
182
- [More Information Needed]
183
-
184
- ## Glossary [optional]
185
-
186
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
187
-
188
- [More Information Needed]
189
-
190
- ## More Information [optional]
191
-
192
- [More Information Needed]
193
-
194
- ## Model Card Authors [optional]
195
-
196
- [More Information Needed]
197
-
198
- ## Model Card Contact
199
-
200
- [More Information Needed]
201
- ### Framework versions
202
-
203
- - PEFT 0.19.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
toolspec_adapter/adapter/adapter_config.json DELETED
@@ -1,52 +0,0 @@
1
- {
2
- "alora_invocation_tokens": null,
3
- "alpha_pattern": {},
4
- "arrow_config": null,
5
- "auto_mapping": null,
6
- "base_model_name_or_path": null,
7
- "bias": "none",
8
- "corda_config": null,
9
- "ensure_weight_tying": false,
10
- "eva_config": null,
11
- "exclude_modules": null,
12
- "fan_in_fan_out": false,
13
- "inference_mode": true,
14
- "init_lora_weights": true,
15
- "layer_replication": null,
16
- "layers_pattern": null,
17
- "layers_to_transform": null,
18
- "loftq_config": {},
19
- "lora_alpha": 16,
20
- "lora_bias": false,
21
- "lora_dropout": 0.05,
22
- "lora_ga_config": null,
23
- "megatron_config": null,
24
- "megatron_core": "megatron.core",
25
- "modules_to_save": null,
26
- "peft_type": "LORA",
27
- "peft_version": "0.19.0",
28
- "qalora_group_size": 16,
29
- "r": 8,
30
- "rank_pattern": {},
31
- "revision": null,
32
- "target_modules": [
33
- "surface_host.toolspec_bridge.adapter",
34
- "surface_host.validator_feedback_bridge.adapter",
35
- "surface_host.toolspec_head.receipt_formatter",
36
- "surface_host.toolspec_head.precondition_adapter",
37
- "surface_host.toolspec_head.validator_gate",
38
- "surface_host.toolspec_head.postcondition_adapter",
39
- "surface_host.tool_protocol_adapter.bridge",
40
- "surface_host.runtime_harness_adapter.bridge",
41
- "surface_host.toolspec_head.trigger_gate",
42
- "surface_host.request_normalizer.adapter",
43
- "surface_host.toolspec_head.param_schema_adapter"
44
- ],
45
- "target_parameters": null,
46
- "task_type": "FEATURE_EXTRACTION",
47
- "trainable_token_indices": null,
48
- "use_bdlora": null,
49
- "use_dora": false,
50
- "use_qalora": false,
51
- "use_rslora": false
52
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
toolspec_adapter/adapter/adapter_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e62775d0cd91a0604b237b7d50cdb1da249ec85e8f9a2c6ad4fd7ed8afc805a2
3
- size 724048
 
 
 
 
toolspec_adapter/best_checkpoint_manifest.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "best_epoch": 4,
3
- "best_quality_score": 0.46349615617231893,
4
- "eval_metrics": {
5
- "avg_binary_accuracy": 0.81,
6
- "confirmation_required_accuracy": 0.8,
7
- "count": 25,
8
- "eval_batches": 25,
9
- "eval_loss": 6.897225952148437,
10
- "mode_accuracy": 0.56,
11
- "permission_bit_accuracy": 0.8545454545454545,
12
- "precondition_ok_accuracy": 0.76,
13
- "quality_score": 0.46349615617231893,
14
- "rollback_supported_accuracy": 0.8,
15
- "schema_ok_accuracy": 0.76,
16
- "session_required_accuracy": 1.0,
17
- "tool_accuracy": 0.44,
18
- "trigger_accuracy": 0.76,
19
- "validator_required_accuracy": 0.8,
20
- "worktree_required_accuracy": 0.8
21
- },
22
- "train_metrics": {
23
- "loss": 0.42175399448190415,
24
- "micro_batches": 70,
25
- "optimizer_steps": 5
26
- }
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
toolspec_adapter/epoch_history.json DELETED
@@ -1,144 +0,0 @@
1
- {
2
- "epochs": [
3
- {
4
- "epoch": 1,
5
- "eval_metrics": {
6
- "avg_binary_accuracy": 0.795,
