2026-05-27 07:43:53 +00:00
|
|
|
-- Migration: 000054_knowledge_processing_spans
|
2026-05-27 07:31:32 +00:00
|
|
|
-- Per-(knowledge, attempt) span tree for the document parsing pipeline,
|
|
|
|
|
-- inspired by Langfuse's trace / span / generation hierarchy.
|
refactor(knowledge): replace flat stage table with langfuse-style span tree
Addresses review feedback that the PR② design had four shortcomings:
1. The pipeline is a DAG, not a sequence — Embedding and Multimodal
are independent of each other, both downstream of Chunking, both
upstream of PostProcess. The flat (knowledge_id, stage) table
couldn't represent that, so a Chunking failure left dependents
stranded as "pending" forever instead of being marked as
impossible-to-run.
2. No history across attempts. A reparse erased the previous run's
status before the new run started, leaving operators with no way
to investigate "why did this fail twice?".
3. Stages had only status + duration. Operators want to know how big
the work was — pages parsed, chunks created, tokens embedded, VLM
calls made — to distinguish "slow because the file is huge" from
"slow because the docreader is wedged".
4. Multimodal fans out N image tasks; Embedding fans out M batches;
PostProcess fans out into Summary/Question/Wiki/Graph. Each unit
is interesting on its own (Langfuse already captures this for
LLM calls). The flat model couldn't express it.
The redesign mirrors Langfuse's trace/span/generation hierarchy:
* Migration 000053 supersedes 000052: knowledge_processing_spans
table with (knowledge_id, attempt, span_id) primary key, plus
parent_span_id, kind ∈ {root, stage, subspan, generation},
status ∈ {pending,running,done,failed,skipped,cancelled}, and
JSONB input/output/metadata fields.
* SpanTracker (replacing StageTracker) exposes OpenAttempt /
BeginStage / BeginSubSpan / EndSpan / FailSpan / SkipSpan /
LookupStage. Cross-process workers (image_multimodal) get the
parent's attempt + span via payload + LookupStage so subspans
attach correctly.
* StageDependencies declares the DAG; FailSpan now cascades —
descendants of the failed span and dependent stages are flipped
to "cancelled" with a UPSTREAM_FAILED code. The UI sees a clear
blast radius instead of orphan spinners.
* Reparse now calls OpenAttempt up front so the timeline reflects
"new attempt, all pending" instead of letting the previous run's
status linger until the worker picks up the task.
* Image_multimodal records each image as a generation subspan with
its own success/failure on the parent attempt's multimodal stage.
The finalize-on-last-attempt counter logic is preserved unchanged.
* GET /api/v1/knowledge/:id/spans (also kept /stages alias) returns
a tree shape with synthesized pending placeholders so the
frontend always renders five timeline segments. ?attempt=N
enables history navigation.
2026-05-27 06:05:47 +00:00
|
|
|
--
|
2026-05-27 07:31:32 +00:00
|
|
|
-- Background: knowledge.parse_status is a 4-state field (pending /
|
|
|
|
|
-- processing / completed / failed). When users hit "stuck in processing",
|
|
|
|
|
-- they have no way to tell which stage is actually running — DocReader,
|
|
|
|
|
-- chunking, embedding, multimodal OCR/VLM, or the final post-process
|
|
|
|
|
-- handoff. Operators face the same problem.
|
refactor(knowledge): replace flat stage table with langfuse-style span tree
Addresses review feedback that the PR② design had four shortcomings:
1. The pipeline is a DAG, not a sequence — Embedding and Multimodal
are independent of each other, both downstream of Chunking, both
upstream of PostProcess. The flat (knowledge_id, stage) table
couldn't represent that, so a Chunking failure left dependents
stranded as "pending" forever instead of being marked as
impossible-to-run.
2. No history across attempts. A reparse erased the previous run's
status before the new run started, leaving operators with no way
to investigate "why did this fail twice?".
3. Stages had only status + duration. Operators want to know how big
the work was — pages parsed, chunks created, tokens embedded, VLM
calls made — to distinguish "slow because the file is huge" from
"slow because the docreader is wedged".
4. Multimodal fans out N image tasks; Embedding fans out M batches;
PostProcess fans out into Summary/Question/Wiki/Graph. Each unit
is interesting on its own (Langfuse already captures this for
LLM calls). The flat model couldn't express it.
