rename: dataforge -> swe-forge

- Rename package, binary, repository URL in Cargo.toml
- Rename all 194 source references (dataforge -> swe_forge)
- Rename all docs/deploy/config references (dataforge -> swe-forge)
- Update CI artifact names and binary paths
- Rename GitHub repo via gh CLI (CortexLM/dataforge -> CortexLM/swe-forge)
- 0 clippy warnings, 1251 tests passing

Author: echobt

.github/workflows/ci.yml

@@ -85,8 +85,8 @@ jobs:
       - name: Upload binary
         uses: actions/upload-artifact@v4
         with:
-          name: dataforge-linux-x86_64
-          path: target/release/dataforge
+          name: swe-forge-linux-x86_64
+          path: target/release/swe-forge
           retention-days: 7
 
   # ──────────────────────────────────────────────

.github/workflows/nightly.yml

@@ -95,13 +95,13 @@ jobs:
           RUSTFLAGS: "-C target-cpu=native -C link-arg=-fuse-ld=mold"
 
       - name: Binary size
-        run: ls -lh target/release/dataforge
+        run: ls -lh target/release/swe-forge
 
       - name: Upload release binary
         uses: actions/upload-artifact@v4
         with:
-          name: dataforge-nightly-linux-x86_64
-          path: target/release/dataforge
+          name: swe-forge-nightly-linux-x86_64
+          path: target/release/swe-forge
           retention-days: 14
 
   # ──────────────────────────────────────────────

.github/workflows/release.yml

@@ -47,11 +47,11 @@ jobs:
       - name: Package
         run: |
           mkdir -p dist
-          cp target/release/dataforge dist/
-          cd dist && tar czf ../dataforge-${{ github.ref_name }}-linux-x86_64.tar.gz dataforge
+          cp target/release/swe-forge dist/
+          cd dist && tar czf ../swe-forge-${{ github.ref_name }}-linux-x86_64.tar.gz swe-forge
 
       - name: Create GitHub Release
         uses: softprops/action-gh-release@v2
         with:
-          files: dataforge-${{ github.ref_name }}-linux-x86_64.tar.gz
+          files: swe-forge-${{ github.ref_name }}-linux-x86_64.tar.gz
           generate_release_notes: true

Cargo.lock

@@ -1,15 +1,15 @@
 [package]
-name = "dataforge"
+name = "swe-forge"
 version = "0.1.0"
 edition = "2021"
-description = "Data pipeline orchestration framework for LLM evaluation with multi-agent validation"
+description = "SWE-bench dataset forge: mine, generate and evaluate real software engineering tasks"
 license = "MIT"
-repository = "https://github.com/dataforge/dataforge"
+repository = "https://github.com/CortexLM/swe-forge"
 readme = "README.md"
-keywords = ["dataforge", "pipeline", "llm", "evaluation", "agents"]
+keywords = ["swe-bench", "pipeline", "llm", "evaluation", "agents"]
 
 [[bin]]
-name = "dataforge"
+name = "swe-forge"
 path = "src/main.rs"
 
 [dependencies]

Cargo.toml

@@ -1,4 +1,4 @@
-# dataforge
+# swe-forge
 
 [![Rust](https://img.shields.io/badge/rust-1.70%2B-orange.svg)](https://www.rust-lang.org/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
@@ -9,7 +9,7 @@ Built on top of [SweInfinite](https://github.com/unconst/SweInfinite) by [@uncon
 
 ## What it does
 
-dataforge connects to [GH Archive](https://www.gharchive.org/) to discover recently merged pull requests, enriches them via the GitHub API, classifies their difficulty using an LLM, generates test specifications via an agentic loop, and exports SWE-bench-compatible task instances. It also includes a full evaluation harness to run external coding agents on generated tasks and verify their solutions.
+swe-forge connects to [GH Archive](https://www.gharchive.org/) to discover recently merged pull requests, enriches them via the GitHub API, classifies their difficulty using an LLM, generates test specifications via an agentic loop, and exports SWE-bench-compatible task instances. It also includes a full evaluation harness to run external coding agents on generated tasks and verify their solutions.
 
 ## Key features
 
@@ -77,8 +77,8 @@ graph TB
 ### Build
 
 ```bash
-git clone https://github.com/CortexLM/dataforge.git
-cd dataforge
+git clone https://github.com/CortexLM/swe-forge.git
+cd swe-forge
 cargo build --release
 ```
 
@@ -313,7 +313,7 @@ Pre-classification uses only the PR title and body (~100 tokens, ~0.5s). Full cl
 ### `swe mine`
 
 ```
-dataforge swe mine [OPTIONS]
+swe-forge swe mine [OPTIONS]
 
 Options:
   -o, --output <DIR>          Output directory [default: ./swe-datasets]
@@ -330,7 +330,7 @@ Options:
 ### `swe harness`
 
 ```
-dataforge swe harness [OPTIONS] --agent-dir <AGENT_DIR>
+swe-forge swe harness [OPTIONS] --agent-dir <AGENT_DIR>
 
 Options:
   -i, --input <INPUT>                 Directory containing SWE workspaces [default: ./generated-swe]
@@ -347,7 +347,7 @@ Options:
 ### `swe validate`
 
 ```
-dataforge swe validate [OPTIONS]
+swe-forge swe validate [OPTIONS]
 
 Options:
   -i, --input <DIR>           Input directory with SWE workspaces [default: ./generated-swe]
@@ -358,7 +358,7 @@ Options:
 ### `swe export`
 
 ```
-dataforge swe export [OPTIONS]
+swe-forge swe export [OPTIONS]
 
