Hack23 · pethers · May 31, 2026 · May 31, 2026 · May 31, 2026
diff --git a/.github/prompts/03-data-download.md b/.github/prompts/03-data-download.md
@@ -158,7 +158,7 @@ npx tsx scripts/download-parliamentary-data.ts \
   2>&1 | tee /tmp/pipeline-output.log
 ```
 
-File-budget constraint: safe-outputs `create_pull_request` hard-caps at **100 files** (E003). With 23 core artifacts + README + article.md + per-document analyses + HTML + JSON, `--limit 20` keeps the total under 80. Cap document-type workflows at `--limit 20`. Aggregation workflows may use `--limit 30` because they produce fewer per-document files.
+File-budget constraint: safe-outputs `create_pull_request` hard-caps at **200 files** (E003). With 23 core artifacts + README + article.md + per-document analyses + HTML + JSON, `--limit 20` keeps the total well under 180. Cap document-type workflows at `--limit 20`. Aggregation workflows may use `--limit 30` because they produce fewer per-document files.
 
 **Aggregation** workflows (evening-analysis, week-ahead, month-ahead, weekly-review, monthly-review, realtime-monitor):
 

diff --git a/.github/prompts/07-commit-and-pr.md b/.github/prompts/07-commit-and-pr.md
@@ -55,31 +55,31 @@ The dedicated **`news-translate`** workflow owns markdown translation only: each
    | Rendered articles (all 14 languages) | `news/$ARTICLE_DATE-$SUBFOLDER-{en,sv,da,no,fi,de,fr,es,nl,ar,he,ja,ko,zh}.html` |
    | News-translate executive-brief translations (only from `news-translate.md`) | `analysis/daily/$ARTICLE_DATE/$SUBFOLDER/executive-brief_<lang>.md` |
 
-   Stage `documents/*.md` selectively — keep the total ≤ 90 files (see step 2). Skip `analysis/daily/**/pass1/` entirely; it is a local gate-evidence snapshot (`04-analysis-pipeline.md`), not a deliverable.
+   Stage `documents/*.md` selectively — keep the total ≤ 180 files (see step 2). Skip `analysis/daily/**/pass1/` entirely; it is a local gate-evidence snapshot (`04-analysis-pipeline.md`), not a deliverable.
 
-2. **100-file guard (non-negotiable).** Run this snippet before calling safeoutputs. The safe-outputs handler hard-rejects PRs with > 100 files (E003); the guard uses a 90-file threshold to leave headroom for metadata the handler may add.
+2. **200-file guard (non-negotiable).** Run this snippet before calling safeoutputs. The safe-outputs handler hard-rejects PRs with > 200 files (E003); the guard uses a 180-file threshold to leave headroom for metadata the handler may add.
 
    ```bash
    set -euo pipefail
    STAGED_COUNT=$(git diff --cached --name-only | wc -l | tr -d '[:space:]')
-   echo "📊 Staged file count: $STAGED_COUNT (limit: 90)"
-   if [ "$STAGED_COUNT" -gt 90 ]; then
-     echo "⚠️ OVER FILE BUDGET ($STAGED_COUNT > 90). Unstaging documents/ ..."
+   echo "📊 Staged file count: $STAGED_COUNT (limit: 180)"
+   if [ "$STAGED_COUNT" -gt 180 ]; then
+     echo "⚠️ OVER FILE BUDGET ($STAGED_COUNT > 180). Unstaging documents/ ..."
      git reset HEAD -- "analysis/daily/$ARTICLE_DATE/$SUBFOLDER/documents/" 2>/dev/null || true
      STAGED_COUNT=$(git diff --cached --name-only | wc -l | tr -d '[:space:]')
      echo "📊 After unstaging documents/: $STAGED_COUNT files"
-     if [ "$STAGED_COUNT" -gt 90 ]; then
-       echo "❌ STILL OVER BUDGET ($STAGED_COUNT > 90). Unstaging all JSON files..."
