Skip to content

wanghai-tech / hikoon-ACR

Go to a project
Toggle navigation
Toggle navigation pinning
Commit 015e3261 015e3261ebda5f73356df75e52100bc4bcbd917a by cnb.bofCdSsphPA
Options

Freeze a live blocker matrix for semantic extraction jobs 

Constraint: The current container still lacks mounted source audio and the semantic model runtimes, so repeated manual spot-checks are noisy and wasteful.
Rejected: Ad-hoc one-job validation only | It would not show whether failures are contract-wide or model-specific.
Confidence: high
Scope-risk: narrow
Directive: Re-run the matrix before claiming any semantic worker progress so blocker drift across MERT/MuQ/ECAPA is visible.
Tested: /usr/local/miniconda3/bin/python -m py_compile scripts/run_phase1_embedding_preflight_matrix_live.py; git diff --check; /usr/local/miniconda3/bin/python scripts/run_phase1_embedding_preflight_matrix_live.py --dsn 'postgres://d2:d2pass@127.0.0.1:5432/d2' --schema acr_test --output data/pgvector_eval/music20/phase1_embedding_preflight_matrix_report.json
Not-tested: This matrix still cannot prove successful semantic inference until assets and runtime dependencies are available.
1 parent 399db601
Inline Side-by-side
Showing 9 changed files with 1293 additions and 0 deletions
1 {
2 "worker": "run_embedding_job",
3 "schema": "acr_test",
4 "job": {
5 "extraction_job_id": 2,
6 "feature_set_id": 3,
7 "target_scope": "reference_set:phase1_hot_reference_v1",
8 "job_status": "pending",
9 "shard_key": "phase1/reference/mert/v1-95m/5s_2.5s",
10 "job_metadata": {
11 "lane": "semantic",
12 "role": "primary_baseline",
13 "phase": "phase1"
14 },
15 "feature_name": "semantic_embedding",
16 "feature_level": "window",
17 "extraction_granularity": "sliding_window",
18 "window_sec": 5.0,
19 "hop_sec": 2.5,
20 "embedding_dim": 768,
21 "distance_metric": "cosine",
22 "feature_config": {
23 "role": "primary_semantic_baseline"
24 },
25 "model_id": 3,
26 "model_name": "mert",
27 "model_version": "v1-95m",
28 "model_family": "music_ssl",
29 "input_sample_rate": 24000,
30 "output_embedding_dim": 768,
31 "model_metadata": {
32 "lane": "semantic",
33 "role": "primary_baseline",
34 "phase": "phase1"
35 }
36 },
37 "target_scope_summary": {
38 "scope_type": "reference_set",
39 "scope_value": "phase1_hot_reference_v1",
40 "reference_set_id": 2,
41 "reference_set_name": "phase1_hot_reference_v1",
42 "recording_count": 20,
43 "ready_asset_count": 20,
44 "active_window_count": 20
45 },
46 "scope_window_count": 20,
47 "status_after_start": {
48 "extraction_job_id": 2,
49 "job_status": "running",
50 "input_count": 20,
51 "output_count": null,
52 "started_at": "2026-06-04T13:52:49.952665+08:00",
53 "finished_at": null,
54 "log_uri": null,
55 "metadata_json": {
56 "lane": "semantic",
57 "role": "primary_baseline",
58 "phase": "phase1",
59 "worker": "run_embedding_job",
60 "dry_run": false,
61 "vector_table": "audio_embedding_vector_768",
62 "output_target": "audio_embedding",
63 "execution_mode": "preflight",
64 "runtime_report": {
65 "ready": false,
66 "model_name": "mert",
67 "availability": {
68 "numpy": true,
69 "torch": false,
70 "torchaudio": false,
71 "transformers": false
72 },
73 "requirements": [
74 "numpy",
75 "torch",
76 "torchaudio",
77 "transformers"
78 ],
79 "missing_dependencies": [
80 "torch",
81 "torchaudio",
82 "transformers"
83 ]
84 },
85 "scope_window_count": 20,
86 "vector_table_report": {
87 "reason": null,
88 "resolved": true,
89 "expected_dim": 768,
90 "table_exists": true,
91 "allowed_vector_tables": [
92 "audio_embedding_vector_192",
93 "audio_embedding_vector_768"
94 ],
95 "requested_vector_table": "audio_embedding_vector_768"
96 },
97 "target_scope_summary": {
98 "scope_type": "reference_set",
99 "scope_value": "phase1_hot_reference_v1",
100 "recording_count": 20,
101 "reference_set_id": 2,
102 "ready_asset_count": 20,
103 "reference_set_name": "phase1_hot_reference_v1",
104 "active_window_count": 20
105 }
106 }
107 },
108 "status_after_complete": null,
109 "status_after_failed": {
110 "extraction_job_id": 2,
111 "job_status": "failed",
112 "input_count": 20,
113 "output_count": 0,
114 "started_at": "2026-06-04T13:52:49.952665+08:00",
115 "finished_at": "2026-06-04T13:52:49.954302+08:00",
116 "log_uri": null,
117 "metadata_json": {
118 "lane": "semantic",
119 "role": "primary_baseline",
120 "phase": "phase1",
121 "worker": "run_embedding_job",
122 "dry_run": false,
123 "artifact_dir": "data/pgvector_eval/music20/phase1_embeddings",
124 "vector_table": "audio_embedding_vector_768",
125 "output_target": "audio_embedding",
126 "execution_mode": "preflight_failure",
127 "failure_reason": "preflight_failed",
128 "runtime_report": {
129 "ready": false,
130 "model_name": "mert",
131 "availability": {
132 "numpy": true,
133 "torch": false,
134 "torchaudio": false,
135 "transformers": false
136 },
137 "requirements": [
138 "numpy",
139 "torch",
140 "torchaudio",
141 "transformers"
142 ],
143 "missing_dependencies": [
144 "torch",
145 "torchaudio",
146 "transformers"
147 ]
148 },
149 "preflight_blockers": [
150 "unreadable_audio_assets",
151 "model_runtime_unavailable"
152 ],
153 "scope_window_count": 20,
154 "write_target_table": "audio_embedding",
155 "vector_table_report": {
156 "reason": null,
157 "resolved": true,
158 "expected_dim": 768,
159 "table_exists": true,
160 "allowed_vector_tables": [
161 "audio_embedding_vector_192",
162 "audio_embedding_vector_768"
