PlanOpticon

Phase 1: Add pydantic data models and standardized output structure Stories 1.1-1.4: Pydantic models for all output types (DiagramResult, ScreenCapture, TranscriptSegment, ActionItem, KeyPoint, Entity, Relationship, KnowledgeGraphData, VideoManifest, BatchManifest), standardized video/batch output directory layout, and manifest I/O helpers.

leo 2026-02-14 22:11 trunk

Commit b2df90efa9defc9d4fd85c44845818c0329dc6c7a746572118f742c1345b3c16

Parent cfb7e1815723cfd…

4 files changed +9 +144 +190 +56

+ tests/test_models.py + tests/test_output_structure.py + video_processor/models.py + video_processor/output_structure.py

A tests/test_models.py

		--- a/tests/test_models.py
		+++ b/tests/test_models.py
		@@ -0,0 +1,9 @@
	1	+"""Tests forimport json
	2	+
	3	+import pytestor pydantic data models."""
	4	+
	5	+from video_processor.models import (
	6	+ ActionItem,
	7	+ BatchManifest,
	8	+ BatchVideoEntry,
	9	+ Di7 Di"""Tests f confidence=0.45

	--- a/tests/test_models.py
	+++ b/tests/test_models.py
	@@ -0,0 +1,9 @@

	--- a/tests/test_models.py
	+++ b/tests/test_models.py
	@@ -0,0 +1,9 @@
1	"""Tests forimport json
2
3	import pytestor pydantic data models."""
4
5	from video_processor.models import (
6	ActionItem,
7	BatchManifest,
8	BatchVideoEntry,
9	Di7 Di"""Tests f confidence=0.45

