[Agora] Run debates for analyses without debate sessions

Goal

Increase Agora coverage by adding substantive debate sessions for analyses that currently have none. Debate coverage is a core quality mechanism: claims should be challenged, contextualized, and synthesized before they feed the Exchange or Atlas.

Acceptance Criteria

☑ The selected analyses have new debate_sessions rows linked by analysis_id

☑ Each debate has transcript_json or a substantive consensus/dissent summary

☑ The before/after count of analyses without debate sessions is recorded

☑ No placeholder debate rows are inserted

Approach

Query completed analyses without linked debate_sessions, prioritizing active gaps and recent analyses.

Run or reconstruct the standard Agora debate workflow for a bounded batch.

Persist only substantive debates with transcript or summary content.

Verify linked rows and record the remaining gap count.

Dependencies

quest-engine-ci - Generates this task when queue depth is low and debate coverage gaps exist.

Dependents

Exchange and Atlas ranking tasks depend on debated, quality-tested claims.

Work Log

2026-04-21 21:06 UTC — Slot 54

Started task d6cc6f1b-2f55-4309-a924-93f46a5fcf32.
Read AGENTS.md, CLAUDE.md, this spec, alignment-feedback-loops.md, and landscape-gap-framework.md.
Checked recent work: current branch is one commit behind origin/main; recent debate-backfill commits exist, including 0971a8820 adding scripts/run_pending_debates.py.
Verified live PostgreSQL state via scidex.core.database.get_db(): 37 analyses currently have no linked debate_sessions row, so the task is still necessary.
Plan: use the existing resumable scripts/run_pending_debates.py runner for a bounded batch of 10, then verify the before/after missing count and that each new session has non-empty transcript_json/round content.

2026-04-21 21:55 UTC — Slot 54

Ran timeout 1800 python3 scripts/run_pending_debates.py --limit 10 --min-success 10; six sessions were committed before the shell timeout interrupted the seventh in-progress debate.
Resumed with timeout 1800 python3 scripts/run_pending_debates.py --limit 4 --min-success 4; four additional sessions committed successfully.
Runner summaries: initial before count was 37 analyses without sessions; resumed batch reduced the remaining count from 31 to 27.
Independent verification query found 10 new sessions created after 2026-04-21 14:07 America/Los_Angeles, each with transcript_json length 4, four debate_rounds rows, and minimum round content length >= 8,798 characters.
New session analysis IDs: SDA-2026-04-07-gap-pubmed-20260406-041428-53b81741, SDA-2026-04-07-gap-pubmed-20260406-062202-c8c5a9a1, SDA-2026-04-07-gap-pubmed-20260406-062141-611cf046, SDA-2026-04-07-gap-debate-20260406-062039-7ef9980b, SDA-2026-04-07-gap-debate-20260406-062033-839c3e2a, SDA-2026-04-07-gap-pubmed-20260406-041445-7e1dc0b2, SDA-2026-04-07-gap-pubmed-20260406-041434-d7920f3b, SDA-2026-04-07-gap-pubmed-20260406-041423-2d1db50c, SDA-2026-04-07-gap-pubmed-20260406-062118-2cdbb0dd, SDA-2026-04-07-gap-pubmed-20260406-062150-a6cc7467.
Result: Done — 10 analyses gained substantive debate coverage; remaining analyses without sessions is 27.

Tasks using this spec (7)

[Agora] Run debates for 10 analyses without debate sessions

Agora done P88

[Agora] Run debates for 10 analyses without debate sessions

Open Debates done P88

[Agora] Run 4-round debates for 10 analyses without debate s

Agora done P87

[Agora] Run 4-round debates for 10 analyses without debate s

Agora done P88

[Agora] Run 4-round debates for 10 analyses without debate s

Agora done P88

[Agora] Run debates for 10 analyses without debate sessions

Agora open P68

[Agora] Run open-question debates for 5 highest-priority kno

Agora running P71

File: quest_engine_debate_coverage_backfill_spec.md

Modified: 2026-04-24 07:15

Size: 3.4 KB