@firedrill-tools/unstructured 0.1.4

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (72) hide show
  1. package/LICENSE +201 -0
  2. package/README.md +275 -0
  3. package/firedrill/agent.target.json +16 -0
  4. package/firedrill/baseline.scenario.json +5 -0
  5. package/firedrill/conformance.suite.json +21 -0
  6. package/firedrill/overloaded.scenario.json +11 -0
  7. package/firedrill/rate-limited.scenario.json +11 -0
  8. package/firedrill/run-response-lost.scenario.json +11 -0
  9. package/firedrill/small-responses.scenario.json +21 -0
  10. package/firedrill/tight-limits.scenario.json +21 -0
  11. package/firedrill/tools/unstructured/behavior.mjs +69 -0
  12. package/firedrill/tools/unstructured/lib/connectors.mjs +68 -0
  13. package/firedrill/tools/unstructured/lib/errors.mjs +58 -0
  14. package/firedrill/tools/unstructured/lib/gzip.mjs +38 -0
  15. package/firedrill/tools/unstructured/lib/identity.mjs +19 -0
  16. package/firedrill/tools/unstructured/lib/ids.mjs +36 -0
  17. package/firedrill/tools/unstructured/lib/jobs-derive.mjs +92 -0
  18. package/firedrill/tools/unstructured/lib/multipart.mjs +171 -0
  19. package/firedrill/tools/unstructured/lib/pages.mjs +40 -0
  20. package/firedrill/tools/unstructured/lib/partition/chunk.mjs +243 -0
  21. package/firedrill/tools/unstructured/lib/partition/csv.mjs +85 -0
  22. package/firedrill/tools/unstructured/lib/partition/csvout.mjs +25 -0
  23. package/firedrill/tools/unstructured/lib/partition/elements.mjs +171 -0
  24. package/firedrill/tools/unstructured/lib/partition/email.mjs +269 -0
  25. package/firedrill/tools/unstructured/lib/partition/html-tokens.mjs +134 -0
  26. package/firedrill/tools/unstructured/lib/partition/html-util.mjs +99 -0
  27. package/firedrill/tools/unstructured/lib/partition/html.mjs +211 -0
  28. package/firedrill/tools/unstructured/lib/partition/index.mjs +122 -0
  29. package/firedrill/tools/unstructured/lib/partition/markdown.mjs +220 -0
  30. package/firedrill/tools/unstructured/lib/partition/other.mjs +118 -0
  31. package/firedrill/tools/unstructured/lib/partition/text.mjs +53 -0
  32. package/firedrill/tools/unstructured/lib/sha256.mjs +161 -0
  33. package/firedrill/tools/unstructured/lib/store.mjs +33 -0
  34. package/firedrill/tools/unstructured/lib/util.mjs +149 -0
  35. package/firedrill/tools/unstructured/lib/validate.mjs +115 -0
  36. package/firedrill/tools/unstructured/lib/wire-multipart.mjs +78 -0
  37. package/firedrill/tools/unstructured/lib/wire.mjs +154 -0
  38. package/firedrill/tools/unstructured/ops/connectors.mjs +129 -0
  39. package/firedrill/tools/unstructured/ops/jobs.mjs +83 -0
  40. package/firedrill/tools/unstructured/ops/nodes.mjs +107 -0
  41. package/firedrill/tools/unstructured/ops/partition.mjs +112 -0
  42. package/firedrill/tools/unstructured/ops/workflows.mjs +180 -0
  43. package/firedrill/tools/unstructured/unstructured.tool.json +4892 -0
  44. package/firedrill/unstructured-archivist.drill.json +68 -0
  45. package/firedrill/unstructured-chunking.drill.json +67 -0
  46. package/firedrill/unstructured-connectors.drill.json +121 -0
  47. package/firedrill/unstructured-denied.drill.json +58 -0