A tests/test_output_structure.py

+144

		--- a/tests/test_output_structure.py
		+++ b/tests/test_output_structure.py
		@@ -0,0 +1,144 @@
	1	+"""Tests for output structure and manifest I/O."""
	2	+
	3	+import json
	4	+import tempfile
	5	+from pathlib"""Tests for output structure and manifest I/O."""
	6	+
	7	+import json
	8	+
	9	+from video_processor.models import (
	10	+ ActionItem,
	11	+ BatchManifest,
	12	+ BatchVideoEntry,
	13	+ DiagramResult,
	14	+ KeyPoint,
	15	+ ProcessingStats,
	16	+ VideoManifest,
	17	+ VideoMetadata,
	18	+)
	19	+from video_processor.output_structure import (
	20	+ create_batch_output_dirs,
	21	+ create_video_output_dirs,
	22	+ read_batch_manifest,
	23	+ read_video_manifest,
	24	+ write_batch_manifest,
	25	+ write_video_manifest,
	26	+)
	27	+
	28	+
	29	+class TestCreateVideoOutputDirs:
	30	+ def test_creates_all_directories(self, tmp_path):
	31	+ dirs = create_video_output_dirs(tmp_path / "output", "test_video")
	32	+ assert dirs["root"].exists()
	33	+ assert dirs["transcript"].exists()
	34	+ assert dirs["frames"].exists()
	35	+ assert dirs["diagrams"].exists()
	36	+ assert dirs["captures"].exists()
	37	+ assert dirs["results"].exists()
	38	+ assert dirs["cache"].exists()
	39	+
	40	+ def test_expected_layout(self, tmp_path):
	41	+ dirs = create_video_output_dirs(tmp_path / "output", "my_video")
	42	+ base = tmp_path / "output"
	43	+ assert dirs["transcript"] == base / "transcript"
	44	+ assert dirs["frames"] == base / "frames"
	45	+ assert dirs["diagrams"] == base / "diagrams"
	46	+ assert dirs["captures"] == base / "captures"
	47	+ assert dirs["results"] == base / "results"
	48	+ assert dirs["cache"] == base / "cache"
	49	+
	50	+ def test_idempotent(self, tmp_path):
	51	+ out = tmp_path / "output"
	52	+ dirs1 = create_video_output_dirs(out, "v")
	53	+ dirs2 = create_video_output_dirs(out, "v")
	54	+ assert dirs1 == dirs2
	55	+
	56	+
	57	+class TestCreateBatchOutputDirs:
	58	+ def test_creates_directories(self, tmp_path):
	59	+ dirs = create_batch_output_dirs(tmp_path / "batch", "my_batch")
	60	+ assert dirs["root"].exists()
	61	+ assert dirs["videos"].exists()
	62	+
	63	+ def test_expected_layout(self, tmp_path):
	64	+ dirs = create_batch_output_dirs(tmp_path / "batch", "b")
	65	+ base = tmp_path / "batch"
	66	+ assert dirs["videos"] == base / "videos"
	67	+
	68	+
	69	+class TestVideoManifestIO:
	70	+ def _sample_manifest(self) -> VideoManifest:
	71	+ return VideoManifest(
	72	+ video=VideoMetadata(title="Test", duration_seconds=120.0),
	73	+ stats=ProcessingStats(frames_extracted=10, diagrams_detected=2),
	74	+ transcript_json="transcript/transcript.json",
	75	+ analysis_md="results/analysis.md",
	76	+ key_points=[KeyPoint(point="Point 1")],
	77	+ action_items=[ActionItem(action="Do thing")],
	78	+ diagrams=[DiagramResult(frame_index=0, confidence=0.9)],
	79	+ )
	80	+
	81	+ def test_write_and_read(self, tmp_path):
	82	+ manifest = self._sample_manifest()
	83	+ write_video_manifest(manifest, tmp_path)
	84	+
	85	+ restored = read_video_manifest(tmp_path)
	86	+ assert restored.video.title == "Test"
	87	+ assert restored.stats.frames_extracted == 10
	88	+ assert len(restored.key_points) == 1
	89	+ assert len(restored.diagrams) == 1
	90	+
	91	+ def test_manifest_file_is_valid_json(self, tmp_path):
	92	+ manifest = self._sample_manifest()
	93	+ write_video_manifest(manifest, tmp_path)
	94	+
	95	+ path = tmp_path / "manifest.json"
	96	+ data = json.loads(path.read_text())
	97	+ assert data["version"] == "1.0"
	98	+ assert data["video"]["title"] == "Test"
	99	+
	100	+ def test_creates_parent_dirs(self, tmp_path):
	101	+ manifest = self._sample_manifest()
	102	+ nested = tmp_path / "a" / "b" / "c"
	103	+ write_video_manifest(manifest, nested)
	104	+ assert (nested / "manifest.json").exists()
	105	+
	106	+
	107	+class TestBatchManifestIO:
	108	+ def _sample_batch(self) -> BatchManifest:
	109	+ return BatchManifest(
	110	+ title="Test Batch",
	111	+ total_videos=2,
	112	+ completed_videos=2,
	113	+ videos=[
	114	+ BatchVideoEntry(
	115	+ video_name="v1",
	116	+ manifest_path="videos/v1/manifest.json",
	117	+ status="completed",
	118	+ ),
	119	+ BatchVideoEntry(
	120	+ video_name="v2",
	121	+ manifest_path="videos/v2/manifest.json",
	122	+ status="completed",
	123	+ ),
	124	+ ],
	125	+ batch_summary_md="batch_summary.md",
	126	+ )
	127	+
	128	+ def test_write_and_read(self, tmp_path):
	129	+ manifest = self._sample_batch()
	130	+ write_batch_manifest(manifest, tmp_path)
	131	+
	132	+ restored = read_batch_manifest(tmp_path)
	133	+ assert restored.title == "Test Batch"
	134	+ assert restored.total_videos == 2
	135	+ assert len(restored.videos) == 2
	136	+ assert restored.videos[0].video_name == "v1"
	137	+
	138	+ def test_manifest_file_is_valid_json(self, tmp_path):
	139	+ manifest = self._sample_batch()
	140	+ write_batch_manifest(manifest, tmp_path)
	141	+
	142	+ path = tmp_path / "manifest.json"
	143	+ data = json.loads(path.read_text())
	144	+ a

	--- a/tests/test_output_structure.py
	+++ b/tests/test_output_structure.py
	@@ -0,0 +1,144 @@