163 ],
164 "requested_vector_table": "audio_embedding_vector_768"
165 },
166 "missing_window_count": 20,
167 "target_scope_summary": {
168 "scope_type": "reference_set",
169 "scope_value": "phase1_hot_reference_v1",
170 "recording_count": 20,
171 "reference_set_id": 2,
172 "ready_asset_count": 20,
173 "reference_set_name": "phase1_hot_reference_v1",
174 "active_window_count": 20
175 },
176 "missing_window_samples": [
177 {
178 "reason": "missing_audio",
179 "asset_id": 1,
180 "window_id": 1,
181 "storage_uri": "/workspace/downloads/100/type_11/93dfdeb0-7da5-42a8-9c71-cf12af57dd191650256918.wav"
182 },
183 {
184 "reason": "missing_audio",
185 "asset_id": 2,
186 "window_id": 2,
187 "storage_uri": "/workspace/downloads/101/type_11/83c0c07f-4f96-4ff4-998c-58db910f3cfa1650256915.wav"
188 },
189 {
190 "reason": "missing_audio",
191 "asset_id": 3,
192 "window_id": 3,
193 "storage_uri": "/workspace/downloads/102/type_11/43440ec5-70b4-4d50-8683-d3e41cad29411650256908.wav"
194 },
195 {
196 "reason": "missing_audio",
197 "asset_id": 4,
198 "window_id": 4,
199 "storage_uri": "/workspace/downloads/103/type_11/19876dbb-fffc-40f8-9530-9322c9ed77681650256912.wav"
200 },
201 {
202 "reason": "missing_audio",
203 "asset_id": 5,
204 "window_id": 5,
205 "storage_uri": "/workspace/downloads/104/type_11/4c1d3e22-045f-445b-ab87-ba1ae3ee09b31650256912.wav"
206 }
207 ]
208 }
209 },
210 "resolved_vector_table": "audio_embedding_vector_768",
211 "vector_table_report": {
212 "requested_vector_table": "audio_embedding_vector_768",
213 "expected_dim": 768,
214 "allowed_vector_tables": [
215 "audio_embedding_vector_192",
216 "audio_embedding_vector_768"
217 ],
218 "resolved": true,
219 "table_exists": true,
220 "reason": null
221 },
222 "runtime_report": {
223 "model_name": "mert",
224 "requirements": [
225 "numpy",
226 "torch",
227 "torchaudio",
228 "transformers"
229 ],
230 "availability": {
231 "numpy": true,
232 "torch": false,
233 "torchaudio": false,
234 "transformers": false
235 },
236 "missing_dependencies": [
237 "torch",
238 "torchaudio",
239 "transformers"
240 ],
241 "ready": false
242 },
243 "processed_windows": [],
244 "notes": [
245 "this worker now validates planner -> job -> scope windows -> PostgreSQL failure semantics",
246 "real model inference should replace the guarded failure path without changing the job contract or idempotent upsert keys"
247 ]
248 }
...\ No newline at end of file ...\ No newline at end of file
1 {
2 "worker": "run_embedding_job",
3 "schema": "acr_test",
4 "job": {
5 "extraction_job_id": 3,
6 "feature_set_id": 4,
7 "target_scope": "reference_set:phase1_hot_reference_v1",
8 "job_status": "pending",
9 "shard_key": "phase1/reference/mert/v1-95m/10s_5s",
10 "job_metadata": {
11 "lane": "semantic",
12 "role": "long_context_validation",
13 "phase": "phase1"
14 },
15 "feature_name": "semantic_embedding",
16 "feature_level": "window",
17 "extraction_granularity": "sliding_window",
18 "window_sec": 10.0,
19 "hop_sec": 5.0,
20 "embedding_dim": 768,
21 "distance_metric": "cosine",
22 "feature_config": {
23 "role": "long_context_validation"
24 },
25 "model_id": 3,
26 "model_name": "mert",
27 "model_version": "v1-95m",
28 "model_family": "music_ssl",
29 "input_sample_rate": 24000,
30 "output_embedding_dim": 768,
31 "model_metadata": {
32 "lane": "semantic",
33 "role": "primary_baseline",
34 "phase": "phase1"
35 }
36 },
37 "target_scope_summary": {
38 "scope_type": "reference_set",
39 "scope_value": "phase1_hot_reference_v1",
40 "reference_set_id": 2,
41 "reference_set_name": "phase1_hot_reference_v1",
42 "recording_count": 20,
43 "ready_asset_count": 20,
44 "active_window_count": 20
45 },
46 "scope_window_count": 20,
47 "status_after_start": {
48 "extraction_job_id": 3,
49 "job_status": "running",
50 "input_count": 20,
51 "output_count": null,
52 "started_at": "2026-06-04T13:52:50.210469+08:00",
53 "finished_at": null,
54 "log_uri": null,
55 "metadata_json": {
56 "lane": "semantic",
57 "role": "long_context_validation",
58 "phase": "phase1",
59 "worker": "run_embedding_job",
60 "dry_run": false,
61 "vector_table": "audio_embedding_vector_768",
62 "output_target": "audio_embedding",
63 "execution_mode": "preflight",
64 "runtime_report": {
65 "ready": false,
66 "model_name": "mert",
67 "availability": {
68 "numpy": true,
69 "torch": false,
70 "torchaudio": false,
71 "transformers": false
72 },
73 "requirements": [
74 "numpy",
75 "torch",
76 "torchaudio",
77 "transformers"
78 ],
79 "missing_dependencies": [
80 "torch",
81 "torchaudio",
82 "transformers"
83 ]
84 },
85 "scope_window_count": 20,
86 "vector_table_report": {
87 "reason": null,
88 "resolved": true,
89 "expected_dim": 768,
90 "table_exists": true,
91 "allowed_vector_tables": [
92 "audio_embedding_vector_192",
93 "audio_embedding_vector_768"
94 ],
95 "requested_vector_table": "audio_embedding_vector_768"
96 },
97 "target_scope_summary": {
98 "scope_type": "reference_set",
99 "scope_value": "phase1_hot_reference_v1",
100 "recording_count": 20,
101 "reference_set_id": 2,
102 "ready_asset_count": 20,
103 "reference_set_name": "phase1_hot_reference_v1",
104 "active_window_count": 20
105 }
106 }
107 },
108 "status_after_complete": null,
109 "status_after_failed": {
110 "extraction_job_id": 3,
111 "job_status": "failed",
112 "input_count": 20,
113 "output_count": 0,
114 "started_at": "2026-06-04T13:52:50.210469+08:00",
115 "finished_at": "2026-06-04T13:52:50.211993+08:00",
