33 python code auditing

.github/workflows/integration-tests.yml

@@ -1,4 +1,4 @@
-name: Integration Tests
+name: Unit Tests
 
 on:
   push:
@@ -8,7 +8,7 @@ on:
 
 jobs:
   test:
-    name: Run Integration Tests
+    name: Run Unit Tests
     runs-on: ubuntu-latest
 
     steps:
@@ -24,7 +24,7 @@ jobs:
         run: pipx install poetry
 
       - name: Install dependencies
-        run: poetry install --no-root --with dev
+        run: poetry install --with dev
 
       - name: Run tests
         run: poetry run pytest tests/ -v --tb=short

.github/workflows/theseus-engine.yml

@@ -16,36 +16,29 @@ jobs:
         uses: actions/checkout@v4
         with:
           token: ${{ secrets.GITHUB_TOKEN }}
+          fetch-depth: 0
 
       - name: Setup python 3.12
         uses: actions/setup-python@v5
         with:
           python-version: "3.12"
 
       - name: Install poetry
-        uses: snok/install-poetry@v1
-        with:
-          virtualenvs-create: true
-          virtualenvs-in-project: true
+        run: pipx install poetry
 
       - name: Install dependencies
         run: poetry install --no-interaction --no-root
 
-      - name: Run theseus multi-repo analysis (delta load)
-        run: poetry run python scripts/analyse_repository.py
-
-      - name: Update living fossils (survivor check)
+      - name: Run theseus data pipeline (snapshots → survivor → cleanup)
         run: |
-          # Re-blame HEAD for every repo and update the survivor fossil only if
-          # the file:line:commit has actually changed since the last run.
-          # Genesis (historical fossil) is left completely untouched.
-          poetry run python scripts/add_fossils.py --update-survivor
-
-      - name: Clean & minify data payloads
-        run: poetry run python scripts/cleanup_data.py
+          # Analyse new snapshot periods, refresh survivor fossils, and clean/minify
+          # all data payloads.  Genesis (historical fossil) is left untouched
+          # during monthly cron runs.
+          poetry run python scripts/run_pipeline.py --update-survivor
 
       - name: Create pull request for data updates
-        uses: peter-evans/create-pull-request@v6
+        if: success()
+        uses: peter-evans/create-pull-request@b1ddad2c994a25fbc81a28b3ec0e368bb2021c50 # v6.0.0
         with:
           token: ${{ secrets.GITHUB_TOKEN }}
           commit-message: "chore: update theseus persistence data across all repos"
@@ -55,9 +48,9 @@ jobs:
           title: "chore: monthly theseus data pipeline update"
           body: |
             ## Automated Theseus Data Engine Run
-            
+
             This pull request contains the latest pre-computed persistence data, minified payloads, and fossil updates for the tracked repositories.
-            
+
             **Trigger:** Monthly Schedule / Workflow Dispatch
             **Action:** Deltas calculated and fossils verified.
           labels: "automated pr, data update"