+     if [ "$STAGED_COUNT" -gt 180 ]; then
+       echo "❌ STILL OVER BUDGET ($STAGED_COUNT > 180). Unstaging all JSON files..."
        git diff --cached --name-only | grep '\.json$' | xargs -r git reset HEAD -- || true
        STAGED_COUNT=$(git diff --cached --name-only | wc -l | tr -d '[:space:]')
        echo "📊 After unstaging JSON: $STAGED_COUNT files"
      fi
-     if [ "$STAGED_COUNT" -gt 90 ]; then
-       echo "❌ FATAL: Cannot reduce staged files below 90 (currently $STAGED_COUNT). Aborting."
+     if [ "$STAGED_COUNT" -gt 180 ]; then
+       echo "❌ FATAL: Cannot reduce staged files below 180 (currently $STAGED_COUNT). Aborting."
        exit 1
      fi
    fi
-   echo "✅ File budget OK: $STAGED_COUNT ≤ 90"
+   echo "✅ File budget OK: $STAGED_COUNT ≤ 180"
    ```
 
    Skipping this step makes `create_pull_request` fail with E003 and wastes the run.
@@ -195,7 +195,7 @@ Use the template below verbatim, replacing `$…` placeholders with run-observab
 | Longest evidence chain | $LONGEST_CHAIN_LEN hops |
 | Executive-brief languages produced | $BRIEF_LANG_COUNT / 14 |
 | Dashboard charts rendered | $CHART_COUNT |
-| Files staged | $STAGED_FILE_COUNT / 90 |
+| Files staged | $STAGED_FILE_COUNT / 180 |
 
 ## 🧠 Analysis artifacts
 

diff --git a/.github/workflows/news-committee-reports.md b/.github/workflows/news-committee-reports.md
@@ -28,11 +28,11 @@ on:
         required: false
         default: deep
 
-# Full git history needed by safe_outputs Checkout so the agent's git bundle can
-# apply cleanly even when main advances during the agent run. gh-aw v0.76.0 honours
-# `checkout.fetch-depth` for safe_outputs PR/push Checkouts (see compiler_safe_outputs_steps.go).
+# Shallow checkout (fetch-depth: 1) for fast safe_outputs Checkout. The prerequisite step
+# fetches GITHUB_SHA on demand for bundle-apply, making full-history clones unnecessary.
+# gh-aw v0.76.0+ honours `checkout.fetch-depth` (see compiler_safe_outputs_steps.go).
 checkout:
-  fetch-depth: 0
+  fetch-depth: 1
 
 permissions:
   contents: read
@@ -255,7 +255,7 @@ safe-outputs:
     # GitHub raw content
     - raw.githubusercontent.com
   max-patch-size: 10240
-  max-patch-files: 100
+  max-patch-files: 200
   create-pull-request:
     labels: [agentic-news, analysis-data]
     draft: false

diff --git a/.github/workflows/news-election-cycle.md b/.github/workflows/news-election-cycle.md
@@ -38,11 +38,11 @@ on:
         required: false
         default: comprehensive
 
-# Full git history needed by safe_outputs Checkout so the agent's git bundle can
-# apply cleanly even when main advances during the agent run. gh-aw v0.76.0 honours
-# `checkout.fetch-depth` for safe_outputs PR/push Checkouts (see compiler_safe_outputs_steps.go).
+# Shallow checkout (fetch-depth: 1) for fast safe_outputs Checkout. The prerequisite step
+# fetches GITHUB_SHA on demand for bundle-apply, making full-history clones unnecessary.
+# gh-aw v0.76.0+ honours `checkout.fetch-depth` (see compiler_safe_outputs_steps.go).
 checkout:
-  fetch-depth: 0
+  fetch-depth: 1
 
 permissions:
   contents: read
@@ -265,7 +265,7 @@ safe-outputs:
     # GitHub raw content
     - raw.githubusercontent.com
   max-patch-size: 10240
-  max-patch-files: 100
+  max-patch-files: 200
   create-pull-request:
     labels: [agentic-news, analysis-data, long-horizon, forward-look, election-cycle]
     draft: false

diff --git a/.github/workflows/news-evening-analysis.md b/.github/workflows/news-evening-analysis.md
@@ -36,11 +36,11 @@ on:
         required: false
         default: '12'
 
-# Full git history needed by safe_outputs Checkout so the agent's git bundle can
-# apply cleanly even when main advances during the agent run. gh-aw v0.76.0 honours
-# `checkout.fetch-depth` for safe_outputs PR/push Checkouts (see compiler_safe_outputs_steps.go).