	--- a/tests/test_output_structure.py
	+++ b/tests/test_output_structure.py
	@@ -0,0 +1,144 @@
1	"""Tests for output structure and manifest I/O."""
2
3	import json
4	import tempfile
5	from pathlib"""Tests for output structure and manifest I/O."""
6
7	import json
8
9	from video_processor.models import (
10	ActionItem,
11	BatchManifest,
12	BatchVideoEntry,
13	DiagramResult,
14	KeyPoint,
15	ProcessingStats,
16	VideoManifest,
17	VideoMetadata,
18	)
19	from video_processor.output_structure import (
20	create_batch_output_dirs,
21	create_video_output_dirs,
22	read_batch_manifest,
23	read_video_manifest,
24	write_batch_manifest,
25	write_video_manifest,
26	)
27
28
29	class TestCreateVideoOutputDirs:
30	def test_creates_all_directories(self, tmp_path):
31	dirs = create_video_output_dirs(tmp_path / "output", "test_video")
32	assert dirs["root"].exists()
33	assert dirs["transcript"].exists()
34	assert dirs["frames"].exists()
35	assert dirs["diagrams"].exists()
36	assert dirs["captures"].exists()
37	assert dirs["results"].exists()
38	assert dirs["cache"].exists()
39
40	def test_expected_layout(self, tmp_path):
41	dirs = create_video_output_dirs(tmp_path / "output", "my_video")
42	base = tmp_path / "output"
43	assert dirs["transcript"] == base / "transcript"
44	assert dirs["frames"] == base / "frames"
45	assert dirs["diagrams"] == base / "diagrams"
46	assert dirs["captures"] == base / "captures"
47	assert dirs["results"] == base / "results"
48	assert dirs["cache"] == base / "cache"
49
50	def test_idempotent(self, tmp_path):
51	out = tmp_path / "output"
52	dirs1 = create_video_output_dirs(out, "v")
53	dirs2 = create_video_output_dirs(out, "v")
54	assert dirs1 == dirs2
55
56
57	class TestCreateBatchOutputDirs:
58	def test_creates_directories(self, tmp_path):
59	dirs = create_batch_output_dirs(tmp_path / "batch", "my_batch")
60	assert dirs["root"].exists()
61	assert dirs["videos"].exists()
62
63	def test_expected_layout(self, tmp_path):
64	dirs = create_batch_output_dirs(tmp_path / "batch", "b")
65	base = tmp_path / "batch"
66	assert dirs["videos"] == base / "videos"
67
68
69	class TestVideoManifestIO:
70	def _sample_manifest(self) -> VideoManifest:
71	return VideoManifest(
72	video=VideoMetadata(title="Test", duration_seconds=120.0),
73	stats=ProcessingStats(frames_extracted=10, diagrams_detected=2),
74	transcript_json="transcript/transcript.json",
75	analysis_md="results/analysis.md",
76	key_points=[KeyPoint(point="Point 1")],
77	action_items=[ActionItem(action="Do thing")],
78	diagrams=[DiagramResult(frame_index=0, confidence=0.9)],
79	)
80
81	def test_write_and_read(self, tmp_path):
82	manifest = self._sample_manifest()
83	write_video_manifest(manifest, tmp_path)
84
85	restored = read_video_manifest(tmp_path)
86	assert restored.video.title == "Test"
87	assert restored.stats.frames_extracted == 10
88	assert len(restored.key_points) == 1
89	assert len(restored.diagrams) == 1
90
91	def test_manifest_file_is_valid_json(self, tmp_path):
92	manifest = self._sample_manifest()
93	write_video_manifest(manifest, tmp_path)
94
95	path = tmp_path / "manifest.json"
96	data = json.loads(path.read_text())
97	assert data["version"] == "1.0"
98	assert data["video"]["title"] == "Test"
99
100	def test_creates_parent_dirs(self, tmp_path):
101	manifest = self._sample_manifest()
102	nested = tmp_path / "a" / "b" / "c"
103	write_video_manifest(manifest, nested)
104	assert (nested / "manifest.json").exists()
105
106
107	class TestBatchManifestIO:
108	def _sample_batch(self) -> BatchManifest:
109	return BatchManifest(
110	title="Test Batch",
111	total_videos=2,
112	completed_videos=2,
113	videos=[
114	BatchVideoEntry(
115	video_name="v1",
116	manifest_path="videos/v1/manifest.json",
117	status="completed",
118	),
119	BatchVideoEntry(
120	video_name="v2",
121	manifest_path="videos/v2/manifest.json",
122	status="completed",
123	),
124	],
125	batch_summary_md="batch_summary.md",
126	)
127
128	def test_write_and_read(self, tmp_path):
129	manifest = self._sample_batch()
130	write_batch_manifest(manifest, tmp_path)
131
132	restored = read_batch_manifest(tmp_path)
133	assert restored.title == "Test Batch"
134	assert restored.total_videos == 2
135	assert len(restored.videos) == 2
136	assert restored.videos[0].video_name == "v1"
137
138	def test_manifest_file_is_valid_json(self, tmp_path):
139	manifest = self._sample_batch()
140	write_batch_manifest(manifest, tmp_path)
141
142	path = tmp_path / "manifest.json"
143	data = json.loads(path.read_text())
144	a