  48. package/firedrill/unstructured-fresh-actor.drill.json +68 -0
  49. package/firedrill/unstructured-overloaded.drill.json +51 -0
  50. package/firedrill/unstructured-partition-errors.drill.json +66 -0
  51. package/firedrill/unstructured-partition.drill.json +95 -0
  52. package/firedrill/unstructured-rate-limited.drill.json +66 -0
  53. package/firedrill/unstructured-revoked-key.drill.json +773 -0
  54. package/firedrill/unstructured-run-lost.drill.json +51 -0
  55. package/firedrill/unstructured-small-responses.drill.json +173 -0
  56. package/firedrill/unstructured-tight-limits.drill.json +203 -0
  57. package/firedrill/unstructured-workflows-jobs.drill.json +167 -0
  58. package/firedrill/world.json +1556 -0
  59. package/firedrill.json +5 -0
  60. package/package.json +52 -0
  61. package/starter.json +1114 -0
  62. package/test/conformance.mjs +37 -0
  63. package/test/flows/access.mjs +54 -0
  64. package/test/flows/chunking.mjs +95 -0
  65. package/test/flows/connectors.mjs +76 -0
  66. package/test/flows/errors.mjs +115 -0
  67. package/test/flows/faults.mjs +73 -0
  68. package/test/flows/partition.mjs +225 -0
  69. package/test/flows/workflows.mjs +123 -0
  70. package/test/hostile-gen.mjs +0 -0
  71. package/test/hostile.mjs +155 -0
  72. package/test/lib.mjs +113 -0
@@ -0,0 +1,51 @@
1
+ {
2
+ "schemaVersion": 1,
3
+ "id": "unstructured-run-lost",
4
+ "title": "workflows.run commits the job and emits job.created, then answers 500; a naive retry creates a second job",
5
+ "targetId": "conformance-agent",
6
+ "scenarioId": "run-response-lost",
7
+ "actorId": "analyst",
8
+ "task": {
9
+ "instruction": "Run the run-lost flow against the synthetic Unstructured Tool and fail loudly on any unexpected status, header or body."
10
+ },
11
+ "assertions": [
12
+ {
13
+ "id": "workflows-run-tool_error-101",
14
+ "kind": "operation.count",
15
+ "operation": {
16
+ "packageId": "unstructured",
17
+ "operationId": "workflows.run"
18
+ },
19
+ "outcomes": [
20
+ "tool_error"
21
+ ],
22
+ "comparison": {
23
+ "operator": "equals",
24
+ "value": 2
25
+ }
26
+ },
27
+ {
28
+ "id": "job-created-events-102",
29
+ "kind": "event.count",
30
+ "event": {
31
+ "packageId": "unstructured",
32
+ "eventId": "job.created"
33
+ },
34
+ "phase": "emitted",
35
+ "comparison": {
36
+ "operator": "equals",
37
+ "value": 2
38
+ }
39
+ },
40
+ {
41
+ "id": "jobs-count-103",
42
+ "kind": "state.count",
43
+ "packageId": "unstructured",
44
+ "namespace": "jobs",
45
+ "comparison": {
46
+ "operator": "equals",
47
+ "value": 8
48
+ }
49
+ }
50
+ ]
51
+ }
@@ -0,0 +1,173 @@
1
+ {
2
+ "schemaVersion": 1,
3
+ "id": "unstructured-small-responses",
4
+ "title": "response_bytes lowered to 520: every list or page over the budget fails 413 RESPONSE_TOO_LARGE, never a shortened 200; filtered lists, small pages and point reads still work",
5
+ "targetId": "conformance-agent",
6
+ "scenarioId": "small-responses",
7
+ "actorId": "analyst",
8
+ "task": {
9
+ "instruction": "Run the small-responses flow against the synthetic Unstructured Tool and fail loudly on any unexpected status, header or body."