The redesign mirrors Langfuse's trace/span/generation hierarchy:
* Migration 000053 supersedes 000052: knowledge_processing_spans
table with (knowledge_id, attempt, span_id) primary key, plus
parent_span_id, kind ∈ {root, stage, subspan, generation},
status ∈ {pending,running,done,failed,skipped,cancelled}, and
JSONB input/output/metadata fields.
* SpanTracker (replacing StageTracker) exposes OpenAttempt /
BeginStage / BeginSubSpan / EndSpan / FailSpan / SkipSpan /
LookupStage. Cross-process workers (image_multimodal) get the
parent's attempt + span via payload + LookupStage so subspans
attach correctly.
* StageDependencies declares the DAG; FailSpan now cascades —
descendants of the failed span and dependent stages are flipped
to "cancelled" with a UPSTREAM_FAILED code. The UI sees a clear
blast radius instead of orphan spinners.
* Reparse now calls OpenAttempt up front so the timeline reflects
"new attempt, all pending" instead of letting the previous run's
status linger until the worker picks up the task.
* Image_multimodal records each image as a generation subspan with
its own success/failure on the parent attempt's multimodal stage.
The finalize-on-last-attempt counter logic is preserved unchanged.
* GET /api/v1/knowledge/:id/spans (also kept /stages alias) returns
a tree shape with synthesized pending placeholders so the
frontend always renders five timeline segments. ?attempt=N
enables history navigation.
2026-05-27 06:05:47 +00:00
|
|
|
--
|
2026-05-27 07:31:32 +00:00
|
|
|
-- This table persists per-stage progress (and finer-grained subspans) so:
|
|
|
|
|
-- 1. The frontend can render a five-segment timeline showing where
|
|
|
|
|
-- each document is in the pipeline, with collapsible per-image /
|
|
|
|
|
-- per-batch subspans underneath.
|
|
|
|
|
-- 2. Failures carry a stable error_code (DOCREADER_TIMEOUT,
|
|
|
|
|
-- EMBEDDING_RATE_LIMIT, ...) the UI can map to localized
|
|
|
|
|
-- remediation text.
|
|
|
|
|
-- 3. Reparse history is preserved across attempts — operators can
|
|
|
|
|
-- navigate ?attempt=N to post-mortem "why did it fail twice?".
|
|
|
|
|
-- 4. Cascade-cancel rules use the parent_span_id tree to flip
|
|
|
|
|
-- dependent subspans/stages to "cancelled" when an upstream
|
|
|
|
|
-- span fails, so the UI shows a clear blast radius instead of
|
|
|
|
|
-- orphan spinners.
|
refactor(knowledge): replace flat stage table with langfuse-style span tree
Addresses review feedback that the PR② design had four shortcomings:
1. The pipeline is a DAG, not a sequence — Embedding and Multimodal
are independent of each other, both downstream of Chunking, both
upstream of PostProcess. The flat (knowledge_id, stage) table
couldn't represent that, so a Chunking failure left dependents
stranded as "pending" forever instead of being marked as
impossible-to-run.
2. No history across attempts. A reparse erased the previous run's
status before the new run started, leaving operators with no way
to investigate "why did this fail twice?".
3. Stages had only status + duration. Operators want to know how big
the work was — pages parsed, chunks created, tokens embedded, VLM
calls made — to distinguish "slow because the file is huge" from
"slow because the docreader is wedged".
4. Multimodal fans out N image tasks; Embedding fans out M batches;
PostProcess fans out into Summary/Question/Wiki/Graph. Each unit
is interesting on its own (Langfuse already captures this for
LLM calls). The flat model couldn't express it.
The redesign mirrors Langfuse's trace/span/generation hierarchy:
* Migration 000053 supersedes 000052: knowledge_processing_spans
table with (knowledge_id, attempt, span_id) primary key, plus
parent_span_id, kind ∈ {root, stage, subspan, generation},
status ∈ {pending,running,done,failed,skipped,cancelled}, and
JSONB input/output/metadata fields.
