From 8d15c2e0b326933f8fc912e3b13f37e78a9bc0b6 Mon Sep 17 00:00:00 2001
From: srdusr <99972264+srdusr@users.noreply.github.com>
Date: Wed, 14 Feb 2024 00:37:00 +0200
Subject: History view: SQLite storage, daemon/TUI split over Unix socket

Implements build-order step 3. Adds:

- internal/store: SQLite (WAL, single-writer) history table, raw
  request/response blobs plus metadata for the list view.
- internal/proxy: request/response capture wired into forward(). HTTP/1.1
  legs are captured byte-exact via a teeConn that records wire bytes as
  they're read, taken right after the message is fully drained (so no
  manual re-reading/replaying is needed - RoundTrip's own streaming does
  the draining). HTTP/2 legs (no meaningful "raw bytes" of their own -
  multiplexed, HPACK-compressed framing) are reconstructed instead, and
  marked as such in storage.
- internal/ipc: JSON-over-Unix-socket protocol between mitmuxd (owns the
  proxy and the DB) and any client - list/get for queries, subscribe for
  a live push stream of newly captured entries. Keeps the proxy engine
  independent of the UI, per the architecture sketch.
- cmd/mitmux: Bubble Tea TUI - a live-updating history table and a
  request/response detail view with raw bytes.

Two real bugs surfaced during testing and got fixed before commit:
1. http.Transport's HTTP/2 auto-dispatch does a literal *tls.Conn type
   assertion on the dialed connection; wrapping it in a capturing teeConn
   broke that silently, and HTTP/2 framing got parsed as HTTP/1.1 text.
   Fixed by dropping http.Transport for the upstream leg entirely in
   favor of an explicit per-protocol round trip (see PLAN.md stack note).
2. singleConnListener wrapped the client teeConn *inside* a
   closeSignalConn, so ConnContext's type assertion for it silently
   failed and HTTP/1.1 client-side capture never activated. Fixed the
   wrap order; verified via direct SQLite inspection that request_exact
   flips back to 1 and the stored bytes are genuinely wire-exact
   (preserved chunked-encoding framing, original header casing/order).

Verified live: plain HTTP, HTTPS H1.1, HTTPS H2, and a POST with a body,
checked against the raw stored bytes directly in SQLite; IPC list/get/
subscribe against a throwaway client; and the TUI driven end-to-end in a
tmux session (list, detail view, tab between request/response, live
update on a new request while sitting on the list).
---
 internal/proxy/capture.go | 83 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 83 insertions(+)
 create mode 100644 internal/proxy/capture.go

(limited to 'internal/proxy/capture.go')

diff --git a/internal/proxy/capture.go b/internal/proxy/capture.go
new file mode 100644
index 0000000..ccc95e9
--- /dev/null
+++ b/internal/proxy/capture.go
@@ -0,0 +1,83 @@
+package proxy
+
+import (
+	"bytes"
+	"io"
+	"net/http"
+)
+
+// cappedTee wraps an io.Reader, copying up to maxCaptureBytes of what
+// passes through into an internal buffer while still passing everything
+// through unmodified and unbounded to the real reader. Used to capture a
+// bounded sample of a body for reconstruction when exact wire capture
+// isn't available (the HTTP/2 leg - see below).
+type cappedTee struct {
+	r   io.Reader
+	buf bytes.Buffer
+}
+
+func newCappedTee(r io.Reader) *cappedTee {
+	return &cappedTee{r: r}
+}
+
+func (c *cappedTee) Read(p []byte) (int, error) {
+	n, err := c.r.Read(p)
+	if n > 0 {
+		if room := maxCaptureBytes - c.buf.Len(); room > 0 {
+			end := n
+			if end > room {
+				end = room
+			}
+			c.buf.Write(p[:end])
+		}
+	}
+	return n, err
+}
+
+// captureRequest returns the raw bytes of r for storage. When tee is
+// non-nil (an HTTP/1.1 client connection), the bytes are exactly what
+// was read off the wire. Otherwise (HTTP/2, which has no single "raw
+// bytes" representation - it's multiplexed, HPACK-compressed framing)
+// it's a reconstruction from the parsed request, exact=false.
+func captureRequest(r *http.Request, tee *teeConn, bodyCap *cappedTee) (raw []byte, exact bool) {
+	if tee != nil {
+		return tee.Take(), true
+	}
+
+	dump := r.Clone(r.Context())
+	if bodyCap != nil {
+		dump.Body = io.NopCloser(bytes.NewReader(bodyCap.buf.Bytes()))
+		dump.ContentLength = int64(bodyCap.buf.Len())
+	} else {
+		dump.Body = http.NoBody
+		dump.ContentLength = 0
+	}
+	var buf bytes.Buffer
+	if err := dump.Write(&buf); err != nil {
+		return nil, false
+	}
+	return buf.Bytes(), false
+}
+
+// captureResponse mirrors captureRequest for the upstream leg: exact
+// wire bytes when tee is non-nil (upstream negotiated HTTP/1.1),
+// otherwise a reconstruction.
+func captureResponse(resp *http.Response, tee *teeConn, bodyCap *cappedTee) (raw []byte, exact bool) {
+	if tee != nil {
+		return tee.Take(), true
+	}
+
+	dump := *resp
+	if bodyCap != nil {
+		dump.Body = io.NopCloser(bytes.NewReader(bodyCap.buf.Bytes()))
+		dump.ContentLength = int64(bodyCap.buf.Len())
+	} else {
+		dump.Body = http.NoBody
+		dump.ContentLength = 0
+	}
+	var buf bytes.Buffer
+	if err := dump.Write(&buf); err != nil {
+		return nil, false
+	}
+	return buf.Bytes(), false
+}
-- 
cgit v1.2.3