10
+ },
11
+ "assertions": [
12
+ {
13
+ "id": "sources-list-ok-117",
14
+ "kind": "operation.count",
15
+ "operation": {
16
+ "packageId": "unstructured",
17
+ "operationId": "sources.list"
18
+ },
19
+ "outcomes": [
20
+ "ok"
21
+ ],
22
+ "comparison": {
23
+ "operator": "greater_than_or_equal",
24
+ "value": 1
25
+ }
26
+ },
27
+ {
28
+ "id": "destinations-list-ok-118",
29
+ "kind": "operation.count",
30
+ "operation": {
31
+ "packageId": "unstructured",
32
+ "operationId": "destinations.list"
33
+ },
34
+ "outcomes": [
35
+ "ok"
36
+ ],
37
+ "comparison": {
38
+ "operator": "greater_than_or_equal",
39
+ "value": 1
40
+ }
41
+ },
42
+ {
43
+ "id": "workflows-list-ok-119",
44
+ "kind": "operation.count",
45
+ "operation": {
46
+ "packageId": "unstructured",
47
+ "operationId": "workflows.list"
48
+ },
49
+ "outcomes": [
50
+ "ok"
51
+ ],
52
+ "comparison": {
53
+ "operator": "greater_than_or_equal",
54
+ "value": 1
55
+ }
56
+ },
57
+ {
58
+ "id": "jobs-list-ok-120",
59
+ "kind": "operation.count",
60
+ "operation": {
61
+ "packageId": "unstructured",
62
+ "operationId": "jobs.list"
63
+ },
64
+ "outcomes": [
65
+ "ok"
66
+ ],
67
+ "comparison": {
68
+ "operator": "greater_than_or_equal",
69
+ "value": 1
70
+ }
71
+ },
72
+ {
73
+ "id": "sources-list-tool_error-121",
74
+ "kind": "operation.count",
75
+ "operation": {
76
+ "packageId": "unstructured",
77
+ "operationId": "sources.list"
78
+ },
79
+ "outcomes": [
80
+ "tool_error"
81
+ ],
82
+ "comparison": {
83
+ "operator": "equals",
84
+ "value": 3
85
+ }
86
+ },
87
+ {
88
+ "id": "destinations-list-tool_error-122",
89
+ "kind": "operation.count",
90
+ "operation": {
91
+ "packageId": "unstructured",
92
+ "operationId": "destinations.list"
93
+ },
94
+ "outcomes": [
95
+ "tool_error"
96
+ ],
97
+ "comparison": {
98
+ "operator": "equals",
99
+ "value": 1
100
+ }
101
+ },
102
+ {
103
+ "id": "workflows-list-tool_error-123",
104
+ "kind": "operation.count",
105
+ "operation": {
106
+ "packageId": "unstructured",
107
+ "operationId": "workflows.list"
108
+ },
109
+ "outcomes": [
110
+ "tool_error"
111
+ ],
112
+ "comparison": {
113
+ "operator": "equals",
114
+ "value": 5
115
+ }
116
+ },
117
+ {
118
+ "id": "jobs-list-tool_error-124",
119
+ "kind": "operation.count",
120
+ "operation": {
121
+ "packageId": "unstructured",
122
+ "operationId": "jobs.list"
123
+ },
124
+ "outcomes": [
125
+ "tool_error"
126
+ ],
127
+ "comparison": {
128
+ "operator": "equals",
129
+ "value": 2
130
+ }
131
+ },
132
+ {
133
+ "id": "workflows-get-ok-125",
134
+ "kind": "operation.count",
135
+ "operation": {
136
+ "packageId": "unstructured",
137
+ "operationId": "workflows.get"
138
+ },
139
+ "outcomes": [
140
+ "ok"
141
+ ],
142
+ "comparison": {
143
+ "operator": "equals",
144
+ "value": 1
145
+ }
146
+ },
147
+ {
148
+ "id": "sources-create-ok-126",
149