data/claude-code_data.json

@@ -1 +1 @@
-{"snapshots":[{"snapshot_date":"2025-02","composition":{"2025":315}},{"snapshot_date":"2025-03","composition":{"2025":368}},{"snapshot_date":"2025-04","composition":{"2025":455}},{"snapshot_date":"2025-05","composition":{"2025":756}},{"snapshot_date":"2025-06","composition":{"2025":876}},{"snapshot_date":"2025-07","composition":{"2025":77387}},{"snapshot_date":"2025-08","composition":{"2025":77900}},{"snapshot_date":"2025-09","composition":{"2025":78823}},{"snapshot_date":"2025-10","composition":{"2025":56350}},{"snapshot_date":"2025-11","composition":{"2025":60301}},{"snapshot_date":"2025-12","composition":{"2025":86284}},{"snapshot_date":"2026-01","composition":{"2025":86626,"2026":35}},{"snapshot_date":"2026-02","composition":{"2025":86420,"2026":653}},{"snapshot_date":"2026-03","composition":{"2025":86142,"2026":1705}},{"snapshot_date":"2026-04","composition":{"2025":86142,"2026":2431}},{"snapshot_date":"2026-05","composition":{"2026":3361,"2025":86136}}],"fossils":{"genesis":{"timestamp":1740245022,"file":".devcontainer/Dockerfile","content":"FROM node:20","year":"2025","commit":"bd5ca70","view_commit":"bd5ca708adf82c4b81857abf40fe36d9d9cc3d1c","line":1},"survivor":{"timestamp":1740245022,"file":"README.md","content":"When you use Claude Code, we collect feedback, which includes usage data (such as code acceptance or rejections), associated conversation data, and user feedback submitted via the `/bug` command.","year":"2025","commit":"bd5ca70","view_commit":"main","line":62}}}
+{"snapshots":[{"snapshot_date":"2025-02","composition":{"2025":315}},{"snapshot_date":"2025-03","composition":{"2025":368}},{"snapshot_date":"2025-04","composition":{"2025":752}},{"snapshot_date":"2025-05","composition":{"2025":847}},{"snapshot_date":"2025-06","composition":{"2025":77617}},{"snapshot_date":"2025-07","composition":{"2025":77977}},{"snapshot_date":"2025-08","composition":{"2025":78851}},{"snapshot_date":"2025-09","composition":{"2025":56419}},{"snapshot_date":"2025-10","composition":{"2025":60375}},{"snapshot_date":"2025-11","composition":{"2025":86353}},{"snapshot_date":"2025-12","composition":{"2025":86746}},{"snapshot_date":"2026-01","composition":{"2025":86493,"2026":716}},{"snapshot_date":"2026-02","composition":{"2025":86216,"2026":1694}},{"snapshot_date":"2026-03","composition":{"2026":2376,"2025":86216}},{"snapshot_date":"2026-04","composition":{"2025":86210,"2026":3326}},{"snapshot_date":"2026-05","composition":{"2025":85997,"2026":11497}}],"fossils":{"genesis":{"timestamp":1740421074,"file":"SECURITY.md","content":"# Security Policy","year":"2025","commit":"429d03e","view_commit":"429d03e3823d7dfeaf162321f033f2b667c9b554","line":1},"survivor":{"timestamp":1740245022,"file":".devcontainer/init-firewall.sh","content":"#!/bin/bash","year":"2025","commit":"bd5ca70","view_commit":"main","line":1}}}