+# Shallow checkout (fetch-depth: 1) for fast safe_outputs Checkout. The prerequisite step
+# fetches GITHUB_SHA on demand for bundle-apply, making full-history clones unnecessary.
+# gh-aw v0.76.0+ honours `checkout.fetch-depth` (see compiler_safe_outputs_steps.go).
 checkout:
-  fetch-depth: 0
+  fetch-depth: 1
 
 permissions:
   contents: read
@@ -263,7 +263,7 @@ safe-outputs:
     # GitHub raw content
     - raw.githubusercontent.com
   max-patch-size: 10240
-  max-patch-files: 100
+  max-patch-files: 200
   create-pull-request:
     labels: [agentic-news, analysis-data]
     draft: false

diff --git a/.github/workflows/news-interpellations.md b/.github/workflows/news-interpellations.md
@@ -28,11 +28,11 @@ on:
         required: false
         default: deep
 
-# Full git history needed by safe_outputs Checkout so the agent's git bundle can
-# apply cleanly even when main advances during the agent run. gh-aw v0.76.0 honours
-# `checkout.fetch-depth` for safe_outputs PR/push Checkouts (see compiler_safe_outputs_steps.go).
+# Shallow checkout (fetch-depth: 1) for fast safe_outputs Checkout. The prerequisite step
+# fetches GITHUB_SHA on demand for bundle-apply, making full-history clones unnecessary.
+# gh-aw v0.76.0+ honours `checkout.fetch-depth` (see compiler_safe_outputs_steps.go).
 checkout:
-  fetch-depth: 0
+  fetch-depth: 1
 
 permissions:
   contents: read
@@ -255,7 +255,7 @@ safe-outputs:
     # GitHub raw content
     - raw.githubusercontent.com
   max-patch-size: 10240
-  max-patch-files: 100
+  max-patch-files: 200
   create-pull-request:
     labels: [agentic-news, analysis-data]
     draft: false

diff --git a/.github/workflows/news-month-ahead.md b/.github/workflows/news-month-ahead.md
@@ -31,11 +31,11 @@ on:
         required: false
         default: deep
 
-# Full git history needed by safe_outputs Checkout so the agent's git bundle can
-# apply cleanly even when main advances during the agent run. gh-aw v0.76.0 honours
-# `checkout.fetch-depth` for safe_outputs PR/push Checkouts (see compiler_safe_outputs_steps.go).
+# Shallow checkout (fetch-depth: 1) for fast safe_outputs Checkout. The prerequisite step
+# fetches GITHUB_SHA on demand for bundle-apply, making full-history clones unnecessary.
+# gh-aw v0.76.0+ honours `checkout.fetch-depth` (see compiler_safe_outputs_steps.go).
 checkout:
-  fetch-depth: 0
+  fetch-depth: 1
 
 permissions:
   contents: read
@@ -258,7 +258,7 @@ safe-outputs:
     # GitHub raw content
     - raw.githubusercontent.com
   max-patch-size: 10240
-  max-patch-files: 100
+  max-patch-files: 200
   create-pull-request:
     labels: [agentic-news, analysis-data]
     draft: false

diff --git a/.github/workflows/news-monthly-review.md b/.github/workflows/news-monthly-review.md
@@ -30,11 +30,11 @@ on:
         required: false
         default: deep
 
-# Full git history needed by safe_outputs Checkout so the agent's git bundle can
-# apply cleanly even when main advances during the agent run. gh-aw v0.76.0 honours
-# `checkout.fetch-depth` for safe_outputs PR/push Checkouts (see compiler_safe_outputs_steps.go).