* SpanTracker (replacing StageTracker) exposes OpenAttempt /
BeginStage / BeginSubSpan / EndSpan / FailSpan / SkipSpan /
LookupStage. Cross-process workers (image_multimodal) get the
parent's attempt + span via payload + LookupStage so subspans
attach correctly.
* StageDependencies declares the DAG; FailSpan now cascades —
descendants of the failed span and dependent stages are flipped
to "cancelled" with a UPSTREAM_FAILED code. The UI sees a clear
blast radius instead of orphan spinners.
* Reparse now calls OpenAttempt up front so the timeline reflects
"new attempt, all pending" instead of letting the previous run's
status linger until the worker picks up the task.
* Image_multimodal records each image as a generation subspan with
its own success/failure on the parent attempt's multimodal stage.
The finalize-on-last-attempt counter logic is preserved unchanged.
* GET /api/v1/knowledge/:id/spans (also kept /stages alias) returns
a tree shape with synthesized pending placeholders so the
frontend always renders five timeline segments. ?attempt=N
enables history navigation.
2026-05-27 06:05:47 +00:00
|
|
|
--
|
2026-05-27 07:31:32 +00:00
|
|
|
-- Schema mirrors Langfuse's vocabulary:
|
refactor(knowledge): replace flat stage table with langfuse-style span tree
Addresses review feedback that the PR② design had four shortcomings:
1. The pipeline is a DAG, not a sequence — Embedding and Multimodal
are independent of each other, both downstream of Chunking, both
upstream of PostProcess. The flat (knowledge_id, stage) table
couldn't represent that, so a Chunking failure left dependents
stranded as "pending" forever instead of being marked as
impossible-to-run.
2. No history across attempts. A reparse erased the previous run's
status before the new run started, leaving operators with no way
to investigate "why did this fail twice?".
3. Stages had only status + duration. Operators want to know how big
the work was — pages parsed, chunks created, tokens embedded, VLM
calls made — to distinguish "slow because the file is huge" from
"slow because the docreader is wedged".
4. Multimodal fans out N image tasks; Embedding fans out M batches;
PostProcess fans out into Summary/Question/Wiki/Graph. Each unit
is interesting on its own (Langfuse already captures this for
LLM calls). The flat model couldn't express it.
The redesign mirrors Langfuse's trace/span/generation hierarchy:
* Migration 000053 supersedes 000052: knowledge_processing_spans
table with (knowledge_id, attempt, span_id) primary key, plus
parent_span_id, kind ∈ {root, stage, subspan, generation},
status ∈ {pending,running,done,failed,skipped,cancelled}, and
JSONB input/output/metadata fields.
* SpanTracker (replacing StageTracker) exposes OpenAttempt /
BeginStage / BeginSubSpan / EndSpan / FailSpan / SkipSpan /
LookupStage. Cross-process workers (image_multimodal) get the
parent's attempt + span via payload + LookupStage so subspans
attach correctly.
* StageDependencies declares the DAG; FailSpan now cascades —
descendants of the failed span and dependent stages are flipped
to "cancelled" with a UPSTREAM_FAILED code. The UI sees a clear
blast radius instead of orphan spinners.
* Reparse now calls OpenAttempt up front so the timeline reflects
"new attempt, all pending" instead of letting the previous run's
status linger until the worker picks up the task.
* Image_multimodal records each image as a generation subspan with
its own success/failure on the parent attempt's multimodal stage.
The finalize-on-last-attempt counter logic is preserved unchanged.
* GET /api/v1/knowledge/:id/spans (also kept /stages alias) returns
a tree shape with synthesized pending placeholders so the
frontend always renders five timeline segments. ?attempt=N
enables history navigation.
2026-05-27 06:05:47 +00:00
|
|
|
-- * one ROOT span per (knowledge_id, attempt) acting as the trace
|
|
|
|
|
-- * STAGE spans (docreader/chunking/embedding/multimodal/postprocess)
|
|
|
|
|
-- are children of root
|
|
|
|
|
-- * SUBSPANs (multimodal.image[i], embedding.batch[i], postprocess.spawn.X)
|
|
|
|
|
-- hang off their stage. The kind="generation" subset corresponds 1:1 to
|
|
|
|
|
-- a Langfuse generation; metadata.langfuse_trace_id stitches them.
|
2026-05-27 07:43:53 +00:00
|
|
|
DO $$ BEGIN RAISE NOTICE '[Migration 000054] Creating table: knowledge_processing_spans'; END $$;
|
refactor(knowledge): replace flat stage table with langfuse-style span tree
Addresses review feedback that the PR② design had four shortcomings:
1. The pipeline is a DAG, not a sequence — Embedding and Multimodal
are independent of each other, both downstream of Chunking, both
upstream of PostProcess. The flat (knowledge_id, stage) table
couldn't represent that, so a Chunking failure left dependents
stranded as "pending" forever instead of being marked as
impossible-to-run.