116 "log_uri": null,
117 "metadata_json": {
118 "lane": "semantic",
119 "role": "long_context_validation",
120 "phase": "phase1",
121 "worker": "run_embedding_job",
122 "dry_run": false,
123 "artifact_dir": "data/pgvector_eval/music20/phase1_embeddings",
124 "vector_table": "audio_embedding_vector_768",
125 "output_target": "audio_embedding",
126 "execution_mode": "preflight_failure",
127 "failure_reason": "preflight_failed",
128 "runtime_report": {
129 "ready": false,
130 "model_name": "mert",
131 "availability": {
132 "numpy": true,
133 "torch": false,
134 "torchaudio": false,
135 "transformers": false
136 },
137 "requirements": [
138 "numpy",
139 "torch",
140 "torchaudio",
141 "transformers"
142 ],
143 "missing_dependencies": [
144 "torch",
145 "torchaudio",
146 "transformers"
147 ]
148 },
149 "preflight_blockers": [
150 "unreadable_audio_assets",
151 "model_runtime_unavailable"
152 ],
153 "scope_window_count": 20,
154 "write_target_table": "audio_embedding",
155 "vector_table_report": {
156 "reason": null,
157 "resolved": true,
158 "expected_dim": 768,
159 "table_exists": true,
160 "allowed_vector_tables": [
161 "audio_embedding_vector_192",
162 "audio_embedding_vector_768"
163 ],
164 "requested_vector_table": "audio_embedding_vector_768"
165 },
166 "missing_window_count": 20,
167 "target_scope_summary": {
168 "scope_type": "reference_set",
169 "scope_value": "phase1_hot_reference_v1",
170 "recording_count": 20,
171 "reference_set_id": 2,
172 "ready_asset_count": 20,
173 "reference_set_name": "phase1_hot_reference_v1",
174 "active_window_count": 20
175 },
176 "missing_window_samples": [
177 {
178 "reason": "missing_audio",
179 "asset_id": 1,
180 "window_id": 1,
181 "storage_uri": "/workspace/downloads/100/type_11/93dfdeb0-7da5-42a8-9c71-cf12af57dd191650256918.wav"
182 },
183 {
184 "reason": "missing_audio",
185 "asset_id": 2,
186 "window_id": 2,
187 "storage_uri": "/workspace/downloads/101/type_11/83c0c07f-4f96-4ff4-998c-58db910f3cfa1650256915.wav"
188 },
189 {
190 "reason": "missing_audio",
191 "asset_id": 3,
192 "window_id": 3,
193 "storage_uri": "/workspace/downloads/102/type_11/43440ec5-70b4-4d50-8683-d3e41cad29411650256908.wav"
194 },
195 {
196 "reason": "missing_audio",
197 "asset_id": 4,
198 "window_id": 4,
199 "storage_uri": "/workspace/downloads/103/type_11/19876dbb-fffc-40f8-9530-9322c9ed77681650256912.wav"
200 },
201 {
202 "reason": "missing_audio",
203 "asset_id": 5,
204 "window_id": 5,
205 "storage_uri": "/workspace/downloads/104/type_11/4c1d3e22-045f-445b-ab87-ba1ae3ee09b31650256912.wav"
206 }
207 ]
208 }
209 },
210 "resolved_vector_table": "audio_embedding_vector_768",
211 "vector_table_report": {
212 "requested_vector_table": "audio_embedding_vector_768",
213 "expected_dim": 768,
214 "allowed_vector_tables": [
215 "audio_embedding_vector_192",
216 "audio_embedding_vector_768"
217 ],
218 "resolved": true,
219 "table_exists": true,
220 "reason": null
221 },
222 "runtime_report": {
223 "model_name": "mert",
224 "requirements": [
225 "numpy",
226 "torch",
227 "torchaudio",
228 "transformers"
229 ],
230 "availability": {
231 "numpy": true,
232 "torch": false,
233 "torchaudio": false,
234 "transformers": false
235 },
236 "missing_dependencies": [
237 "torch",
238 "torchaudio",
239 "transformers"
240 ],
241 "ready": false
242 },
243 "processed_windows": [],
244 "notes": [
245 "this worker now validates planner -> job -> scope windows -> PostgreSQL failure semantics",
246 "real model inference should replace the guarded failure path without changing the job contract or idempotent upsert keys"
247 ]
248 }
...\ No newline at end of file ...\ No newline at end of file
1 {
2 "worker": "run_embedding_job",
3 "schema": "acr_test",
4 "job": {
5 "extraction_job_id": 4,
6 "feature_set_id": 5,
7 "target_scope": "reference_set:phase1_hot_reference_v1",
8 "job_status": "pending",
9 "shard_key": "phase1/reference/muq/large-msd-iter/5s_2.5s",
10 "job_metadata": {
11 "lane": "semantic",
12 "role": "challenger",
13 "phase": "phase1"
14 },
15 "feature_name": "semantic_embedding",
16 "feature_level": "window",
17 "extraction_granularity": "sliding_window",
18 "window_sec": 5.0,
19 "hop_sec": 2.5,
20 "embedding_dim": 768,
21 "distance_metric": "cosine",
22 "feature_config": {
23 "role": "semantic_challenger"
24 },
25 "model_id": 4,
26 "model_name": "muq",
27 "model_version": "large-msd-iter",
28 "model_family": "music_ssl",
29 "input_sample_rate": 24000,
30 "output_embedding_dim": 768,
31 "model_metadata": {
32 "lane": "semantic",
33 "role": "challenger",
34 "phase": "phase1"
35 }
36 },
37 "target_scope_summary": {
38 "scope_type": "reference_set",
39 "scope_value": "phase1_hot_reference_v1",
40 "reference_set_id": 2,
41 "reference_set_name": "phase1_hot_reference_v1",
42 "recording_count": 20,
43 "ready_asset_count": 20,
44 "active_window_count": 20
45 },
46 "scope_window_count": 20,
47 "status_after_start": {
48 "extraction_job_id": 4,
49 "job_status": "running",
50 "input_count": 20,
51 "output_count": null,
52 "started_at": "2026-06-04T13:52:50.434101+08:00",
53 "finished_at": null,
54 "log_uri": null,
55 "metadata_json": {
56 "lane": "semantic",
57 "role": "challenger",
58 "phase": "phase1",
59 "worker": "run_embedding_job",
60 "dry_run": false,
61 "vector_table": "audio_embedding_vector_768",
62 "output_target": "audio_embedding",
63 "execution_mode": "preflight",
64 "runtime_report": {