data/langchain_data.json

@@ -1 +1 @@
-{"snapshots":[{"snapshot_date":"2022-12","composition":{"2022":15774}},{"snapshot_date":"2023-03","composition":{"2022":28253,"2023":61969}},{"snapshot_date":"2023-06","composition":{"2023":487975,"2022":21681}},{"snapshot_date":"2023-09","composition":{"2023":681274,"2022":16291}},{"snapshot_date":"2023-12","composition":{"2023":881194,"2022":14704}},{"snapshot_date":"2024-03","composition":{"2024":357436,"2023":944924,"2022":10842}},{"snapshot_date":"2024-06","composition":{"2023":826677,"2024":645423,"2022":7685}},{"snapshot_date":"2024-09","composition":{"2023":686097,"2024":664907,"2022":7295}},{"snapshot_date":"2024-12","composition":{"2024":683157,"2023":546569,"2022":7138}},{"snapshot_date":"2025-01","composition":{"2024":720654,"2023":544169,"2022":7122,"2025":5}},{"snapshot_date":"2025-02","composition":{"2023":542683,"2024":707703,"2025":56681,"2022":7106}},{"snapshot_date":"2025-03","composition":{"2023":533418,"2024":657044,"2025":124237,"2022":6529}},{"snapshot_date":"2025-04","composition":{"2023":491914,"2024":630484,"2025":129671,"2022":6346}},{"snapshot_date":"2025-05","composition":{"2024":448680,"2025":144491,"2023":315772,"2022":5672}},{"snapshot_date":"2025-06","composition":{"2023":313764,"2024":444312,"2025":158141,"2022":5671}},{"snapshot_date":"2025-07","composition":{"2023":313208,"2024":441747,"2025":170384,"2022":5671}},{"snapshot_date":"2025-08","composition":{"2025":203640,"2023":308982,"2024":435295,"2022":5429}},{"snapshot_date":"2025-09","composition":{"2025":222619,"2023":308625,"2024":433511,"2022":5427}},{"snapshot_date":"2025-10","composition":{"2023":306859,"2025":253209,"2024":429458,"2022":5409}},{"snapshot_date":"2025-11","composition":{"2025":213274,"2023":83597,"2024":138301,"2022":3632}},{"snapshot_date":"2025-12","composition":{"2025":213376,"2023":83259,"2024":137738,"2022":3489}},{"snapshot_date":"2026-01","composition":{"2025":221792,"2023":82989,"2024":136828,"2022":3485,"2026":268}},{"snapshot_date":"2026-02","composition":{"2024":128469,"2023":81140,"2025":207607,"2026":12545,"2022":3485}},{"snapshot_date":"2026-03","composition":{"2023":81121,"2025":198803,"2024":126788,"2026":35860,"2022":3484}},{"snapshot_date":"2026-04","composition":{"2025":195106,"2023":81079,"2024":126636,"2026":47792,"2022":3475}},{"snapshot_date":"2026-05","composition":{"2025":194140,"2026":72120,"2023":125330,"2024":126474,"2022":3475}}],"fossils":{"genesis":{"timestamp":1666648275,"file":".flake8","content":"[flake8]","year":"2022","commit":"18aeb72","view_commit":"18aeb720126a68201c7e3b5a617139c27c779496","line":1},"survivor":{"timestamp":1666648275,"file":".github/workflows/_lint.yml","content":"jobs:","year":"2022","commit":"18aeb72","view_commit":"master","line":33}}}
+{"snapshots":[{"snapshot_date":"2022-12","composition":{"2022":33781}},{"snapshot_date":"2023-03","composition":{"2022":23173,"2023":99857}},{"snapshot_date":"2023-06","composition":{"2023":673974,"2022":18477}},{"snapshot_date":"2023-09","composition":{"2023":737974,"2022":15979}},{"snapshot_date":"2023-12","composition":{"2023":1060355,"2022":11100}},{"snapshot_date":"2024-03","composition":{"2023":889068,"2022":10561,"2024":491964}},{"snapshot_date":"2024-06","composition":{"2024":566702,"2023":709506,"2022":7565}},{"snapshot_date":"2024-09","composition":{"2024":658281,"2023":662951,"2022":7142}},{"snapshot_date":"2024-12","composition":{"2024":720724,"2023":544255,"2022":7122}},{"snapshot_date":"2025-01","composition":{"2023":542769,"2024":707768,"2022":7106,"2025":56667}},{"snapshot_date":"2025-02","composition":{"2024":657110,"2023":533502,"2022":6529,"2025":124263}},{"snapshot_date":"2025-03","composition":{"2025":156895,"2023":529492,"2024":639961,"2022":6506}},{"snapshot_date":"2025-04","composition":{"2025":144495,"2023":315832,"2024":448736,"2022":5672}},{"snapshot_date":"2025-05","composition":{"2025":158158,"2023":313824,"2024":444368,"2022":5671}},{"snapshot_date":"2025-06","composition":{"2023":313268,"2024":441875,"2022":5671,"2025":170299}},{"snapshot_date":"2025-07","composition":{"2023":309042,"2025":203651,"2024":435352,"2022":5429}},{"snapshot_date":"2025-08","composition":{"2025":222636,"2023":308685,"2024":433568,"2022":5427}},{"snapshot_date":"2025-09","composition":{"2023":306919,"2025":253228,"2024":429514,"2022":5409}},{"snapshot_date":"2025-10","composition":{"2025":213219,"2023":83609,"2024":138310,"2022":3632}},{"snapshot_date":"2025-11","composition":{"2025":213381,"2023":83271,"2024":137738,"2022":3489}},{"snapshot_date":"2025-12","composition":{"2025":221811,"2023":83009,"2024":136936,"2022":3485}},{"snapshot_date":"2026-01","composition":{"2025":207615,"2026":12524,"2023":81152,"2024":128469,"2022":3485}},{"snapshot_date":"2026-02","composition":{"2025":198810,"2023":81133,"2026":35849,"2024":126788,"2022":3484}},{"snapshot_date":"2026-03","composition":{"2025":195107,"2023":81091,"2024":126636,"2026":47777,"2022":3475}},{"snapshot_date":"2026-04","composition":{"2025":194170,"2026":71165,"2023":81047,"2024":126480,"2022":3475}},{"snapshot_date":"2026-05","composition":{"2025":192543,"2026":86935,"2023":81024,"2024":125964,"2022":3475}}],"fossils":{"genesis":{"timestamp":1666666586,"file":"examples/natbot.py","content":"\"\"\"Run NatBot.\"\"\"","year":"2022","commit":"1ef3ab4","view_commit":"1ef3ab4d0e663be147a5bcf542045e1f4a065778","line":1},"survivor":{"timestamp":1666648275,"file":".github/workflows/_lint.yml","content":"jobs:","year":"2022","commit":"18aeb72","view_commit":"master","line":33}}}