2. No history across attempts. A reparse erased the previous run's
status before the new run started, leaving operators with no way
to investigate "why did this fail twice?".
3. Stages had only status + duration. Operators want to know how big
the work was — pages parsed, chunks created, tokens embedded, VLM
calls made — to distinguish "slow because the file is huge" from
"slow because the docreader is wedged".
4. Multimodal fans out N image tasks; Embedding fans out M batches;
PostProcess fans out into Summary/Question/Wiki/Graph. Each unit
is interesting on its own (Langfuse already captures this for
LLM calls). The flat model couldn't express it.
The redesign mirrors Langfuse's trace/span/generation hierarchy:
* Migration 000053 supersedes 000052: knowledge_processing_spans
table with (knowledge_id, attempt, span_id) primary key, plus
parent_span_id, kind ∈ {root, stage, subspan, generation},
status ∈ {pending,running,done,failed,skipped,cancelled}, and
JSONB input/output/metadata fields.
* SpanTracker (replacing StageTracker) exposes OpenAttempt /
BeginStage / BeginSubSpan / EndSpan / FailSpan / SkipSpan /
LookupStage. Cross-process workers (image_multimodal) get the
parent's attempt + span via payload + LookupStage so subspans
attach correctly.
* StageDependencies declares the DAG; FailSpan now cascades —
descendants of the failed span and dependent stages are flipped
to "cancelled" with a UPSTREAM_FAILED code. The UI sees a clear
blast radius instead of orphan spinners.
* Reparse now calls OpenAttempt up front so the timeline reflects
"new attempt, all pending" instead of letting the previous run's
status linger until the worker picks up the task.
* Image_multimodal records each image as a generation subspan with
its own success/failure on the parent attempt's multimodal stage.
The finalize-on-last-attempt counter logic is preserved unchanged.
* GET /api/v1/knowledge/:id/spans (also kept /stages alias) returns
a tree shape with synthesized pending placeholders so the
frontend always renders five timeline segments. ?attempt=N
enables history navigation.
2026-05-27 06:05:47 +00:00
|
|
|
|
|
|
|
|
CREATE TABLE IF NOT EXISTS knowledge_processing_spans (
|
|
|
|
|
id BIGSERIAL PRIMARY KEY,
|
|
|
|
|
knowledge_id VARCHAR(64) NOT NULL,
|
|
|
|
|
attempt INT NOT NULL DEFAULT 1,
|
|
|
|
|
span_id VARCHAR(64) NOT NULL,
|
|
|
|
|
parent_span_id VARCHAR(64),
|
|
|
|
|
name VARCHAR(64) NOT NULL,
|
|
|
|
|
kind VARCHAR(16) NOT NULL, -- root / stage / subspan / generation
|
|
|
|
|
status VARCHAR(16) NOT NULL, -- pending/running/done/failed/skipped/cancelled
|
|
|
|
|
input JSONB,
|
|
|
|
|
output JSONB,
|
|
|
|
|
metadata JSONB,
|
|
|
|
|
error_code VARCHAR(64),
|
|
|
|
|
error_message TEXT,
|
|
|
|
|
error_detail TEXT,
|
|
|
|
|
started_at TIMESTAMP WITH TIME ZONE,
|
|
|
|
|
finished_at TIMESTAMP WITH TIME ZONE,
|
|
|
|
|
duration_ms BIGINT,
|
|
|
|
|
created_at TIMESTAMP WITH TIME ZONE NOT NULL DEFAULT CURRENT_TIMESTAMP,
|
|
|
|
|
updated_at TIMESTAMP WITH TIME ZONE NOT NULL DEFAULT CURRENT_TIMESTAMP,
|
|
|
|
|
CONSTRAINT uq_kpspan_attempt_span UNIQUE (knowledge_id, attempt, span_id)
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
-- Primary read path: fetch every span for a (knowledge, attempt) tuple in
|
|
|
|
|
-- one indexed range scan, then build the tree in memory. The unique
|
|
|
|
|
-- constraint above already covers point lookups.