+ "kind": "operation.count",
150
+ "operation": {
151
+ "packageId": "unstructured",
152
+ "operationId": "sources.create"
153
+ },
154
+ "outcomes": [
155
+ "ok"
156
+ ],
157
+ "comparison": {
158
+ "operator": "equals",
159
+ "value": 1
160
+ }
161
+ },
162
+ {
163
+ "id": "sources-count-127",
164
+ "kind": "state.count",
165
+ "packageId": "unstructured",
166
+ "namespace": "sources",
167
+ "comparison": {
168
+ "operator": "equals",
169
+ "value": 5
170
+ }
171
+ }
172
+ ]
173
+ }
@@ -0,0 +1,203 @@
1
+ {
2
+ "schemaVersion": 1,
3
+ "id": "unstructured-tight-limits",
4
+ "title": "With meta/limits lowered every bounded scan fails INTERNAL_ERROR instead of truncating; point reads and scan-free writes still work",
5
+ "targetId": "conformance-agent",
6
+ "scenarioId": "tight-limits",
7
+ "actorId": "analyst",
8
+ "task": {
9
+ "instruction": "Run the tight-limits flow against the synthetic Unstructured Tool and fail loudly on any unexpected status, header or body."
10
+ },
11
+ "assertions": [
12
+ {
13
+ "id": "sources-list-tool_error-104",
14
+ "kind": "operation.count",
15
+ "operation": {
16
+ "packageId": "unstructured",
17
+ "operationId": "sources.list"
18
+ },
19
+ "outcomes": [
20
+ "tool_error"
21
+ ],
22
+ "comparison": {
23
+ "operator": "greater_than_or_equal",
24
+ "value": 1
25
+ }
26
+ },
27
+ {
28
+ "id": "destinations-list-tool_error-105",
29
+ "kind": "operation.count",
30
+ "operation": {
31
+ "packageId": "unstructured",
32
+ "operationId": "destinations.list"
33
+ },
34
+ "outcomes": [
35
+ "tool_error"
36
+ ],
37
+ "comparison": {
38
+ "operator": "greater_than_or_equal",
39
+ "value": 1
40
+ }
41
+ },
42
+ {
43
+ "id": "workflows-list-tool_error-106",
44
+ "kind": "operation.count",
45
+ "operation": {
46
+ "packageId": "unstructured",
47
+ "operationId": "workflows.list"
48
+ },
49
+ "outcomes": [
50
+ "tool_error"
51
+ ],
52
+ "comparison": {
53
+ "operator": "greater_than_or_equal",
54
+ "value": 1
55
+ }
56
+ },
57
+ {
58
+ "id": "jobs-list-tool_error-107",
59
+ "kind": "operation.count",
60
+ "operation": {
61
+ "packageId": "unstructured",
62
+ "operationId": "jobs.list"
63
+ },
64
+ "outcomes": [
65
+ "tool_error"
66
+ ],
67
+ "comparison": {
68
+ "operator": "greater_than_or_equal",
69
+ "value": 1
70
+ }
71
+ },
72
+ {
73
+ "id": "sources-create-tool_error-108",
74
+ "kind": "operation.count",
75
+ "operation": {
76
+ "packageId": "unstructured",
77
+ "operationId": "sources.create"
78
+ },
79
+ "outcomes": [
80
+ "tool_error"
81
+ ],
82
+ "comparison": {
83
+ "operator": "greater_than_or_equal",
84
+ "value": 1
85
+ }
86
+ },
87
+ {
88
+ "id": "destinations-create-tool_error-109",
89
+ "kind": "operation.count",
90
+ "operation": {
91
+ "packageId": "unstructured",
92
+ "operationId": "destinations.create"
93
+ },
94
+ "outcomes": [
95
+ "tool_error"
96
+ ],