A video_processor/models.py

+190

		--- a/video_processor/models.py
		+++ b/video_processor/models.py
		@@ -0,0 +1,190 @@
	1	+"""Pydantic data models for PlanOpticon output."""
	2	+
	3	+from datetime import datetime
	4	+pathlib import Pathetime
	5	+from enum import Enum
	6	+from typing import Any, Dict, List, OptionalProtocol, runti: str = "") -> None: ...
	7	+
	8	+
	9	+class DiagramType(str, Enum):
	10	+ "" flowchart = "flowchart"
	11	+ sequence = "sequence"
	12	+ architecture = "architecture"
	13	+ whiteboard = "whiteboard"
	14	+ chart = "chart"
	15	+ table = "table"
	16	+ slide = "slide"
	17	+ screenshot = "screenshot"
	18	+ unknown = "unknown"
	19	+
	20	+
	21	+class OutputFormat(str, Enum):
	22	+ """Av markdown = "markdown"
	23	+ json = "json"
	24	+ html = "html"
	25	+ pdf = "pdf"
	26	+ pdf"
	27	+ pptx = "pptx"
	28	+ svg = "svg"
	29	+ png = "png"
	30	+
	31	+
	32	+class TranscriptSegment(BaseModel):
	33	+ """A single segmen of transcribed audio."""
	34	+
	35	+ start: float = Field(description="Start time in seconds")
	36	+ end: float = Field(description="End time in seconds")
	37	+ text: str = Field(description="Transcribed text")
	38	+ speaker: Optional[str] = Field(default=None, description="Speaker identifier")
	39	+ confidence: Optional[float] = Field(default=None, description="Transcription confidence 0-1")
	40	+
	41	+
	42	+class ActionItem(BaseMod action="Relative path
	43	+ action: str = Field(description="The action to be taken")
	44	+ assignee: Optional[str] = Field(default=None, description="Person responsible")
	45	+ deadline: Optional[str] = Field(default=None, description="Deadline or timeframe")
	46	+ priority: Optional[str] = Field(default=None, description="Priority level")
	47	+ context: Optional[str] = Field(default=None, description="Additional context")
	48	+ souss ActionItem(BaseModel):
	49	+ default=None, d (transcript/diagram)"
	50	+ )
	51	+
	52	+
	53	+class KeyPoint(BaseModel):
	54	+ """A key point xtracted from content."""
	55	+
	56	+ point: str = Field(description="The key point")
	57	+ topic: Optional[str] = Field(default=None, description="Topic or category")
	58	+ details: Optional[str] = Field(default=None, description="Supporting details")
	59	+ timestamp: Optional[float] = Field(default=None, description="Timestamp in video (seconds)")
	60	+ source: Optional[str] = Field(default=None, description="Where thie, code, document, terminal, browse] = Field(
	61	+ default_f"""Pydantic data models for PlanOpticon output."""
	62	+
	63	+from datetime import datetime
	64	+from enummodels for PlanOpticon output."""
	65	+
	66	+from datetime import datetime
	67	+from enum import Enum
	68	+from typing import Any, Dict, List, OptionalProtocol, run in seconds")
	69	+ end: float = Field(description="End time in seconds")
	70	+ text: str = Field(description="Transcribed text")
	71	+ speaker: Optional[str] = Field(default=None, description="Speaker identifier")
	72	+ confidence: Optional[float] = Field(default=None, description="Transcription confidence 0-1")
	73	+
	74	+
	75	+class ActionItem(BaseModel):
	76	+ """An action item extracted from content."""
	77	+
	78	+ action: str = Field(description="The action to be taken")
	79	+ assignee: Optional[str] = Field(default=None, description="Person responsible")
	80	+ deadline: Optional[str] = Field(default=None, description="Deadline or timeframe")
	81	+ priority: Optional[str] = Field(default=None, description="Priority level")
	82	+ context: Optional
	83	+ vel")
	84	+ context: Optional[str] = Field(default=None, description="Additional context")
	85	+ source: Optional[str] = Field(
	86	+ default=None, description="Where this was found (transcript/diagram)"
	87	+ )
	88	+
	89	+
	90	+class KeyPoint(BaseModel):
	91	+ """A key point extracted from content."""
	92	+
	93	+ point: str = Field(description="The key point")
	94	+ topic: Optional[str] = Field(default=None, description="Topic or category")
	95	+ details: Optional[str] = Field(default=None, description="Supporting details")
	96	+ timestamp: Optional[float] = Field(default=None, description="Timestamp in vido (seconds)")
	97	+ source: Optional[str] = Field(default=None, description="Where this was found")
	98	+ related_diagrams: List[int] = Field(
	99	+ default_factory=list, description="Indices of related diagrams"