|
|
|
|
|
CREATE INDEX IF NOT EXISTS idx_kpspan_knowledge_attempt
|
|
|
|
|
ON knowledge_processing_spans (knowledge_id, attempt);
|
|
|
|
|
|
|
|
|
|
-- Operator query: "find spans stuck in running too long". Used by ad-hoc
|
2026-05-27 07:31:32 +00:00
|
|
|
-- diagnostics and the housekeeping sweep.
|
refactor(knowledge): replace flat stage table with langfuse-style span tree
Addresses review feedback that the PR② design had four shortcomings:
1. The pipeline is a DAG, not a sequence — Embedding and Multimodal
are independent of each other, both downstream of Chunking, both
upstream of PostProcess. The flat (knowledge_id, stage) table
couldn't represent that, so a Chunking failure left dependents
stranded as "pending" forever instead of being marked as
impossible-to-run.
2. No history across attempts. A reparse erased the previous run's
status before the new run started, leaving operators with no way
to investigate "why did this fail twice?".
3. Stages had only status + duration. Operators want to know how big
the work was — pages parsed, chunks created, tokens embedded, VLM
calls made — to distinguish "slow because the file is huge" from
"slow because the docreader is wedged".
4. Multimodal fans out N image tasks; Embedding fans out M batches;
PostProcess fans out into Summary/Question/Wiki/Graph. Each unit
is interesting on its own (Langfuse already captures this for
LLM calls). The flat model couldn't express it.
The redesign mirrors Langfuse's trace/span/generation hierarchy:
* Migration 000053 supersedes 000052: knowledge_processing_spans
table with (knowledge_id, attempt, span_id) primary key, plus
parent_span_id, kind ∈ {root, stage, subspan, generation},
status ∈ {pending,running,done,failed,skipped,cancelled}, and
JSONB input/output/metadata fields.
* SpanTracker (replacing StageTracker) exposes OpenAttempt /
BeginStage / BeginSubSpan / EndSpan / FailSpan / SkipSpan /
LookupStage. Cross-process workers (image_multimodal) get the
parent's attempt + span via payload + LookupStage so subspans
attach correctly.
* StageDependencies declares the DAG; FailSpan now cascades —
descendants of the failed span and dependent stages are flipped
to "cancelled" with a UPSTREAM_FAILED code. The UI sees a clear
blast radius instead of orphan spinners.
* Reparse now calls OpenAttempt up front so the timeline reflects
"new attempt, all pending" instead of letting the previous run's
status linger until the worker picks up the task.
* Image_multimodal records each image as a generation subspan with
its own success/failure on the parent attempt's multimodal stage.
The finalize-on-last-attempt counter logic is preserved unchanged.
* GET /api/v1/knowledge/:id/spans (also kept /stages alias) returns
a tree shape with synthesized pending placeholders so the
frontend always renders five timeline segments. ?attempt=N
enables history navigation.
2026-05-27 06:05:47 +00:00
|
|
|
CREATE INDEX IF NOT EXISTS idx_kpspan_status_started
|
|
|
|
|
ON knowledge_processing_spans (status, started_at);
|
|
|
|
|
|
|
|
|
|
-- Lineage walks: cascade-cancel a stage's downstream needs to find every
|
|
|
|
|
-- child by parent_span_id. The cardinality is small (≤ tens per attempt)
|
|
|
|
|
-- so we don't need a covering index, just B-tree on parent.
|
|
|
|
|
CREATE INDEX IF NOT EXISTS idx_kpspan_parent
|
|
|
|
|
ON knowledge_processing_spans (parent_span_id)
|
|
|
|
|
WHERE parent_span_id IS NOT NULL;
|
|
|
|
|
|
2026-05-27 07:43:53 +00:00
|
|
|
DO $$ BEGIN RAISE NOTICE '[Migration 000054] knowledge_processing_spans table ready'; END $$;
|