7
- "confirmation_required_accuracy": 0.8,
8
- "count": 25,
9
- "eval_batches": 25,
10
- "eval_loss": 7.704372234344483,
11
- "mode_accuracy": 0.44,
12
- "permission_bit_accuracy": 0.850909090909091,
13
- "precondition_ok_accuracy": 0.76,
14
- "quality_score": 0.21877532557574186,
15
- "rollback_supported_accuracy": 0.72,
16
- "schema_ok_accuracy": 0.76,
17
- "session_required_accuracy": 1.0,
18
- "tool_accuracy": 0.24,
19
- "trigger_accuracy": 0.76,
20
- "validator_required_accuracy": 0.8,
21
- "worktree_required_accuracy": 0.76
22
- },
23
- "improved": true,
24
- "quality_score": 0.21877532557574186,
25
- "train_metrics": {
26
- "loss": 0.5388983534915107,
27
- "micro_batches": 70,
28
- "optimizer_steps": 5
29
- }
30
- },
31
- {
32
- "epoch": 2,
33
- "eval_metrics": {
34
- "avg_binary_accuracy": 0.81,
35
- "confirmation_required_accuracy": 0.8,
36
- "count": 25,
37
- "eval_batches": 25,
38
- "eval_loss": 7.129253711700439,
39
- "mode_accuracy": 0.48,
40
- "permission_bit_accuracy": 0.8545454545454545,
41
- "precondition_ok_accuracy": 0.76,
42
- "quality_score": 0.4400157397790389,
43
- "rollback_supported_accuracy": 0.8,
44
- "schema_ok_accuracy": 0.76,
45
- "session_required_accuracy": 1.0,
46
- "tool_accuracy": 0.44,
47
- "trigger_accuracy": 0.76,
48
- "validator_required_accuracy": 0.8,
49
- "worktree_required_accuracy": 0.8
50
- },
51
- "improved": true,
52
- "quality_score": 0.4400157397790389,
53
- "train_metrics": {
54
- "loss": 0.4655745736190251,
55
- "micro_batches": 70,
56
- "optimizer_steps": 5
57
- }
58
- },
59
- {
60
- "epoch": 3,
61
- "eval_metrics": {
62
- "avg_binary_accuracy": 0.81,
63
- "confirmation_required_accuracy": 0.8,
64
- "count": 25,
65
- "eval_batches": 25,
66
- "eval_loss": 6.935494079589843,
67
- "mode_accuracy": 0.48,
68
- "permission_bit_accuracy": 0.8545454545454545,
69
- "precondition_ok_accuracy": 0.76,
70
- "quality_score": 0.4229221342606978,
71
- "rollback_supported_accuracy": 0.8,
72
- "schema_ok_accuracy": 0.76,
73
- "session_required_accuracy": 1.0,
74
- "tool_accuracy": 0.4,
75
- "trigger_accuracy": 0.76,
76
- "validator_required_accuracy": 0.8,
77
- "worktree_required_accuracy": 0.8
78
- },
79
- "improved": false,
80
- "quality_score": 0.4229221342606978,
81
- "train_metrics": {
82
- "loss": 0.43205853487764084,
83
- "micro_batches": 70,
84
- "optimizer_steps": 5
85
- }
86
- },
87
- {
88
- "epoch": 4,
89
- "eval_metrics": {
90
- "avg_binary_accuracy": 0.81,
91
- "confirmation_required_accuracy": 0.8,
92
- "count": 25,
93
- "eval_batches": 25,
94
- "eval_loss": 6.897225952148437,
95
- "mode_accuracy": 0.56,
96
- "permission_bit_accuracy": 0.8545454545454545,
97
- "precondition_ok_accuracy": 0.76,
98
- "quality_score": 0.46349615617231893,
99
- "rollback_supported_accuracy": 0.8,
100
- "schema_ok_accuracy": 0.76,
101
- "session_required_accuracy": 1.0,
102
- "tool_accuracy": 0.44,
103
- "trigger_accuracy": 0.76,
104
- "validator_required_accuracy": 0.8,
105
- "worktree_required_accuracy": 0.8
106
- },
107
- "improved": true,
108
- "quality_score": 0.46349615617231893,
109
- "train_metrics": {
110
- "loss": 0.42175399448190415,
111
- "micro_batches": 70,
112
- "optimizer_steps": 5
113
- }
114
- },
115
- {
116
- "epoch": 5,
117
- "eval_metrics": {
118
- "avg_binary_accuracy": 0.81,
119
- "confirmation_required_accuracy": 0.8,
120
- "count": 25,
121
- "eval_batches": 25,
122
- "eval_loss": 6.89590030670166,
123
- "mode_accuracy": 0.56,
124
- "permission_bit_accuracy": 0.8545454545454545,
125
- "precondition_ok_accuracy": 0.76,
126