97
+ "comparison": {
98
+ "operator": "greater_than_or_equal",
99
+ "value": 1
100
+ }
101
+ },
102
+ {
103
+ "id": "workflows-create-tool_error-110",
104
+ "kind": "operation.count",
105
+ "operation": {
106
+ "packageId": "unstructured",
107
+ "operationId": "workflows.create"
108
+ },
109
+ "outcomes": [
110
+ "tool_error"
111
+ ],
112
+ "comparison": {
113
+ "operator": "greater_than_or_equal",
114
+ "value": 1
115
+ }
116
+ },
117
+ {
118
+ "id": "sources-delete-tool_error-111",
119
+ "kind": "operation.count",
120
+ "operation": {
121
+ "packageId": "unstructured",
122
+ "operationId": "sources.delete"
123
+ },
124
+ "outcomes": [
125
+ "tool_error"
126
+ ],
127
+ "comparison": {
128
+ "operator": "greater_than_or_equal",
129
+ "value": 1
130
+ }
131
+ },
132
+ {
133
+ "id": "destinations-delete-tool_error-112",
134
+ "kind": "operation.count",
135
+ "operation": {
136
+ "packageId": "unstructured",
137
+ "operationId": "destinations.delete"
138
+ },
139
+ "outcomes": [
140
+ "tool_error"
141
+ ],
142
+ "comparison": {
143
+ "operator": "greater_than_or_equal",
144
+ "value": 1
145
+ }
146
+ },
147
+ {
148
+ "id": "workflows-delete-tool_error-113",
149
+ "kind": "operation.count",
150
+ "operation": {
151
+ "packageId": "unstructured",
152
+ "operationId": "workflows.delete"
153
+ },
154
+ "outcomes": [
155
+ "tool_error"
156
+ ],
157
+ "comparison": {
158
+ "operator": "greater_than_or_equal",
159
+ "value": 1
160
+ }
161
+ },
162
+ {
163
+ "id": "workflows-run-tool_error-114",
164
+ "kind": "operation.count",
165
+ "operation": {
166
+ "packageId": "unstructured",
167
+ "operationId": "workflows.run"
168
+ },
169
+ "outcomes": [
170
+ "tool_error"
171
+ ],
172
+ "comparison": {
173
+ "operator": "greater_than_or_equal",
174
+ "value": 1
175
+ }
176
+ },
177
+ {
178
+ "id": "sources-create-ok-115",
179
+ "kind": "operation.count",
180
+ "operation": {
181
+ "packageId": "unstructured",
182
+ "operationId": "sources.create"
183
+ },
184
+ "outcomes": [
185
+ "ok"
186
+ ],
187
+ "comparison": {
188
+ "operator": "equals",
189
+ "value": 1
190
+ }
191
+ },
192
+ {
193
+ "id": "sources-count-116",
194
+ "kind": "state.count",
195
+ "packageId": "unstructured",
196
+ "namespace": "sources",
197
+ "comparison": {
198
+ "operator": "equals",
199
+ "value": 5
200
+ }
201
+ }
202
+ ]
203
+ }
@@ -0,0 +1,167 @@
1
+ {
2
+ "schemaVersion": 1,
3
+ "id": "unstructured-workflows-jobs",
4
+ "title": "Workflows and jobs: list/sort/page, node rules, run with source and runtime files, derived statuses, download equals direct partition, cancel, delete rules",
5
+ "targetId": "conformance-agent",
6
+ "scenarioId": "baseline",
7
+ "actorId": "analyst",
8
+ "task": {
9
+ "instruction": "Run the workflows flow against the synthetic Unstructured Tool and fail loudly on any unexpected status, header or body."