	100	+ )
	101	+
	102	+
	103	+class DiagramResult(BaseModel):
	104	+ """Result from diagram extraction and analysis."""
	105	+
	106	+ frame_index: int = Field(description="Index of the source frame")
	107	+ timestamtional[float] = Field(default=None, description="Transcription confidenModel):
	108	+ Field(default=None, description="Mermaid syntax representation nameot")
	109	+ confidelt=None, descriptia: Optional[Dict[str, Any]] = Field(
	110	+ default=None, description="Chart data for reproduction (labels, values, chart_type)"
	111	+ )
	112	+ image_path: Optional[str] = Field(default=None, description="Relative path tss ActionItem(BaseModel):
	113	+ path to rendered ] = Field(default=None, description="Relative path to rendered PNG")
	114	+ merma
	115	+ id_path: Optional[str] = Field(default=None, description="Relative path to mermaid source")
	116	+
	117	+
	118	+class ScreenCapture(BaseModel):
	119	+ """A screen ime
	120	+from enum import Enum
	121	+from typing import Any, Dict, List, OptionalProtocol, runti: str = "") -> None: ...
	122	+
	123	+
	124	+class DiagramType(str, Enum):
	125	+ """Types of visual content detected in video frames."""
	126	+
	127	+ flowchart = "flowchart"
	128	+ sequence = "sequence"
	129	+ architecture = "architecture"
	130	+ whiteboard = "whiteboard"
	131	+ chart = "chart"
	132	+ table = "table"
	133	+ slide = "slide"
	134	+ screenshot = "screenshot"
	135	+ unknown = "unknown"
	136	+
	137	+
	138	+class OutputFormat(str, En"""Pydantic data models for PlanOpticon output."""
	139	+
	140	+from datetime import datetime
	141	+from enum import Enum
	142	+from typing import Any, Dict, Lie, code, document, terminal, eyPoint(B, description="Text visible in the diagram")
	143	+ elements: List[str] = F elements: List[str] = Field(default_factory=list, description="Identified elements")
	144	+ relationships: List[str] = Field(default_factory=list, description="Identified relationships")
	145	+ mermaid: Optional[str] = Field(default=None, description="Mermaid syntax representation")
	146	+ chart_data: Opti default=None, description="Chart data for reproduction (labels, values, chart_type)"
	147	+ )
	148	+ image_path: Optional[str] = Field(default=None, description="Relative path to original frame")
	149	+ svg_path: Optional[str] = Field(default=None, description="Relative path to rendered SVG")
	150	+ png
	151	+ ""Pydantic con output."""
	152	+
	153	+from datetime import datetime
	154	+from enum import Enum
	155	+from typing import Any, Dict, List, Optionaantic data models for PlanOpticon output."""
	156	+
	157	+from datetime import datetime
	158	+from enum import Enum
	159	+from typing import Any, Dict, List, OptionalProtocol, runti: str = "") -> None: ...
	160	+
	161	+
	162	+class DiagramType(str, Enum):
	163	+ """Types of visual content detected in video frames."""
	164	+
	165	+ flowchart = "flowchart"
	166	+ sequence = "sequence"
	167	+ architecture = "architecture"
	168	+ whiteboard = "whiteboard"
	169	+ chart = "chart"
	170	+ table = "table"
	171	+ slide = "slide"
	172	+ screenshot = "screensr] = Field(default=None, description="Brief description of the content")
	173	+ image_path: Optional= Field(
	174	+ default=0.0, description="Detection confidence that triggered fallback"
	175	+ )
	176	+ content_type: Optional[str] = Field(
	177	+ default=None,
	178	+ description="Content type: slide, code, document, terminal, browser, chat, other",
	179	+ )
	180	+ eyPoint(B, description="Text visible in the diagram")
	181	+ elements: List[str] = Field(default_factory=list, description="Identified elements")
	182	+ relationships: List[str] = Field(default_factory=list, description="Identified relationships")
	183	+ mermaid: Optional[str] = Field(default=None, description="Mermaid syntax representation")
	184	+ chart_data: Opti default=None, description="Chart data for reproduction (labels, values, chart_type)"
	185	+ )
	186	+ image_path: Optional[str] = Field(default=None, description="Relative path to original frame")
	187	+ svg_path: Optional[str] = Field(default=None, description="Relative path to rendered SVG")
	188	+ png_path: Optional[str] = Field(default=None, description="Relative path to rendered PNG")
	189	+ mermaid_path: Optional[str] = Field(defae, code, document, terminal, browseption="Timestamp in video (second
	190	+

