Squeezr — AI Context Compression

Squeezr exposes several HTTP endpoints for health checks, statistics, and the expand mechanism, alongside the transparent proxy that forwards requests to LLM providers.

Management endpoints

GET /squeezr/health

Enhanced health check endpoint. Returns proxy status, circuit breaker state, bypass mode, compression mode, and expand store pressure.

curl http://localhost:8080/squeezr/health

Response:

{
  "status": "ok",
  "version": "1.22.0",
  "uptime_seconds": 7351,
  "mode": "normal",
  "bypassed": false,
  "circuit_breaker": {
    "state": "closed",
    "consecutive_failures": 0,
    "total_trips": 0,
    "last_success_ago_s": 12
  },
  "expand_store": {
    "size": 42,
    "pressure": "low"
  },
  "compression": {
    "requests": 156,
    "savings_pct": 34.2
  }
}

GET /squeezr/stats

Returns statistics about proxy usage, compression savings, and cache performance.

curl http://localhost:8080/squeezr/stats

GET /squeezr/expand/:id

Retrieves the full original content for a compressed block. This is used internally by the squeezr_expand tool, but can also be called directly for debugging.

curl http://localhost:8080/squeezr/expand/a3f2b1

Returns 404 if the ID is not found (expired or from a previous session).

GET /squeezr/dashboard

Serves the built-in web dashboard UI. Open http://localhost:8080/squeezr/dashboard in your browser to access the interactive dashboard with real-time stats, project history, and configuration management.

GET /squeezr/limits

Returns current rate limit status for all configured providers, including remaining requests, token budgets, and reset timestamps.

curl http://localhost:8080/squeezr/limits

GET /squeezr/project

Returns information about the currently active project: name, path, configuration overrides, and per-project compression statistics.

curl http://localhost:8080/squeezr/project

GET /squeezr/events

Server-Sent Events (SSE) stream for real-time proxy activity. The dashboard uses this endpoint to show live compression events as they happen.

curl -N http://localhost:8080/squeezr/events

Events include: compression (each compressed request), stats (periodic stats updates), and session (session start/end).

GET /squeezr/bypass

Returns the current bypass mode state.

curl http://localhost:8080/squeezr/bypass
# => { "bypassed": false }

POST /squeezr/bypass

Toggles or sets bypass mode. Send {"enabled": true} to enable, {"enabled": false} to disable, or an empty body to toggle. Runtime-only — resets on proxy restart.

curl -X POST http://localhost:8080/squeezr/bypass \
  -H 'content-type: application/json' \
  -d '{"enabled": true}'
# => { "bypassed": true }

POST /squeezr/config

Changes the compression mode at runtime without restart.

curl -X POST http://localhost:8080/squeezr/config \
  -H 'content-type: application/json' \
  -d '{"mode": "aggressive"}'
# => { "ok": true, "mode": "aggressive" }

Proxy behavior

Squeezr sits transparently between your coding tool and the upstream API. Your tools point at http://localhost:8080 and Squeezr automatically routes to the correct provider:

Tool	Env var	Upstream
Claude Code / Aider	`ANTHROPIC_BASE_URL=http://localhost:8080`	`https://api.anthropic.com`
Gemini CLI	`GEMINI_API_BASE_URL=http://localhost:8080`	`https://generativelanguage.googleapis.com`
Codex	`HTTPS_PROXY=http://localhost:8081` (per-session)	`wss://chatgpt.com` (via MITM)
Ollama	Detected via dummy API key	`http://localhost:11434`

Request flow

Coding Tool
  |
  | POST http://localhost:8080/v1/messages
  v
Squeezr Proxy (localhost:8080)
  |
  | 1. Parse request body
  | 2. Run compression pipeline (3 layers)
  | 3. Inject expand tool definition
  | 4. Forward to upstream API
  |
  | POST https://api.anthropic.com/v1/messages
  v
Anthropic API
  |
  | Stream response chunks
  v
Squeezr Proxy
  |
  | Pass-through (no modification to response)
  v
Coding Tool

Headers

Squeezr forwards all request headers to the upstream, except Host (rewritten to match the upstream), Content-Length (recalculated after compression), and Expect (stripped for Node.js v24 compatibility). Response headers are returned unmodified.

API Endpoints