65 "ready": false,
66 "model_name": "muq",
67 "availability": {
68 "numpy": true,
69 "torch": false,
70 "torchaudio": false,
71 "transformers": false
72 },
73 "requirements": [
74 "numpy",
75 "torch",
76 "torchaudio",
77 "transformers"
78 ],
79 "missing_dependencies": [
80 "torch",
81 "torchaudio",
82 "transformers"
83 ]
84 },
85 "scope_window_count": 20,
86 "vector_table_report": {
87 "reason": null,
88 "resolved": true,
89 "expected_dim": 768,
90 "table_exists": true,
91 "allowed_vector_tables": [
92 "audio_embedding_vector_192",
93 "audio_embedding_vector_768"
94 ],
95 "requested_vector_table": "audio_embedding_vector_768"
96 },
97 "target_scope_summary": {
98 "scope_type": "reference_set",
99 "scope_value": "phase1_hot_reference_v1",
100 "recording_count": 20,
101 "reference_set_id": 2,
102 "ready_asset_count": 20,
103 "reference_set_name": "phase1_hot_reference_v1",
104 "active_window_count": 20
105 }
106 }
107 },
108 "status_after_complete": null,
109 "status_after_failed": {
110 "extraction_job_id": 4,
111 "job_status": "failed",
112 "input_count": 20,
113 "output_count": 0,
114 "started_at": "2026-06-04T13:52:50.434101+08:00",
115 "finished_at": "2026-06-04T13:52:50.435667+08:00",
116 "log_uri": null,
117 "metadata_json": {
118 "lane": "semantic",
119 "role": "challenger",
120 "phase": "phase1",
121 "worker": "run_embedding_job",
122 "dry_run": false,
123 "artifact_dir": "data/pgvector_eval/music20/phase1_embeddings",
124 "vector_table": "audio_embedding_vector_768",
125 "output_target": "audio_embedding",
126 "execution_mode": "preflight_failure",
127 "failure_reason": "preflight_failed",
128 "runtime_report": {
129 "ready": false,
130 "model_name": "muq",
131 "availability": {
132 "numpy": true,
133 "torch": false,
134 "torchaudio": false,
135 "transformers": false
136 },
137 "requirements": [
138 "numpy",
139 "torch",
140 "torchaudio",
141 "transformers"
142 ],
143 "missing_dependencies": [
144 "torch",
145 "torchaudio",
146 "transformers"
147 ]
148 },
149 "preflight_blockers": [
150 "unreadable_audio_assets",
151 "model_runtime_unavailable"
152 ],
153 "scope_window_count": 20,
154 "write_target_table": "audio_embedding",
155 "vector_table_report": {
156 "reason": null,
157 "resolved": true,
158 "expected_dim": 768,
159 "table_exists": true,
160 "allowed_vector_tables": [
161 "audio_embedding_vector_192",
162 "audio_embedding_vector_768"
163 ],
164 "requested_vector_table": "audio_embedding_vector_768"
165 },
166 "missing_window_count": 20,
167 "target_scope_summary": {
168 "scope_type": "reference_set",
169 "scope_value": "phase1_hot_reference_v1",
170 "recording_count": 20,
171 "reference_set_id": 2,
172 "ready_asset_count": 20,
173 "reference_set_name": "phase1_hot_reference_v1",
174 "active_window_count": 20
175 },
176 "missing_window_samples": [
177 {
178 "reason": "missing_audio",
179 "asset_id": 1,
180 "window_id": 1,
181 "storage_uri": "/workspace/downloads/100/type_11/93dfdeb0-7da5-42a8-9c71-cf12af57dd191650256918.wav"
182 },
183 {
184 "reason": "missing_audio",
185 "asset_id": 2,
186 "window_id": 2,
187 "storage_uri": "/workspace/downloads/101/type_11/83c0c07f-4f96-4ff4-998c-58db910f3cfa1650256915.wav"
188 },
189 {
190 "reason": "missing_audio",
191 "asset_id": 3,
192 "window_id": 3,
193 "storage_uri": "/workspace/downloads/102/type_11/43440ec5-70b4-4d50-8683-d3e41cad29411650256908.wav"
194 },
195 {
196 "reason": "missing_audio",
197 "asset_id": 4,
198 "window_id": 4,
199 "storage_uri": "/workspace/downloads/103/type_11/19876dbb-fffc-40f8-9530-9322c9ed77681650256912.wav"
200 },
201 {
202 "reason": "missing_audio",
203 "asset_id": 5,
204 "window_id": 5,
205 "storage_uri": "/workspace/downloads/104/type_11/4c1d3e22-045f-445b-ab87-ba1ae3ee09b31650256912.wav"
206 }
207 ]
208 }
209 },
210 "resolved_vector_table": "audio_embedding_vector_768",
211 "vector_table_report": {
212 "requested_vector_table": "audio_embedding_vector_768",
213 "expected_dim": 768,
214 "allowed_vector_tables": [
215 "audio_embedding_vector_192",
216 "audio_embedding_vector_768"
217 ],
218 "resolved": true,
219 "table_exists": true,
220 "reason": null
221 },
222 "runtime_report": {
223 "model_name": "muq",
224 "requirements": [
225 "numpy",
226 "torch",
227 "torchaudio",
228 "transformers"
229 ],
230 "availability": {
231 "numpy": true,
232 "torch": false,
233 "torchaudio": false,
234 "transformers": false
235 },
236 "missing_dependencies": [
237 "torch",
238 "torchaudio",
239 "transformers"
240 ],
241 "ready": false
242 },
243 "processed_windows": [],
244 "notes": [
245 "this worker now validates planner -> job -> scope windows -> PostgreSQL failure semantics",
246 "real model inference should replace the guarded failure path without changing the job contract or idempotent upsert keys"
247 ]
248 }
...\ No newline at end of file ...\ No newline at end of file
1 {
2 "worker": "run_embedding_job",
3 "schema": "acr_test",
4 "job": {
5 "extraction_job_id": 5,
6 "feature_set_id": 6,
7 "target_scope": "reference_set:phase1_hot_reference_v1",
8 "job_status": "pending",
9 "shard_key": "phase1/reference/ecapa/acr-baseline-v1/5s_2.5s",
10 "job_metadata": {
11 "lane": "semantic",
12 "role": "historical_baseline",
13 "phase": "phase1"
14 },
15 "feature_name": "semantic_embedding",
16 "feature_level": "window",
17 "extraction_granularity": "sliding_window",
18 "window_sec": 5.0,
19 "hop_sec": 2.5,
20 "embedding_dim": 192,