- "quality_score": 0.4635160408540206,
127
- "rollback_supported_accuracy": 0.8,
128
- "schema_ok_accuracy": 0.76,
129
- "session_required_accuracy": 1.0,
130
- "tool_accuracy": 0.44,
131
- "trigger_accuracy": 0.76,
132
- "validator_required_accuracy": 0.8,
133
- "worktree_required_accuracy": 0.8
134
- },
135
- "improved": false,
136
- "quality_score": 0.4635160408540206,
137
- "train_metrics": {
138
- "loss": 0.4198248211826597,
139
- "micro_batches": 70,
140
- "optimizer_steps": 5
141
- }
142
- }
143
- ]
144
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
toolspec_adapter/host_manifest.json DELETED
@@ -1,238 +0,0 @@
1
- {
2
- "hidden_size": 2048,
3
- "host_config": {
4
- "attn_implementation": null,
5
- "backbone_name_or_path": "/public/wang_libo/veriloop_coder_e1/model",
6
- "device_map": null,
7
- "dtype": null,
8
- "evidence_rank_hint": 8,
9
- "expose_backbone_inventory": false,
10
- "freeze_backbone": true,
11
- "hidden_size_override": 2048,
12
- "host_dropout": 0.0,
13
- "identity_rank_hint": 8,
14
- "load_backbone_weights": false,
15
- "local_files_only": true,
16
- "low_cpu_mem_usage": true,
17
- "memory_rank_hint": 4,
18
- "rollback_rank_hint": 8,
19
- "runtime_rank_hint": 8,
20
- "toolspec_rank_hint": 8,
21
- "trust_remote_code": true,
22
- "uncertainty_rank_hint": 8,
23
- "use_safetensors": null,
24
- "validator_rank_hint": 8
25
- },
26
- "load_result": {
27
- "has_base_config": true,
28
- "has_base_model": true,
29
- "hidden_size": 2048,
30
- "notes": [
31
- "class=AutoModelForCausalLM",
32
- "quant=4bit"
33
- ],
34
- "source": "trainer_qwen36_loader"
35
- },
36
- "peft_named_modules": [
37
- "claim_extractor",
38
- "claim_extractor.adapter",
39
- "dropout",
40
- "episodic_memory",
41
- "episodic_memory.adapter",
42
- "evidence_binding",
43
- "evidence_binding.adapter",
44
- "failure_signal_bridge",
45
- "failure_signal_bridge.rollback_bridge",
46
- "identity_adapter",
47
- "identity_adapter.bridge",
48
- "identity_guard",
49
- "identity_guard.adapter",
50
- "input_norm",
51
- "memory_boundary_guard",
52
- "memory_boundary_guard.adapter",
53
- "memory_boundary_guard.rollback_filter",
54
- "patch_binding",
55
- "patch_binding.adapter",
56
- "permission_context_manager",
57
- "permission_context_manager.adapter",
58
- "progress_state_tracker",
59
- "progress_state_tracker.adapter",
60
- "progress_state_tracker.rollback_memory",
61
- "proof_carrying_hints",
62
- "proof_carrying_hints.bridge",
63
- "provenance_binding",
64
- "provenance_binding.adapter",
65
- "public_identity_head",
66
- "public_identity_head.proj",
67
- "query_runtime_engine",
68
- "query_runtime_engine.adapter",
69
- "request_normalizer",
70
- "request_normalizer.adapter",
71
- "request_normalizer.adapter.base_layer",
72
- "request_normalizer.adapter.lora_A",
73
- "request_normalizer.adapter.lora_A.default",
74
- "request_normalizer.adapter.lora_B",
75
- "request_normalizer.adapter.lora_B.default",
76
- "request_normalizer.adapter.lora_dropout",
77
- "request_normalizer.adapter.lora_dropout.default",
78
- "request_normalizer.adapter.lora_embedding_A",
79
- "request_normalizer.adapter.lora_embedding_B",
80
- "request_normalizer.adapter.lora_magnitude_vector",
81
- "rollback_adapter",
82
- "rollback_adapter.head",
83
- "rollback_engine",
84
- "rollback_engine.adapter",
85
- "runtime_binding",
86
- "runtime_binding.adapter",
87
- "runtime_harness_adapter",
88
- "runtime_harness_adapter.bridge",
89
- "runtime_harness_adapter.bridge.base_layer",
90
- "runtime_harness_adapter.bridge.lora_A",
91