	--- a/video_processor/models.py
	+++ b/video_processor/models.py
	@@ -0,0 +1,190 @@

	--- a/video_processor/models.py
	+++ b/video_processor/models.py
	@@ -0,0 +1,190 @@
1	"""Pydantic data models for PlanOpticon output."""
2
3	from datetime import datetime
4	pathlib import Pathetime
5	from enum import Enum
6	from typing import Any, Dict, List, OptionalProtocol, runti: str = "") -> None: ...
7
8
9	class DiagramType(str, Enum):
10	"" flowchart = "flowchart"
11	sequence = "sequence"
12	architecture = "architecture"
13	whiteboard = "whiteboard"
14	chart = "chart"
15	table = "table"
16	slide = "slide"
17	screenshot = "screenshot"
18	unknown = "unknown"
19
20
21	class OutputFormat(str, Enum):
22	"""Av markdown = "markdown"
23	json = "json"
24	html = "html"
25	pdf = "pdf"
26	pdf"
27	pptx = "pptx"
28	svg = "svg"
29	png = "png"
30
31
32	class TranscriptSegment(BaseModel):
33	"""A single segmen of transcribed audio."""
34
35	start: float = Field(description="Start time in seconds")
36	end: float = Field(description="End time in seconds")
37	text: str = Field(description="Transcribed text")
38	speaker: Optional[str] = Field(default=None, description="Speaker identifier")
39	confidence: Optional[float] = Field(default=None, description="Transcription confidence 0-1")
40
41
42	class ActionItem(BaseMod action="Relative path
43	action: str = Field(description="The action to be taken")
44	assignee: Optional[str] = Field(default=None, description="Person responsible")
45	deadline: Optional[str] = Field(default=None, description="Deadline or timeframe")
46	priority: Optional[str] = Field(default=None, description="Priority level")
47	context: Optional[str] = Field(default=None, description="Additional context")
48	souss ActionItem(BaseModel):
49	default=None, d (transcript/diagram)"
50	)
51
52
53	class KeyPoint(BaseModel):
54	"""A key point xtracted from content."""
55
56	point: str = Field(description="The key point")
57	topic: Optional[str] = Field(default=None, description="Topic or category")
58	details: Optional[str] = Field(default=None, description="Supporting details")
59	timestamp: Optional[float] = Field(default=None, description="Timestamp in video (seconds)")
60	source: Optional[str] = Field(default=None, description="Where thie, code, document, terminal, browse] = Field(
61	default_f"""Pydantic data models for PlanOpticon output."""
62
63	from datetime import datetime
64	from enummodels for PlanOpticon output."""
65
66	from datetime import datetime
67	from enum import Enum
68	from typing import Any, Dict, List, OptionalProtocol, run in seconds")
69	end: float = Field(description="End time in seconds")
70	text: str = Field(description="Transcribed text")
71	speaker: Optional[str] = Field(default=None, description="Speaker identifier")
72	confidence: Optional[float] = Field(default=None, description="Transcription confidence 0-1")
73
74
75	class ActionItem(BaseModel):
76	"""An action item extracted from content."""
77
78	action: str = Field(description="The action to be taken")
79	assignee: Optional[str] = Field(default=None, description="Person responsible")
80	deadline: Optional[str] = Field(default=None, description="Deadline or timeframe")
81	priority: Optional[str] = Field(default=None, description="Priority level")
82	context: Optional
83	vel")
84	context: Optional[str] = Field(default=None, description="Additional context")
85	source: Optional[str] = Field(
86	default=None, description="Where this was found (transcript/diagram)"
87	)
88
89
90	class KeyPoint(BaseModel):
91	"""A key point extracted from content."""
92
93	point: str = Field(description="The key point")
94	topic: Optional[str] = Field(default=None, description="Topic or category")
95	details: Optional[str] = Field(default=None, description="Supporting details")
96	timestamp: Optional[float] = Field(default=None, description="Timestamp in vido (seconds)")
97	source: Optional[str] = Field(default=None, description="Where this was found")
98	related_diagrams: List[int] = Field(
99	default_factory=list, description="Indices of related diagrams"