+# Shallow checkout (fetch-depth: 1) for fast safe_outputs Checkout. The prerequisite step
+# fetches GITHUB_SHA on demand for bundle-apply, making full-history clones unnecessary.
+# gh-aw v0.76.0+ honours `checkout.fetch-depth` (see compiler_safe_outputs_steps.go).
 checkout:
-  fetch-depth: 0
+  fetch-depth: 1
 
 permissions:
   contents: read
@@ -257,7 +257,7 @@ safe-outputs:
     # GitHub raw content
     - raw.githubusercontent.com
   max-patch-size: 10240
-  max-patch-files: 100
+  max-patch-files: 200
   create-pull-request:
     labels: [agentic-news, analysis-data]
     draft: false

diff --git a/.github/workflows/news-motions.md b/.github/workflows/news-motions.md
@@ -28,11 +28,11 @@ on:
         required: false
         default: deep
 
-# Full git history needed by safe_outputs Checkout so the agent's git bundle can
-# apply cleanly even when main advances during the agent run. gh-aw v0.76.0 honours
-# `checkout.fetch-depth` for safe_outputs PR/push Checkouts (see compiler_safe_outputs_steps.go).
+# Shallow checkout (fetch-depth: 1) for fast safe_outputs Checkout. The prerequisite step
+# fetches GITHUB_SHA on demand for bundle-apply, making full-history clones unnecessary.
+# gh-aw v0.76.0+ honours `checkout.fetch-depth` (see compiler_safe_outputs_steps.go).
 checkout:
-  fetch-depth: 0
+  fetch-depth: 1
 
 permissions:
   contents: read
@@ -255,7 +255,7 @@ safe-outputs:
     # GitHub raw content
     - raw.githubusercontent.com
   max-patch-size: 10240
-  max-patch-files: 100
+  max-patch-files: 200
   create-pull-request:
     labels: [agentic-news, analysis-data]
     draft: false

diff --git a/.github/workflows/news-propositions.md b/.github/workflows/news-propositions.md
@@ -28,11 +28,11 @@ on:
         required: false
         default: deep
 
-# Full git history needed by safe_outputs Checkout so the agent's git bundle can
-# apply cleanly even when main advances during the agent run. gh-aw v0.76.0 honours
-# `checkout.fetch-depth` for safe_outputs PR/push Checkouts (see compiler_safe_outputs_steps.go).
+# Shallow checkout (fetch-depth: 1) for fast safe_outputs Checkout. The prerequisite step
+# fetches GITHUB_SHA on demand for bundle-apply, making full-history clones unnecessary.
+# gh-aw v0.76.0+ honours `checkout.fetch-depth` (see compiler_safe_outputs_steps.go).
 checkout:
-  fetch-depth: 0
+  fetch-depth: 1
 
 permissions:
   contents: read
@@ -255,7 +255,7 @@ safe-outputs:
     # GitHub raw content
     - raw.githubusercontent.com
   max-patch-size: 10240
-  max-patch-files: 100
+  max-patch-files: 200
   create-pull-request:
     labels: [agentic-news, analysis-data]
     draft: false
@@ -301,9 +301,9 @@ Generates deep political intelligence analysis **and** renders the HTML article
 
 > 🟡 **Plan to call `safeoutputs___create_pull_request` by agent minute 42 (hard deadline 45)** to reserve job-level headroom for setup variance and the safe-outputs runner. See `00-base-contract.md §Session timing` and `07-commit-and-pr.md §Deadline enforcement`.
 >
-> **AI-FIRST target**: Pass 2 is mandatory. Complete agent-phase analysis/rendering by agent minute 40 so the PR opens before the agent-minute-45 cutoff. Compress scope before skipping iterations — keep `--limit 10` for document-type workflows (well under the 100-file PR cap given 14 HTML take 14 slots) while keeping 1:1 per-document coverage for every `dok_id` in the manifest (`05-analysis-gate.md` check 2). Scheduled runs use `analysis_depth=deep`; reserve `comprehensive` for manual `workflow_dispatch` backfills.