21 "distance_metric": "cosine",
22 "feature_config": {
23 "role": "historical_baseline"
24 },
25 "model_id": 5,
26 "model_name": "ecapa",
27 "model_version": "acr-baseline-v1",
28 "model_family": "speech_derived",
29 "input_sample_rate": 16000,
30 "output_embedding_dim": 192,
31 "model_metadata": {
32 "lane": "semantic",
33 "role": "historical_baseline",
34 "phase": "phase1"
35 }
36 },
37 "target_scope_summary": {
38 "scope_type": "reference_set",
39 "scope_value": "phase1_hot_reference_v1",
40 "reference_set_id": 2,
41 "reference_set_name": "phase1_hot_reference_v1",
42 "recording_count": 20,
43 "ready_asset_count": 20,
44 "active_window_count": 20
45 },
46 "scope_window_count": 20,
47 "status_after_start": {
48 "extraction_job_id": 5,
49 "job_status": "running",
50 "input_count": 20,
51 "output_count": null,
52 "started_at": "2026-06-04T13:52:50.702135+08:00",
53 "finished_at": null,
54 "log_uri": null,
55 "metadata_json": {
56 "lane": "semantic",
57 "role": "historical_baseline",
58 "phase": "phase1",
59 "worker": "run_embedding_job",
60 "dry_run": false,
61 "vector_table": "audio_embedding_vector_192",
62 "output_target": "audio_embedding",
63 "execution_mode": "preflight",
64 "runtime_report": {
65 "ready": false,
66 "model_name": "ecapa",
67 "availability": {
68 "numpy": true,
69 "torch": false,
70 "torchaudio": false,
71 "speechbrain": false
72 },
73 "requirements": [
74 "numpy",
75 "torch",
76 "torchaudio",
77 "speechbrain"
78 ],
79 "missing_dependencies": [
80 "torch",
81 "torchaudio",
82 "speechbrain"
83 ]
84 },
85 "scope_window_count": 20,
86 "vector_table_report": {
87 "reason": null,
88 "resolved": true,
89 "expected_dim": 192,
90 "table_exists": true,
91 "allowed_vector_tables": [
92 "audio_embedding_vector_192",
93 "audio_embedding_vector_768"
94 ],
95 "requested_vector_table": "audio_embedding_vector_192"
96 },
97 "target_scope_summary": {
98 "scope_type": "reference_set",
99 "scope_value": "phase1_hot_reference_v1",
100 "recording_count": 20,
101 "reference_set_id": 2,
102 "ready_asset_count": 20,
103 "reference_set_name": "phase1_hot_reference_v1",
104 "active_window_count": 20
105 }
106 }
107 },
108 "status_after_complete": null,
109 "status_after_failed": {
110 "extraction_job_id": 5,
111 "job_status": "failed",
112 "input_count": 20,
113 "output_count": 0,
114 "started_at": "2026-06-04T13:52:50.702135+08:00",
115 "finished_at": "2026-06-04T13:52:50.703634+08:00",
116 "log_uri": null,
117 "metadata_json": {
118 "lane": "semantic",
119 "role": "historical_baseline",
120 "phase": "phase1",
121 "worker": "run_embedding_job",
122 "dry_run": false,
123 "artifact_dir": "data/pgvector_eval/music20/phase1_embeddings",
124 "vector_table": "audio_embedding_vector_192",
125 "output_target": "audio_embedding",
126 "execution_mode": "preflight_failure",
127 "failure_reason": "preflight_failed",
128 "runtime_report": {
129 "ready": false,
130 "model_name": "ecapa",
131 "availability": {
132 "numpy": true,
133 "torch": false,
134 "torchaudio": false,
135 "speechbrain": false
136 },
137 "requirements": [
138 "numpy",
139 "torch",
140 "torchaudio",
141 "speechbrain"
142 ],
143 "missing_dependencies": [
144 "torch",
145 "torchaudio",
146 "speechbrain"
147 ]
148 },
149 "preflight_blockers": [
150 "unreadable_audio_assets",
151 "model_runtime_unavailable"
152 ],
153 "scope_window_count": 20,
154 "write_target_table": "audio_embedding",
155 "vector_table_report": {
156 "reason": null,
157 "resolved": true,
158 "expected_dim": 192,
159 "table_exists": true,
160 "allowed_vector_tables": [
161 "audio_embedding_vector_192",
162 "audio_embedding_vector_768"
163 ],
164 "requested_vector_table": "audio_embedding_vector_192"
165 },
166 "missing_window_count": 20,
167 "target_scope_summary": {
168 "scope_type": "reference_set",
169 "scope_value": "phase1_hot_reference_v1",
170 "recording_count": 20,
171 "reference_set_id": 2,
172 "ready_asset_count": 20,
173 "reference_set_name": "phase1_hot_reference_v1",
174 "active_window_count": 20
175 },
176 "missing_window_samples": [
177 {
178 "reason": "missing_audio",
179 "asset_id": 1,
180 "window_id": 1,
181 "storage_uri": "/workspace/downloads/100/type_11/93dfdeb0-7da5-42a8-9c71-cf12af57dd191650256918.wav"
182 },
183 {
184 "reason": "missing_audio",
185 "asset_id": 2,
186 "window_id": 2,
187 "storage_uri": "/workspace/downloads/101/type_11/83c0c07f-4f96-4ff4-998c-58db910f3cfa1650256915.wav"
188 },
189 {
190 "reason": "missing_audio",
191 "asset_id": 3,
192 "window_id": 3,
193 "storage_uri": "/workspace/downloads/102/type_11/43440ec5-70b4-4d50-8683-d3e41cad29411650256908.wav"
194 },
195 {
196 "reason": "missing_audio",
197 "asset_id": 4,
198 "window_id": 4,
199 "storage_uri": "/workspace/downloads/103/type_11/19876dbb-fffc-40f8-9530-9322c9ed77681650256912.wav"
200 },
201 {
202 "reason": "missing_audio",
203 "asset_id": 5,
204 "window_id": 5,
205 "storage_uri": "/workspace/downloads/104/type_11/4c1d3e22-045f-445b-ab87-ba1ae3ee09b31650256912.wav"
206 }
207 ]
208 }
209 },
210 "resolved_vector_table": "audio_embedding_vector_192",
211 "vector_table_report": {
212 "requested_vector_table": "audio_embedding_vector_192",
213 "expected_dim": 192,
214 "allowed_vector_tables": [
215 "audio_embedding_vector_192",
216 "audio_embedding_vector_768"
217 ],
218 "resolved": true,
219 "table_exists": true,
220 "reason": null
221 },
222 "runtime_report": {
223 "model_name": "ecapa",
224 "requirements": [
