fix(stream): prevent tool-call truncation, premature termination, upstream leaks + timeout hardening

.env.example

@@ -5,5 +5,16 @@ CC_API_KEY=
 HOST=127.0.0.1
 PORT=8787
 
+# Upstream timeouts (milliseconds)
+# Max wall-clock time for CC to return response headers + first byte.
+# Bump this for slow reasoning models that take a while to start streaming.
+# CC_UPSTREAM_TIMEOUT_MS=600000   # default: 10 minutes
+
+# Max gap between consecutive data chunks during streaming. If CC opens the
+# connection but stops sending data mid-response (stalled tool call, dropped
+# TCP, etc.), the proxy aborts the stream and the client gets a clean
+# error/finish instead of hanging forever. Set to 0 to disable.
+# CC_IDLE_TIMEOUT_MS=120000       # default: 2 minutes
+
 # Anthropic model mapping (optional — prefer --setup-claude-code)
 # ANTHROPIC_DEFAULT_MODEL=deepseek/deepseek-v4-pro

.github/workflows/ci.yml

@@ -34,19 +34,3 @@ jobs:
       - name: Build
         run: pnpm build
 
-  docker:
-    runs-on: ubuntu-latest
-    needs: quality
-    if: github.ref == 'refs/heads/main' && github.event_name == 'push'
-
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Build Docker image
-        uses: docker/build-push-action@v6
-        with:
-          push: false
-          tags: commandcode-api-proxy:latest

DEVELOPMENT.md

@@ -72,26 +72,6 @@ tests/
 └── e2e.test.ts           # End-to-end integration tests
 ```
 
-## Docker
-
-```bash
-# Build
-docker build -t commandcode-api-proxy .
-
-# Run with env var
-docker run --rm -p 8787:8787 \
-  -e CC_API_KEY=user_xxx \
-  commandcode-api-proxy
-
-# Or mount auth.json
-docker run --rm -p 8787:8787 \
-  -v ~/.config/commandcode-api-proxy:/home/node/.config/commandcode-api-proxy:ro \
-  commandcode-api-proxy
-
-# Using docker compose
-docker compose up -d
-```
-
 ## Tech stack
 
 - **Runtime:** Node.js (zero runtime dependencies)

Makefile

@@ -1,4 +1,4 @@
-.PHONY: build dev start test test-watch test-coverage fmt lint check clean docker-build docker-run docker-run-detached release help
+.PHONY: build dev start test test-watch test-coverage fmt lint check clean release help
 
 APP_NAME := commandcode-api-proxy
 VERSION := $(shell node -p "require('./package.json').version")
@@ -32,21 +32,6 @@ clean: ## Clean build artifacts
 	rm -rf dist/
 	rm -rf coverage/
 
-docker-build: ## Build Docker image
-	docker build -t $(APP_NAME):$(VERSION) .
-	docker tag $(APP_NAME):$(VERSION) $(APP_NAME):latest
-
-docker-run: ## Run Docker container
-	docker run --rm -p 8787:8787 \
-		-e CC_API_KEY=$(or $(CC_API_KEY),) \
-		$(APP_NAME):latest
-
-docker-run-detached: ## Run Docker container in background
-	docker run -d --name $(APP_NAME) \
-		-p 8787:8787 \
-		-e CC_API_KEY=$(or $(CC_API_KEY),) \
-		$(APP_NAME):latest
-
 release: build test ## Build and test for release
 	@echo "Ready for release: pnpm publish"
 

README.md

@@ -73,15 +73,17 @@ commandcode-api-proxy auth logout
 
 Equivalent env vars (lower priority than CLI flags):
 
-| Env var          | Description                                                                                                             |
-| ---------------- | ----------------------------------------------------------------------------------------------------------------------- |
-| `HOST`           | Bind address                                                                                                            |
-| `PORT`           | Port                                                                                                                    |
-| `CC_API_KEY`     | Command Code API key                                                                                                    |
-| `CC_API_BASE`    | Upstream API base URL                                                                                                   |
-| `CC_CLI_VERSION` | CLI version sent upstream                                                                                               |
-| `LOG_LEVEL`      | Log level (`info`, `debug`, etc.)                                                                                       |
-| `CORS_ORIGIN`    | `Access-Control-Allow-Origin` value. `*` by default; empty string disables CORS. Restrict before exposing on a network. |
+| Env var                  | Description                                                                                                             |
+| ------------------------ | ----------------------------------------------------------------------------------------------------------------------- |
+| `HOST`                   | Bind address                                                                                                            |
+| `PORT`                   | Port                                                                                                                    |
+| `CC_API_KEY`             | Command Code API key                                                                                                    |
+| `CC_API_BASE`            | Upstream API base URL                                                                                                   |
+| `CC_CLI_VERSION`         | CLI version sent upstream                                                                                               |
+| `CC_UPSTREAM_TIMEOUT_MS` | Max ms for upstream to return response headers + first byte (default `600000` / 10 min). Bump for slow reasoning models |
+| `CC_IDLE_TIMEOUT_MS`     | Max ms between consecutive stream chunks (default `120000` / 2 min). `0` disables — detects stalled upstreams            |
+| `LOG_LEVEL`              | Log level (`info`, `debug`, etc.)                                                                                       |
+| `CORS_ORIGIN`            | `Access-Control-Allow-Origin` value. `*` by default; empty string disables CORS. Restrict before exposing on a network. |
 
 > **Security:** the proxy forwards your paid Command Code key upstream and
 > accepts any auth token from clients (`proxy-managed`), so it is designed for

src/config.ts

@@ -15,6 +15,10 @@ export interface Config {
   ccVersion: string;
   logLevel: string;
   corsOrigin: string;
+  /** Max wall-clock ms for upstream to send response headers + first byte. */
+  upstreamTimeoutMs: number;
+  /** Max ms between consecutive chunks during streaming. 0 = disabled. */
+  idleTimeoutMs: number;
 }
 
 /**
@@ -86,5 +90,34 @@ export function loadConfig(): Config {
   // empty to disable) before exposing the proxy on a network.
   const corsOrigin = process.env.CORS_ORIGIN ?? "*";
 
-  return { host, port, apiKey, ccApiBase, ccVersion, logLevel, corsOrigin };
+  // Upstream timeouts. The connection timeout covers the wall-clock time
+  // until the upstream returns response headers + first byte — bump it for
+  // slow reasoning models. The idle timeout catches stalled streams where
+  // the upstream opened the connection but stopped sending chunks
+  // mid-response (e.g. tool call hung on the upstream side). Set
+  // CC_IDLE_TIMEOUT_MS=0 to disable idle detection entirely.
+  const upstreamTimeoutMs = parsePositiveInt(
+    process.env.CC_UPSTREAM_TIMEOUT_MS,
+    600_000, // 10 minutes — covers high-effort reasoning models
+  );
+  const idleTimeoutMs = parsePositiveInt(process.env.CC_IDLE_TIMEOUT_MS, 120_000); // 2 minutes
+
+  return {
+    host,
+    port,
+    apiKey,
+    ccApiBase,
+    ccVersion,
+    logLevel,
+    corsOrigin,
+    upstreamTimeoutMs,
+    idleTimeoutMs,
+  };
+}
+
+function parsePositiveInt(raw: string | undefined, fallback: number): number {
+  if (raw == null || raw === "") return fallback;
+  const n = Number(raw);
+  if (!Number.isFinite(n) || n < 0) return fallback;
+  return Math.floor(n);
 }