100	)
101
102
103	class DiagramResult(BaseModel):
104	"""Result from diagram extraction and analysis."""
105
106	frame_index: int = Field(description="Index of the source frame")
107	timestamtional[float] = Field(default=None, description="Transcription confidenModel):
108	Field(default=None, description="Mermaid syntax representation nameot")
109	confidelt=None, descriptia: Optional[Dict[str, Any]] = Field(
110	default=None, description="Chart data for reproduction (labels, values, chart_type)"
111	)
112	image_path: Optional[str] = Field(default=None, description="Relative path tss ActionItem(BaseModel):
113	path to rendered ] = Field(default=None, description="Relative path to rendered PNG")
114	merma
115	id_path: Optional[str] = Field(default=None, description="Relative path to mermaid source")
116
117
118	class ScreenCapture(BaseModel):
119	"""A screen ime
120	from enum import Enum
121	from typing import Any, Dict, List, OptionalProtocol, runti: str = "") -> None: ...
122
123
124	class DiagramType(str, Enum):
125	"""Types of visual content detected in video frames."""
126
127	flowchart = "flowchart"
128	sequence = "sequence"
129	architecture = "architecture"
130	whiteboard = "whiteboard"
131	chart = "chart"
132	table = "table"
133	slide = "slide"
134	screenshot = "screenshot"
135	unknown = "unknown"
136
137
138	class OutputFormat(str, En"""Pydantic data models for PlanOpticon output."""
139
140	from datetime import datetime
141	from enum import Enum
142	from typing import Any, Dict, Lie, code, document, terminal, eyPoint(B, description="Text visible in the diagram")
143	elements: List[str] = F elements: List[str] = Field(default_factory=list, description="Identified elements")
144	relationships: List[str] = Field(default_factory=list, description="Identified relationships")
145	mermaid: Optional[str] = Field(default=None, description="Mermaid syntax representation")
146	chart_data: Opti default=None, description="Chart data for reproduction (labels, values, chart_type)"
147	)
148	image_path: Optional[str] = Field(default=None, description="Relative path to original frame")
149	svg_path: Optional[str] = Field(default=None, description="Relative path to rendered SVG")
150	png
151	""Pydantic con output."""
152
153	from datetime import datetime
154	from enum import Enum
155	from typing import Any, Dict, List, Optionaantic data models for PlanOpticon output."""
156
157	from datetime import datetime
158	from enum import Enum
159	from typing import Any, Dict, List, OptionalProtocol, runti: str = "") -> None: ...
160
161
162	class DiagramType(str, Enum):
163	"""Types of visual content detected in video frames."""
164
165	flowchart = "flowchart"
166	sequence = "sequence"
167	architecture = "architecture"
168	whiteboard = "whiteboard"
169	chart = "chart"
170	table = "table"
171	slide = "slide"
172	screenshot = "screensr] = Field(default=None, description="Brief description of the content")
173	image_path: Optional= Field(
174	default=0.0, description="Detection confidence that triggered fallback"
175	)
176	content_type: Optional[str] = Field(
177	default=None,
178	description="Content type: slide, code, document, terminal, browser, chat, other",
179	)
180	eyPoint(B, description="Text visible in the diagram")
181	elements: List[str] = Field(default_factory=list, description="Identified elements")
182	relationships: List[str] = Field(default_factory=list, description="Identified relationships")
183	mermaid: Optional[str] = Field(default=None, description="Mermaid syntax representation")
184	chart_data: Opti default=None, description="Chart data for reproduction (labels, values, chart_type)"
185	)
186	image_path: Optional[str] = Field(default=None, description="Relative path to original frame")
187	svg_path: Optional[str] = Field(default=None, description="Relative path to rendered SVG")
188	png_path: Optional[str] = Field(default=None, description="Relative path to rendered PNG")
189	mermaid_path: Optional[str] = Field(defae, code, document, terminal, browseption="Timestamp in video (second
190