225 "numpy",
226 "torch",
227 "torchaudio",
228 "speechbrain"
229 ],
230 "availability": {
231 "numpy": true,
232 "torch": false,
233 "torchaudio": false,
234 "speechbrain": false
235 },
236 "missing_dependencies": [
237 "torch",
238 "torchaudio",
239 "speechbrain"
240 ],
241 "ready": false
242 },
243 "processed_windows": [],
244 "notes": [
245 "this worker now validates planner -> job -> scope windows -> PostgreSQL failure semantics",
246 "real model inference should replace the guarded failure path without changing the job contract or idempotent upsert keys"
247 ]
248 }
...\ No newline at end of file ...\ No newline at end of file
1 {
2 "schema": "acr_test",
3 "dsn_redacted": "postgres://d2:***@127.0.0.1:5432/d2",
4 "semantic_job_count": 4,
5 "results": [
6 {
7 "extraction_job_id": 2,
8 "model_name": "mert",
9 "model_version": "v1-95m",
10 "vector_table": "audio_embedding_vector_768",
11 "returncode": 0,
12 "job_status": "failed",
13 "failure_reason": "preflight_failed",
14 "preflight_blockers": [
15 "unreadable_audio_assets",
16 "model_runtime_unavailable"
17 ],
18 "missing_window_count": 20,
19 "runtime_missing_dependencies": [
20 "torch",
21 "torchaudio",
22 "transformers"
23 ],
24 "vector_table_report": {
25 "reason": null,
26 "resolved": true,
27 "expected_dim": 768,
28 "table_exists": true,
29 "allowed_vector_tables": [
30 "audio_embedding_vector_192",
31 "audio_embedding_vector_768"
32 ],
33 "requested_vector_table": "audio_embedding_vector_768"
34 },
35 "attempt_artifact": "data/pgvector_eval/music20/job2_mert_preflight_attempt.json"
36 },
37 {
38 "extraction_job_id": 3,
39 "model_name": "mert",
40 "model_version": "v1-95m",
41 "vector_table": "audio_embedding_vector_768",
42 "returncode": 0,
43 "job_status": "failed",
44 "failure_reason": "preflight_failed",
45 "preflight_blockers": [
46 "unreadable_audio_assets",
47 "model_runtime_unavailable"
48 ],
49 "missing_window_count": 20,
50 "runtime_missing_dependencies": [
51 "torch",
52 "torchaudio",
53 "transformers"
54 ],
55 "vector_table_report": {
56 "reason": null,
57 "resolved": true,
58 "expected_dim": 768,
59 "table_exists": true,
60 "allowed_vector_tables": [
61 "audio_embedding_vector_192",
62 "audio_embedding_vector_768"
63 ],
64 "requested_vector_table": "audio_embedding_vector_768"
65 },
66 "attempt_artifact": "data/pgvector_eval/music20/job3_mert_preflight_attempt.json"
67 },
68 {
69 "extraction_job_id": 4,
70 "model_name": "muq",
71 "model_version": "large-msd-iter",
72 "vector_table": "audio_embedding_vector_768",
73 "returncode": 0,
74 "job_status": "failed",
75 "failure_reason": "preflight_failed",
76 "preflight_blockers": [
77 "unreadable_audio_assets",
78 "model_runtime_unavailable"
79 ],
80 "missing_window_count": 20,
81 "runtime_missing_dependencies": [
82 "torch",
83 "torchaudio",
84 "transformers"
85 ],
86 "vector_table_report": {
87 "reason": null,
88 "resolved": true,
89 "expected_dim": 768,
90 "table_exists": true,
91 "allowed_vector_tables": [
92 "audio_embedding_vector_192",
93 "audio_embedding_vector_768"
94 ],
95 "requested_vector_table": "audio_embedding_vector_768"
96 },
97 "attempt_artifact": "data/pgvector_eval/music20/job4_muq_preflight_attempt.json"
98 },
99 {
100 "extraction_job_id": 5,
101 "model_name": "ecapa",
102 "model_version": "acr-baseline-v1",
103 "vector_table": "audio_embedding_vector_192",
104 "returncode": 0,
105 "job_status": "failed",
106 "failure_reason": "preflight_failed",
107 "preflight_blockers": [
108 "unreadable_audio_assets",
109 "model_runtime_unavailable"
110 ],
111 "missing_window_count": 20,
112 "runtime_missing_dependencies": [
113 "torch",
114 "torchaudio",
115 "speechbrain"
116 ],
117 "vector_table_report": {
118 "reason": null,
119 "resolved": true,
120 "expected_dim": 192,
121 "table_exists": true,
122 "allowed_vector_tables": [
123 "audio_embedding_vector_192",
124 "audio_embedding_vector_768"
125 ],
126 "requested_vector_table": "audio_embedding_vector_192"
127 },
128 "attempt_artifact": "data/pgvector_eval/music20/job5_ecapa_preflight_attempt.json"
129 }
130 ],
131 "summary": {
132 "failed_jobs": 4,
133 "models": [
134 "mert",
135 "mert",
136 "muq",
137 "ecapa"
138 ],
139 "unique_blockers": [
140 "model_runtime_unavailable",
141 "unreadable_audio_assets"
142 ]
143 }
144 }
...\ No newline at end of file ...\ No newline at end of file
1 #!/usr/bin/env /usr/local/miniconda3/bin/python
2 from __future__ import annotations
3
4 import argparse
5 import json
6 import subprocess
7 from pathlib import Path
8 from typing import Any
9
10 import psycopg
11
12 ROOT = Path(__file__).resolve().parents[1]
13 DEFAULT_OUTPUT = ROOT / 'data' / 'pgvector_eval' / 'music20' / 'phase1_embedding_preflight_matrix_report.json'
14 PYTHON_BIN = '/usr/local/miniconda3/bin/python'
15
16
17 def load_semantic_jobs(conn: psycopg.Connection) -> list[dict[str, Any]]:
18 rows = conn.execute(
19 """
20 SELECT
21 fej.extraction_job_id,
22 mr.model_name,
23 mr.model_version,
24 fs.embedding_dim
25 FROM feature_extraction_job fej
26 JOIN feature_set_registry fs ON fs.feature_set_id = fej.feature_set_id
27 JOIN model_registry mr ON mr.model_id = fs.model_id
28 WHERE fs.feature_name = 'semantic_embedding'
29 AND fs.feature_level = 'window'
30 ORDER BY fej.extraction_job_id;
31 """
32 ).fetchall()
33 return [
34 {
35 'extraction_job_id': int(row[0]),
36 'model_name': row[1],
37 'model_version': row[2],