- "runtime_harness_adapter.bridge.lora_A.default",
92
- "runtime_harness_adapter.bridge.lora_B",
93
- "runtime_harness_adapter.bridge.lora_B.default",
94
- "runtime_harness_adapter.bridge.lora_dropout",
95
- "runtime_harness_adapter.bridge.lora_dropout.default",
96
- "runtime_harness_adapter.bridge.lora_embedding_A",
97
- "runtime_harness_adapter.bridge.lora_embedding_B",
98
- "runtime_harness_adapter.bridge.lora_magnitude_vector",
99
- "runtime_harness_uncertainty_bridge",
100
- "runtime_harness_uncertainty_bridge.adapter",
101
- "sandbox_rollback_bridge",
102
- "sandbox_rollback_bridge.adapter",
103
- "session_compactor",
104
- "session_compactor.adapter",
105
- "session_state_manager",
106
- "session_state_manager.adapter",
107
- "session_state_manager.rollback_state",
108
- "tool_protocol_adapter",
109
- "tool_protocol_adapter.bridge",
110
- "tool_protocol_adapter.bridge.base_layer",
111
- "tool_protocol_adapter.bridge.lora_A",
112
- "tool_protocol_adapter.bridge.lora_A.default",
113
- "tool_protocol_adapter.bridge.lora_B",
114
- "tool_protocol_adapter.bridge.lora_B.default",
115
- "tool_protocol_adapter.bridge.lora_dropout",
116
- "tool_protocol_adapter.bridge.lora_dropout.default",
117
- "tool_protocol_adapter.bridge.lora_embedding_A",
118
- "tool_protocol_adapter.bridge.lora_embedding_B",
119
- "tool_protocol_adapter.bridge.lora_magnitude_vector",
120
- "toolspec_bridge",
121
- "toolspec_bridge.adapter",
122
- "toolspec_bridge.adapter.base_layer",
123
- "toolspec_bridge.adapter.lora_A",
124
- "toolspec_bridge.adapter.lora_A.default",
125
- "toolspec_bridge.adapter.lora_B",
126
- "toolspec_bridge.adapter.lora_B.default",
127
- "toolspec_bridge.adapter.lora_dropout",
128
- "toolspec_bridge.adapter.lora_dropout.default",
129
- "toolspec_bridge.adapter.lora_embedding_A",
130
- "toolspec_bridge.adapter.lora_embedding_B",
131
- "toolspec_bridge.adapter.lora_magnitude_vector",
132
- "toolspec_head",
133
- "toolspec_head.param_schema_adapter",
134
- "toolspec_head.param_schema_adapter.base_layer",
135
- "toolspec_head.param_schema_adapter.lora_A",
136
- "toolspec_head.param_schema_adapter.lora_A.default",
137
- "toolspec_head.param_schema_adapter.lora_B",
138
- "toolspec_head.param_schema_adapter.lora_B.default",
139
- "toolspec_head.param_schema_adapter.lora_dropout",
140
- "toolspec_head.param_schema_adapter.lora_dropout.default",
141
- "toolspec_head.param_schema_adapter.lora_embedding_A",
142
- "toolspec_head.param_schema_adapter.lora_embedding_B",
143
- "toolspec_head.param_schema_adapter.lora_magnitude_vector",
144
- "toolspec_head.postcondition_adapter",
145
- "toolspec_head.postcondition_adapter.base_layer",
146
- "toolspec_head.postcondition_adapter.lora_A",
147
- "toolspec_head.postcondition_adapter.lora_A.default",
148
- "toolspec_head.postcondition_adapter.lora_B",
149
- "toolspec_head.postcondition_adapter.lora_B.default",
150
- "toolspec_head.postcondition_adapter.lora_dropout",
151
- "toolspec_head.postcondition_adapter.lora_dropout.default",
152
- "toolspec_head.postcondition_adapter.lora_embedding_A",
153
- "toolspec_head.postcondition_adapter.lora_embedding_B",
154
- "toolspec_head.postcondition_adapter.lora_magnitude_vector",
155
- "toolspec_head.precondition_adapter",
156
- "toolspec_head.precondition_adapter.base_layer",
157
- "toolspec_head.precondition_adapter.lora_A",
158
- "toolspec_head.precondition_adapter.lora_A.default",
159
- "toolspec_head.precondition_adapter.lora_B",
160
- "toolspec_head.precondition_adapter.lora_B.default",
161
- "toolspec_head.precondition_adapter.lora_dropout",
162