+> **AI-FIRST target**: Pass 2 is mandatory. Complete agent-phase analysis/rendering by agent minute 40 so the PR opens before the agent-minute-45 cutoff. Compress scope before skipping iterations — keep `--limit 10` for document-type workflows (well under the 200-file PR cap given 14 HTML take 14 slots) while keeping 1:1 per-document coverage for every `dok_id` in the manifest (`05-analysis-gate.md` check 2). Scheduled runs use `analysis_depth=deep`; reserve `comprehensive` for manual `workflow_dispatch` backfills.
 >
-> ⚠️ **HARD FILE LIMIT (100 files)**: the safe-outputs handler hard-rejects PRs with > 100 files (E003). Run the 100-file guard from `07-commit-and-pr.md` before calling `safeoutputs___create_pull_request`. Budget: 23 core artifacts + README + article.md + ≤ 10 per-document analyses + 14 HTML + pir-status.json ≈ 50 files. Cap downloads at 10 documents when rendering all 14 languages. When staged > 90, unstage `documents/` first then JSON files until under budget.
+> ⚠️ **HARD FILE LIMIT (200 files)**: the safe-outputs handler hard-rejects PRs with > 200 files (E003). Run the 200-file guard from `07-commit-and-pr.md` before calling `safeoutputs___create_pull_request`. Budget: 23 core artifacts + README + article.md + ≤ 10 per-document analyses + 14 HTML + pir-status.json ≈ 50 files. Cap downloads at 10 documents when rendering all 14 languages. When staged > 180, unstage `documents/` first then JSON files until under budget.
 
 **Single run** (produces all 23 analysis artifacts + aggregated article.md + 14 HTML files, target ~42 agent minutes in a 60-min job):
 

diff --git a/.github/workflows/news-quarter-ahead.md b/.github/workflows/news-quarter-ahead.md
@@ -31,11 +31,11 @@ on:
         required: false
         default: deep
 
-# Full git history needed by safe_outputs Checkout so the agent's git bundle can
-# apply cleanly even when main advances during the agent run. gh-aw v0.76.0 honours
-# `checkout.fetch-depth` for safe_outputs PR/push Checkouts (see compiler_safe_outputs_steps.go).
+# Shallow checkout (fetch-depth: 1) for fast safe_outputs Checkout. The prerequisite step
+# fetches GITHUB_SHA on demand for bundle-apply, making full-history clones unnecessary.
+# gh-aw v0.76.0+ honours `checkout.fetch-depth` (see compiler_safe_outputs_steps.go).
 checkout:
-  fetch-depth: 0
+  fetch-depth: 1
 
 permissions:
   contents: read
@@ -258,7 +258,7 @@ safe-outputs:
     # GitHub raw content
     - raw.githubusercontent.com
   max-patch-size: 10240
-  max-patch-files: 100
+  max-patch-files: 200
   create-pull-request:
     labels: [agentic-news, analysis-data, long-horizon, forward-look]
     draft: false

diff --git a/.github/workflows/news-realtime-monitor.md b/.github/workflows/news-realtime-monitor.md
@@ -40,11 +40,11 @@ on:
         required: false
         default: deep
 
-# Full git history needed by safe_outputs Checkout so the agent's git bundle can
-# apply cleanly even when main advances during the agent run. gh-aw v0.76.0 honours
-# `checkout.fetch-depth` for safe_outputs PR/push Checkouts (see compiler_safe_outputs_steps.go).
+# Shallow checkout (fetch-depth: 1) for fast safe_outputs Checkout. The prerequisite step
+# fetches GITHUB_SHA on demand for bundle-apply, making full-history clones unnecessary.
+# gh-aw v0.76.0+ honours `checkout.fetch-depth` (see compiler_safe_outputs_steps.go).
 checkout:
-  fetch-depth: 0
+  fetch-depth: 1
 
 permissions:
   contents: read
@@ -267,7 +267,7 @@ safe-outputs:
     # GitHub raw content
     - raw.githubusercontent.com
   max-patch-size: 10240
-  max-patch-files: 100
+  max-patch-files: 200
   create-pull-request:
     labels: [agentic-news, analysis-data]
     draft: false