---
id: AGENTIC-WP-0006
type: workplan
title: "Coding Session Memory — Error-Body Mining (content-level root causes)"
domain: helix_forge
repo: agentic-resources
status: ready
owner: codex
topic_slug: helix-forge
created: "2026-06-07"
updated: "2026-06-07"
state_hub_workstream_id: "c6e44147-15fd-4cfa-ab2d-87461a6858f1"
---

# Coding Session Memory — Error-Body Mining

The friction assessment ([ASSESSMENT-infra-friction.md](../docs/ASSESSMENT-infra-friction.md))
can see *that* a session was expensive (tool-mix, cost, overhead share) but not
always *why* at the content level — the specific error messages and repeated
failed approaches. The digest captures tool histograms and prompt/response
snippets, but **not error-body text**. This workplan closes that gap so Detect can
surface recurring root-cause errors, not just coarse markers.

Approach: capture **normalized error fingerprints + samples into the durable Tier 2
digest** (raw Tier 1 blobs are evictable, so mining must persist into the digest),
then cluster recurring fingerprints across sessions into candidate problem
patterns through the existing clusterer. No new capture source — this reads the
event/blob bodies already ingested.

## Capture Error-Body Snippets into the Digest

```task
id: AGENTIC-WP-0006-T01
status: done
priority: high
state_hub_task_id: "136a0a73-61c2-4390-876c-de3880a967e6"
```

Extend `core/digest.py` `build_digest` to extract, from failed events
(`kind=error` and `tool_result` bodies matching the existing `_FAIL_HINTS`), a
**normalized fingerprint** (strip paths, line numbers, UUIDs, hex) plus a short
sample, stored as `digest["error_snippets"] = [{fingerprint, sample, count, tool}]`.
Same error across a session collapses to one fingerprint with a count. Durable in
Tier 2 (survives Tier 1 eviction). Bump `SCHEMA_VERSION`. Unit-tested on synthetic
sessions with repeated and varied errors.

## Recurring-Error Signal + Clustering

```task
id: AGENTIC-WP-0006-T02
status: todo
priority: high
state_hub_task_id: "1a41b6f5-48bc-4080-bd18-94f2186ef566"
```

Add `detect/signals.py` `sig_recurring_error` keyed on the error fingerprint, so
the same error recurring across sessions/repos/flavors clusters into a candidate
problem pattern (locus = fingerprint; magnitude = occurrences). Feeds the existing
clusterer + cross-flavor flagging, so a root-cause error common to multiple flavors
is flagged cross-flavor. Respects the WP-0005 quality filter. Unit-tested on
synthetic digests sharing a fingerprint.

## Re-run Live, Extend Friction Assessment with Root Causes

```task
id: AGENTIC-WP-0006-T03
status: todo
priority: medium
state_hub_task_id: "bed16d23-3971-4257-b066-d1e639fef150"
```

Re-ingest (to populate `error_snippets` — schema bump invalidates old digests) and
re-run detect over the real local sessions. Add a **"content-level root causes"**
section to [ASSESSMENT-infra-friction.md](../docs/ASSESSMENT-infra-friction.md):
top recurring error fingerprints with counts and affected repos/flavors. Full suite
green. After workplan updates, notify the operator to run from `~/state-hub`:

```bash
make fix-consistency REPO=agentic-resources
```