- "toolspec_head.precondition_adapter.lora_dropout.default",
163
- "toolspec_head.precondition_adapter.lora_embedding_A",
164
- "toolspec_head.precondition_adapter.lora_embedding_B",
165
- "toolspec_head.precondition_adapter.lora_magnitude_vector",
166
- "toolspec_head.receipt_formatter",
167
- "toolspec_head.receipt_formatter.base_layer",
168
- "toolspec_head.receipt_formatter.lora_A",
169
- "toolspec_head.receipt_formatter.lora_A.default",
170
- "toolspec_head.receipt_formatter.lora_B",
171
- "toolspec_head.receipt_formatter.lora_B.default",
172
- "toolspec_head.receipt_formatter.lora_dropout",
173
- "toolspec_head.receipt_formatter.lora_dropout.default",
174
- "toolspec_head.receipt_formatter.lora_embedding_A",
175
- "toolspec_head.receipt_formatter.lora_embedding_B",
176
- "toolspec_head.receipt_formatter.lora_magnitude_vector",
177
- "toolspec_head.trigger_gate",
178
- "toolspec_head.trigger_gate.base_layer",
179
- "toolspec_head.trigger_gate.lora_A",
180
- "toolspec_head.trigger_gate.lora_A.default",
181
- "toolspec_head.trigger_gate.lora_B",
182
- "toolspec_head.trigger_gate.lora_B.default",
183
- "toolspec_head.trigger_gate.lora_dropout",
184
- "toolspec_head.trigger_gate.lora_dropout.default",
185
- "toolspec_head.trigger_gate.lora_embedding_A",
186
- "toolspec_head.trigger_gate.lora_embedding_B",
187
- "toolspec_head.trigger_gate.lora_magnitude_vector",
188
- "toolspec_head.validator_gate",
189
- "toolspec_head.validator_gate.base_layer",
190
- "toolspec_head.validator_gate.lora_A",
191
- "toolspec_head.validator_gate.lora_A.default",
192
- "toolspec_head.validator_gate.lora_B",
193
- "toolspec_head.validator_gate.lora_B.default",
194
- "toolspec_head.validator_gate.lora_dropout",
195
- "toolspec_head.validator_gate.lora_dropout.default",
196
- "toolspec_head.validator_gate.lora_embedding_A",
197
- "toolspec_head.validator_gate.lora_embedding_B",
198
- "toolspec_head.validator_gate.lora_magnitude_vector",
199
- "uncertainty_head",
200
- "uncertainty_head.calibration_mlp",
201
- "uncertainty_head.proj",
202
- "validator_feedback_bridge",
203
- "validator_feedback_bridge.adapter",
204
- "validator_feedback_bridge.adapter.base_layer",
205
- "validator_feedback_bridge.adapter.lora_A",
206
- "validator_feedback_bridge.adapter.lora_A.default",
207
- "validator_feedback_bridge.adapter.lora_B",
208
- "validator_feedback_bridge.adapter.lora_B.default",
209
- "validator_feedback_bridge.adapter.lora_dropout",
210
- "validator_feedback_bridge.adapter.lora_dropout.default",
211
- "validator_feedback_bridge.adapter.lora_embedding_A",
212
- "validator_feedback_bridge.adapter.lora_embedding_B",
213
- "validator_feedback_bridge.adapter.lora_magnitude_vector",
214
- "validator_feedback_loop",
215
- "validator_feedback_loop.rollback_adapter",
216
- "validator_receipt_bridge",
217
- "validator_receipt_bridge.adapter",
218
- "validator_uncertainty_bridge",
219
- "validator_uncertainty_bridge.adapter",
220
- "workspace_snapshot_manager",
221
- "workspace_snapshot_manager.rollback_context",
222
- "worktree_binding",
223
- "worktree_binding.adapter",
224
- "worktree_manager",
225
- "worktree_manager.adapter"
226
- ],
227
- "trainable_parameter_report": {
228
- "backbone_frozen": true,
229
- "backbone_present": true,
230
- "hidden_size": 2048,
231
- "host_parameters": 176621573,
232
- "host_trainable_parameters": 360448,
233
- "total_parameters": 34132679301,
234
- "trainable_parameters": 360448,
235
- "version": "veriloop.coder_peft_host.v1"
236
- },
237
- "version": "veriloop.coder_peft_host.v1"
238
- }