You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
📰 EU Parliament Month in Review — Unified Workflow
🔖 Workflow Parameters
Parameter
Value
ARTICLE_TYPE_SLUG
month-in-review
Family
Unified (Stages A → B → C → D → E in one workflow)
Data window
last 30 days
Primary feeds
get_adopted_texts_feed, get_events_feed, get_procedures_feed with timeframe: "one-month".
Stage A budget
≤ 4 min (tighter than other workflows — 30-day data window is larger)
Stage B budget (2 passes)
22–28 min — HARD CEILING per article-horizons.ts (do not exceed the per-slug ceiling on Stage B even if Pass 2 still has shallow sections; force GATE_RESULT=ANALYSIS_ONLY instead)
Stage C budget (gate + optional Pass 3)
≤ 4 min
Stage D budget
≤ 2 min (deterministic)
Stage E budget (commit + single PR)
≤ 2 min
Stage C exit tripwire
minute 36 elapsed (long-horizon prospective: 39; long-horizon retrospective: 38; electoral: 42) — the decision threshold for forcing GATE_RESULT=ANALYSIS_ONLY and (if late) skipping Stage D so the run can still reach the PR call. Per-slug stage ceilings live in src/config/article-horizons.ts; the tripwire backstops any per-stage overrun. Note: Stage D + E run after this tripwire, between the Stage C exit and the PR-call deadline.
Hard PR-call deadline
minute ≤ 45 elapsed (target ≤ 42) — deadline for the single safe-outputs create_pull_request call. Note: engine.mcp.session-timeout is intentionally NOT set — gh-aw v0.71.3 advertises this field but the bundled gateway image (v0.3.1) rejects it; the agent must finish within the 60-min timeout-minutes cap regardless.
Cross-reference prior month-ahead predictions; produce a confirmed/refuted tally.
Include intelligence/historical-baseline.md in the analysis set.
Stage A — Data Collection (Ref: 01, 07)
Run the canonical gateway block from 08-infrastructure.md §4. Source
scripts/mcp-setup.sh, then scripts/wb-mcp-probe.sh and
scripts/imf-mcp-probe.sh. Collect EP feed data first; fall back to
direct endpoints on failure. Deep-fetch up to 10 procedures / voting
records / meeting decisions into ${ANALYSIS_DIR}/data/. Target ≤ 5 min.
source scripts/mcp-setup.sh
mkdir -p "${ANALYSIS_DIR}/data""${ANALYSIS_DIR}/cache/imf"
scripts/imf-mcp-probe.sh >"${ANALYSIS_DIR}/cache/imf/probe-summary.json"&
IMF_PROBE_PID=$!source scripts/wb-mcp-probe.sh
# Run EP MCP collection now while the IMF probe is still in the background.# Wait immediately before Stage B so cache/imf is available for provenance.wait"$IMF_PROBE_PID"||true