10
+ },
11
+ "assertions": [
12
+ {
13
+ "id": "job-created-events-23",
14
+ "kind": "event.count",
15
+ "event": {
16
+ "packageId": "unstructured",
17
+ "eventId": "job.created"
18
+ },
19
+ "phase": "emitted",
20
+ "comparison": {
21
+ "operator": "equals",
22
+ "value": 2
23
+ }
24
+ },
25
+ {
26
+ "id": "job-cancelled-events-24",
27
+ "kind": "event.count",
28
+ "event": {
29
+ "packageId": "unstructured",
30
+ "eventId": "job.cancelled"
31
+ },
32
+ "phase": "emitted",
33
+ "comparison": {
34
+ "operator": "equals",
35
+ "value": 1
36
+ }
37
+ },
38
+ {
39
+ "id": "jobs-value-25",
40
+ "kind": "state.value",
41
+ "packageId": "unstructured",
42
+ "namespace": "jobs",
43
+ "rowId": "e5f60718-7a92-4b3c-9d4e-f60718293a05",
44
+ "path": [
45
+ "stop_requested"
46
+ ],
47
+ "comparison": {
48
+ "operator": "equals",
49
+ "value": true
50
+ }
51
+ },
52
+ {
53
+ "id": "workflows-count-26",
54
+ "kind": "state.count",
55
+ "packageId": "unstructured",
56
+ "namespace": "workflows",
57
+ "comparison": {
58
+ "operator": "equals",
59
+ "value": 6
60
+ }
61
+ },
62
+ {
63
+ "id": "jobs-count-27",
64
+ "kind": "state.count",
65
+ "packageId": "unstructured",
66
+ "namespace": "jobs",
67
+ "comparison": {
68
+ "operator": "equals",
69
+ "value": 8
70
+ }
71
+ },
72
+ {
73
+ "id": "job-files-count-28",
74
+ "kind": "state.count",
75
+ "packageId": "unstructured",
76
+ "namespace": "job-files",
77
+ "comparison": {
78
+ "operator": "equals",
79
+ "value": 2
80
+ }
81
+ },
82
+ {
83
+ "id": "workflows-run-ok-29",
84
+ "kind": "operation.count",
85
+ "operation": {
86
+ "packageId": "unstructured",
87
+ "operationId": "workflows.run"
88
+ },
89
+ "outcomes": [
90
+ "ok"
91
+ ],
92
+ "comparison": {
93
+ "operator": "equals",
94
+ "value": 2
95
+ }
96
+ },
97
+ {
98
+ "id": "jobs-download-output-ok-30",
99
+ "kind": "operation.count",
100
+ "operation": {
101
+ "packageId": "unstructured",
102
+ "operationId": "jobs.download_output"
103
+ },
104
+ "outcomes": [
105
+ "ok"
106
+ ],
107
+ "comparison": {
108
+ "operator": "equals",
109
+ "value": 1
110
+ }
111
+ },
112
+ {
113
+ "id": "order-31",
114
+ "kind": "operation.order",
115
+ "sequence": [
116
+ {
117
+ "anyOf": [
118
+ {
119
+ "packageId": "unstructured",
120
+ "operationId": "workflows.create"
121
+ }
122
+ ]
123
+ },
124
+ {
125
+ "anyOf": [
126
+ {
127
+ "packageId": "unstructured",
128
+ "operationId": "workflows.run"
129
+ }
130
+ ]
131
+ },
132
+ {
133
+ "anyOf": [
134
+ {
135
+ "packageId": "unstructured",
136
+ "operationId": "jobs.get"
137
+ }
138
+ ]
139
+ },
140
+ {
141
+ "anyOf": [
142
+ {
143
+ "packageId": "unstructured",
144
+ "operationId": "jobs.download_output"
145
+ }
146
+ ]
147
+ },
148
+ {
149
+ "anyOf": [
150
+ {
151
+ "packageId": "unstructured",
152
+ "operationId": "jobs.cancel"
153
+ }
154
+ ]
155
+ },
156
+ {
157
+ "anyOf": [
158
+ {
159
+ "packageId": "unstructured",
160
+ "operationId": "workflows.delete"
161
+ }
162
+ ]
163
+ }
164
+ ]
165
+ }
166
+ ]
167
+ }