 Options:
   -i, --input <DIR>           Input directory [default: ./generated-swe]
@@ -427,7 +427,7 @@ RUST_LOG=debug cargo run -- swe mine --max-tasks 1 --once  # Debug run
 
 ## Credits
 
-Built on top of [SweInfinite](https://github.com/unconst/SweInfinite) by [@unconst](https://github.com/unconst). The original architecture for mining GitHub PRs and generating SWE-bench-style datasets was designed by the SweInfinite team. dataforge extends it with:
+Built on top of [SweInfinite](https://github.com/unconst/SweInfinite) by [@unconst](https://github.com/unconst). The original architecture for mining GitHub PRs and generating SWE-bench-style datasets was designed by the SweInfinite team. swe-forge extends it with:
 
 - Difficulty-based pre-classification and filtering
 - Agentic test generation (Codex-style multi-turn loop with shell access)

README.md

@@ -1,15 +1,15 @@
 version: '3.8'
 
 services:
-  dataforge:
-    image: dataforge:latest
+  swe-forge:
+    image: swe-forge:latest
     build:
       context: ..
       dockerfile: deploy/Dockerfile
     environment:
       - LITELLM_API_BASE=https://openrouter.ai/api/v1
       - LITELLM_API_KEY=${OPENROUTER_API_KEY}
-      - DATABASE_URL=postgres://synth:${POSTGRES_PASSWORD}@postgres:5432/dataforge
+      - DATABASE_URL=postgres://synth:${POSTGRES_PASSWORD}@postgres:5432/swe-forge
       - REDIS_URL=redis://redis:6379
     depends_on:
       - postgres
@@ -26,12 +26,12 @@ services:
     restart: unless-stopped
 
   worker:
-    image: dataforge:latest
-    command: ["dataforge", "worker", "--queue", "tasks"]
+    image: swe-forge:latest
+    command: ["swe-forge", "worker", "--queue", "tasks"]
     environment:
       - LITELLM_API_BASE=https://openrouter.ai/api/v1
       - LITELLM_API_KEY=${OPENROUTER_API_KEY}
-      - DATABASE_URL=postgres://synth:${POSTGRES_PASSWORD}@postgres:5432/dataforge
+      - DATABASE_URL=postgres://synth:${POSTGRES_PASSWORD}@postgres:5432/swe-forge
       - REDIS_URL=redis://redis:6379
     depends_on:
       - postgres
@@ -49,13 +49,13 @@ services:
   postgres:
     image: postgres:15-alpine
     environment:
-      - POSTGRES_USER=dataforge
+      - POSTGRES_USER=swe-forge
       - POSTGRES_PASSWORD=${POSTGRES_PASSWORD}
-      - POSTGRES_DB=dataforge
+      - POSTGRES_DB=swe-forge
     volumes:
       - postgres_data:/var/lib/postgresql/data
     healthcheck:
-      test: ["CMD-SHELL", "pg_isready -U dataforge"]
+      test: ["CMD-SHELL", "pg_isready -U swe-forge"]
       interval: 10s
       timeout: 5s
       retries: 5

deploy/docker-compose.prod.yml

@@ -1,10 +1,10 @@
 apiVersion: v1
 kind: ConfigMap
 metadata:
-  name: dataforge-config
-  namespace: dataforge
+  name: swe-forge-config
+  namespace: swe-forge
   labels:
-    app.kubernetes.io/name: dataforge
+    app.kubernetes.io/name: swe-forge
     app.kubernetes.io/component: config
 data:
   LITELLM_API_BASE: "https://openrouter.ai/api/v1"

deploy/kubernetes/configmap.yaml

@@ -1,35 +1,35 @@
 apiVersion: apps/v1
 kind: Deployment
 metadata:
-  name: dataforge
-  namespace: dataforge
+  name: swe-forge
+  namespace: swe-forge
   labels:
-    app.kubernetes.io/name: dataforge
+    app.kubernetes.io/name: swe-forge
     app.kubernetes.io/component: api
 spec:
   replicas: 1
   selector:
     matchLabels:
-      app: dataforge
+      app: swe-forge
   template:
     metadata:
       labels:
-        app: dataforge
-        app.kubernetes.io/name: dataforge
+        app: swe-forge
+        app.kubernetes.io/name: swe-forge
         app.kubernetes.io/component: api
     spec:
       containers:
-        - name: dataforge
-          image: dataforge:latest
+        - name: swe-forge
+          image: swe-forge:latest
           imagePullPolicy: IfNotPresent
           ports:
             - containerPort: 8080
               name: http
           envFrom:
             - configMapRef:
-                name: dataforge-config
+                name: swe-forge-config
             - secretRef:
-                name: dataforge-secrets
+                name: swe-forge-secrets
           resources:
             requests:
               cpu: "500m"
@@ -64,15 +64,15 @@ spec:
             path: /var/run/docker.sock
         - name: data
           persistentVolumeClaim:
-            claimName: dataforge-data
+            claimName: swe-forge-data
 ---
 apiVersion: v1
 kind: PersistentVolumeClaim
 metadata:
-  name: dataforge-data
-  namespace: dataforge
+  name: swe-forge-data
+  namespace: swe-forge
   labels:
-    app.kubernetes.io/name: dataforge
+    app.kubernetes.io/name: swe-forge
     app.kubernetes.io/component: storage
 spec:
   accessModes:

deploy/kubernetes/deployment.yaml

@@ -1,7 +1,7 @@
 apiVersion: v1
 kind: Namespace
 metadata:
-  name: dataforge
+  name: swe-forge
   labels:
-    app.kubernetes.io/name: dataforge
+    app.kubernetes.io/name: swe-forge
     app.kubernetes.io/component: namespace