38 'embedding_dim': int(row[3]) if row[3] is not None else None,
39 'vector_table': f"audio_embedding_vector_{int(row[3])}" if row[3] in (192, 768) else None,
40 }
41 for row in rows
42 ]
43
44
45 def reset_jobs(dsn: str, schema: str) -> None:
46 cmd = [
47 PYTHON_BIN,
48 'scripts/bootstrap_phase1_extraction_jobs_live.py',
49 '--dsn', dsn,
50 '--schema', schema,
51 ]
52 subprocess.run(cmd, cwd=ROOT, check=True, capture_output=True, text=True)
53
54
55 def run_job(dsn: str, schema: str, job: dict[str, Any]) -> dict[str, Any]:
56 attempt_path = ROOT / 'data' / 'pgvector_eval' / 'music20' / f"job{job['extraction_job_id']}_{job['model_name']}_preflight_attempt.json"
57 cmd = [
58 PYTHON_BIN,
59 'workers/run_embedding_job.py',
60 '--dsn', dsn,
61 '--schema', schema,
62 '--job-id', str(job['extraction_job_id']),
63 '--model-name', job['model_name'],
64 '--model-version', job['model_version'],
65 ]
66 if job['vector_table']:
67 cmd.extend(['--vector-table', job['vector_table']])
68 cmd.extend(['--output', str(attempt_path)])
69 proc = subprocess.run(cmd, cwd=ROOT, capture_output=True, text=True)
70 payload = json.loads(attempt_path.read_text(encoding='utf-8'))
71 status_after_failed = payload.get('status_after_failed') or {}
72 metadata = status_after_failed.get('metadata_json') or {}
73 return {
74 'extraction_job_id': job['extraction_job_id'],
75 'model_name': job['model_name'],
76 'model_version': job['model_version'],
77 'vector_table': job['vector_table'],
78 'returncode': proc.returncode,
79 'job_status': status_after_failed.get('job_status') or payload.get('status_after_complete', {}).get('job_status'),
80 'failure_reason': metadata.get('failure_reason'),
81 'preflight_blockers': metadata.get('preflight_blockers'),
82 'missing_window_count': metadata.get('missing_window_count'),
83 'runtime_missing_dependencies': ((metadata.get('runtime_report') or {}).get('missing_dependencies')),
84 'vector_table_report': metadata.get('vector_table_report'),
85 'attempt_artifact': str(attempt_path.relative_to(ROOT)),
86 }
87
88
89 def main() -> None:
90 ap = argparse.ArgumentParser()
91 ap.add_argument('--dsn', required=True)
92 ap.add_argument('--schema', default='acr_test')
93 ap.add_argument('--output', default=str(DEFAULT_OUTPUT))
94 args = ap.parse_args()
95
96 reset_jobs(args.dsn, args.schema)
97 with psycopg.connect(args.dsn, autocommit=True) as conn:
98 conn.execute(f'SET search_path TO {args.schema}, public;')
99 jobs = load_semantic_jobs(conn)
100
101 results = [run_job(args.dsn, args.schema, job) for job in jobs]
102 payload = {
103 'schema': args.schema,
104 'dsn_redacted': 'postgres://d2:***@127.0.0.1:5432/d2',
105 'semantic_job_count': len(results),
106 'results': results,
107 'summary': {
108 'failed_jobs': sum(1 for item in results if item['job_status'] == 'failed'),
109 'models': [item['model_name'] for item in results],
110 'unique_blockers': sorted({blocker for item in results for blocker in (item.get('preflight_blockers') or [])}),
111 },
112 }
113 out = Path(args.output)
114 out.parent.mkdir(parents=True, exist_ok=True)
115 out.write_text(json.dumps(payload, ensure_ascii=False, indent=2), encoding='utf-8')
116 print(json.dumps(payload, ensure_ascii=False, indent=2))
117
118
119 if __name__ == '__main__':
120 main()
1 ## 2026-06-04 1 ## 2026-06-04
2 2
3 - 新增 `scripts/run_phase1_embedding_preflight_matrix_live.py` 与 `phase1_embedding_preflight_matrix_report.json`，对 `mert / muq / ecapa` 四条 semantic jobs 做了统一 live preflight 矩阵验证；结果表明 4 条 job 全都稳定落到 `preflight_failed`，且 blocker 已收敛为 `/workspace/downloads` 未挂载与语义模型 runtime 缺失，而不是单条 job 的偶发异常。
3 - 更新 `run_embedding_job.py`，把 semantic lane 从“只有 dry-run”推进到“真实 scope 读取 + vector table 校验 + runtime 依赖校验 + 缺音频校验 + PostgreSQL failed 落账”的 preflight write contract；当前 live `mert` job 会把 `unreadable_audio_assets` 与 `model_runtime_unavailable` 同时写入 `feature_extraction_job.metadata_json`，不再只停留在纸面设计。 4 - 更新 `run_embedding_job.py`，把 semantic lane 从“只有 dry-run”推进到“真实 scope 读取 + vector table 校验 + runtime 依赖校验 + 缺音频校验 + PostgreSQL failed 落账”的 preflight write contract；当前 live `mert` job 会把 `unreadable_audio_assets` 与 `model_runtime_unavailable` 同时写入 `feature_extraction_job.metadata_json`，不再只停留在纸面设计。
4 - 给 `audio_embedding` 补上 `UNIQUE(feature_set_id, window_id) WHERE window_id IS NOT NULL` 与 `UNIQUE(feature_set_id, asset_id) WHERE window_id IS NULL AND asset_id IS NOT NULL` 两条幂等唯一键，为后续真实 `MERT / MuQ / ECAPA` upsert 落库固定主键策略。 5 - 给 `audio_embedding` 补上 `UNIQUE(feature_set_id, window_id) WHERE window_id IS NOT NULL` 与 `UNIQUE(feature_set_id, asset_id) WHERE window_id IS NULL AND asset_id IS NOT NULL` 两条幂等唯一键，为后续真实 `MERT / MuQ / ECAPA` upsert 落库固定主键策略。
5 - 新增 `phase1_worker_embedding_write_attempt.json`、`phase1_worker_embedding_write_guard_report.json` 与 `phase1_worker_embedding_post_state.json`，在 live PostgreSQL `acr_test` 上验证 semantic lane 的非 dry-run 行为：当前 `scope_window_count=20`，但因 `/workspace/downloads/...` 未挂载且 `torch/torchaudio/transformers` 缺失，job 被诚实标记为 `failed`，同时 `audio_embedding_vector_768_count` 仍保持 `0`。 6 - 新增 `phase1_worker_embedding_write_attempt.json`、`phase1_worker_embedding_write_guard_report.json` 与 `phase1_worker_embedding_post_state.json`，在 live PostgreSQL `acr_test` 上验证 semantic lane 的非 dry-run 行为：当前 `scope_window_count=20`，但因 `/workspace/downloads/...` 未挂载且 `torch/torchaudio/transformers` 缺失，job 被诚实标记为 `failed`，同时 `audio_embedding_vector_768_count` 仍保持 `0`。
......