A video_processor/output_structure.py

+56

		--- a/video_processor/output_structure.py
		+++ b/video_processor/output_structure.py
		@@ -0,0 +1,56 @@
	1	+"""Standardized output directory structure and manifest I/O for PlanOpticon."""
	2	+
	3	+import json
	4	+import logging
	5	+from pathlib import Path
	6	+from typing import Dict
	7	+
	8	+from video_processor.models import BatchManifest, VideoManifest
	9	+
	10	+logger = logging.getLogger(__name__)
	11	+
	12	+
	13	+def create_video_output_dirs(output_dir: str \| Path, video_name: str) -> Dict[str, Path]:
	14	+ """
	15	+ Create standardized single-video output directory structure.
	16	+
	17	+ Layout:
	18	+ output_dir/
	19	+ manifest.json
	20	+ transcript/
	21	+ transcript.json, .txt, .srt
	22	+ frames/
	23	+ frame_0000.jpg ...
	24	+ diagrams/
	25	+ diagram_0.json, .jpg, .mermaid, .svg, .png
	26	+ captures/
	27	+ capture_0.jpg, capture_0.json
	28	+ results/
	29	+ analysis.md, .html, .pdf
	30	+ knowledge_graph.ry structure and mani"s/
	31	+ video_1/manifest.json
	32	+ video_2/manifest.json
	33	+ ...
	34	+
	35	+ Returns dict mapping directory names to Path objects.
	36	+ """
	37	+ base = Path(output_dir)
	38	+ dirs = {
	39	+ "root": base,
	40	+ "videos": base / "videos",
	41	+ }
	42	+ for d in dirs.values():
	43	+ d.mkdir(parents=True, exist_ok=True)
	44	+ logger.info(f"Created batch output structure for '{batch_name}' at {base}")
	45	+ return dirs
	46	+
	47	+
	48	+# --- Manifest I/O ---
	49	+
	50	+
	51	+def write_video_manifest(manifest: VideoManifest, output_dir: str \| Path) -> Path:
	52	+ """Write a VideoManifest to output_dir/manifest.json."""
	53	+ path = Path(output_dir) / "manifest.json"
	54	+ path.parent.mkdir(parents=True, exist_ok=True)
	55	+ path.write_text(manifest.model_dump_json(indent=2))
	56	+ logger.info(f"Wrote video manifest to {pa

	--- a/video_processor/output_structure.py
	+++ b/video_processor/output_structure.py
	@@ -0,0 +1,56 @@

	--- a/video_processor/output_structure.py
	+++ b/video_processor/output_structure.py
	@@ -0,0 +1,56 @@
1	"""Standardized output directory structure and manifest I/O for PlanOpticon."""
2
3	import json
4	import logging
5	from pathlib import Path
6	from typing import Dict
7
8	from video_processor.models import BatchManifest, VideoManifest
9
10	logger = logging.getLogger(__name__)
11
12
13	def create_video_output_dirs(output_dir: str \| Path, video_name: str) -> Dict[str, Path]:
14	"""
15	Create standardized single-video output directory structure.
16
17	Layout:
18	output_dir/
19	manifest.json
20	transcript/
21	transcript.json, .txt, .srt
22	frames/
23	frame_0000.jpg ...
24	diagrams/
25	diagram_0.json, .jpg, .mermaid, .svg, .png
26	captures/
27	capture_0.jpg, capture_0.json
28	results/
29	analysis.md, .html, .pdf
30	knowledge_graph.ry structure and mani"s/
31	video_1/manifest.json
32	video_2/manifest.json
33	...
34
35	Returns dict mapping directory names to Path objects.
36	"""
37	base = Path(output_dir)
38	dirs = {
39	"root": base,
40	"videos": base / "videos",
41	}
42	for d in dirs.values():
43	d.mkdir(parents=True, exist_ok=True)
44	logger.info(f"Created batch output structure for '{batch_name}' at {base}")
45	return dirs
46
47
48	# --- Manifest I/O ---
49
50
51	def write_video_manifest(manifest: VideoManifest, output_dir: str \| Path) -> Path:
52	"""Write a VideoManifest to output_dir/manifest.json."""
53	path = Path(output_dir) / "manifest.json"
54	path.parent.mkdir(parents=True, exist_ok=True)
55	path.write_text(manifest.model_dump_json(indent=2))
56	logger.info(f"Wrote video manifest to {pa

PlanOpticon

Keyboard Shortcuts