...@@ -739,3 +739,38 @@ cd /workspace/acr-engine ...@@ -739,3 +739,38 @@ cd /workspace/acr-engine
739 3. 不把幂等职责留给应用层“先查再写” 739 3. 不把幂等职责留给应用层“先查再写”
740 740
741 这一步对后续的 `MERT / MuQ / ECAPA` 都通用。 741 这一步对后续的 `MERT / MuQ / ECAPA` 都通用。
742
743
744 ## 新增：Semantic preflight blocker matrix
745
746 为了避免下次 session 继续手工逐个试，本轮又新增：
747
748 - `acr-engine/scripts/run_phase1_embedding_preflight_matrix_live.py`
749 - `acr-engine/data/pgvector_eval/music20/phase1_embedding_preflight_matrix_report.json`
750
751 它会：
752
753 1. 先把 `feature_extraction_job` 重置回 `pending`
754 2. 顺序执行全部 semantic jobs（当前是 `mert 5s`、`mert 10s`、`muq 5s`、`ecapa 5s`）
755 3. 归并输出每个 job 的：
756 - `failure_reason`
757 - `preflight_blockers`
758 - `runtime_missing_dependencies`
759 - `vector_table_report`
760
761 ### 当前矩阵结果
762
763 | job | model | vector table | blockers | runtime missing |
764 |---|---|---|---|---|
765 | 2 | `mert v1-95m` | `audio_embedding_vector_768` | `unreadable_audio_assets`, `model_runtime_unavailable` | `torch`, `torchaudio`, `transformers` |
766 | 3 | `mert v1-95m` | `audio_embedding_vector_768` | `unreadable_audio_assets`, `model_runtime_unavailable` | `torch`, `torchaudio`, `transformers` |
767 | 4 | `muq large-msd-iter` | `audio_embedding_vector_768` | `unreadable_audio_assets`, `model_runtime_unavailable` | `torch`, `torchaudio`, `transformers` |
768 | 5 | `ecapa acr-baseline-v1` | `audio_embedding_vector_192` | `unreadable_audio_assets`, `model_runtime_unavailable` | `torch`, `torchaudio`, `speechbrain` |
769
770 结论：
771
772 - 当前 semantic lane 的失败已经具有**稳定矩阵特征**，不是某一个 job 独有的偶发问题
773 - `vector_table` 路径已全部通过
774 - 当前真正阻塞 Phase-1 encoder-only 落地的是：
775 1. `/workspace/downloads` 音频挂载
776 2. 模型 runtime 依赖安装
......
...@@ -191,6 +191,7 @@ sed -n '1,320p' acr-engine/sql/acr_pg_schema_v2.sql ...@@ -191,6 +191,7 @@ sed -n '1,320p' acr-engine/sql/acr_pg_schema_v2.sql
191 - 下一阶段已经不是“补 planner”，而是把 dry-run worker 替换为真实 extractor，并把 `audio_fingerprint / audio_embedding` 写入做成幂等执行 191 - 下一阶段已经不是“补 planner”，而是把 dry-run worker 替换为真实 extractor，并把 `audio_fingerprint / audio_embedding` 写入做成幂等执行
192 - semantic lane 也已完成 live failure contract：`run_embedding_job.py` 现在会同时暴露 `unreadable_audio_assets` 与 `model_runtime_unavailable`，而不是把失败伪装成 completed 192 - semantic lane 也已完成 live failure contract：`run_embedding_job.py` 现在会同时暴露 `unreadable_audio_assets` 与 `model_runtime_unavailable`，而不是把失败伪装成 completed
193 - `audio_embedding` 已补上 window / asset 双路唯一键，后续真实 encoder 只需替换 inference adapter 即可复用同一 upsert 合同 193 - `audio_embedding` 已补上 window / asset 双路唯一键，后续真实 encoder 只需替换 inference adapter 即可复用同一 upsert 合同
194 - `scripts/run_phase1_embedding_preflight_matrix_live.py` 已跑通，4 条 semantic jobs（mert/muq/ecapa）在 `acr_test` 上都被稳定标记为 `preflight_failed`；当前共性 blocker 已收敛为 `/workspace/downloads` 缺失 + 语义模型 runtime 缺失
194 - `phase1_hot_reference_v1` 在 `acr_test` 里已经真实补齐 `20` 个 reference members，因此 worker dry-run 当前看到的 scope 已是 `20 recordings / 20 assets / 20 windows` 195 - `phase1_hot_reference_v1` 在 `acr_test` 里已经真实补齐 `20` 个 reference members，因此 worker dry-run 当前看到的 scope 已是 `20 recordings / 20 assets / 20 windows`
195 - worker contract 现在已有基础前置状态保护；重复执行同一 chromaprint dry-run job 会被 `expected_status=pending` 明确拒绝，证据见 `phase1_worker_double_claim_guard_report.json` 196 - worker contract 现在已有基础前置状态保护；重复执行同一 chromaprint dry-run job 会被 `expected_status=pending` 明确拒绝，证据见 `phase1_worker_double_claim_guard_report.json`
196 - exact lane 的 `run_chromaprint_job.py` 已具备非 dry-run 写入路径；当前在 `acr_test` 的 live 结果是因为 `/workspace/downloads/...` 缺失而明确 `failed`，不是继续假装 `completed` 197 - exact lane 的 `run_chromaprint_job.py` 已具备非 dry-run 写入路径；当前在 `acr_test` 的 live 结果是因为 `/workspace/downloads/...` 缺失而明确 `failed`，不是继续假装 `completed`
......