feat(resolution): gin middleware-chain synthesizer + Opus 4.8 benchmark refresh (#547)

* fix(agent-eval): detect idle by content-stability, not spinner absence

Opus 4.8's extended-thinking TUI shows no spinner / interrupt hint / timer while it streams its final answer — those appear only during the thinking and tool-use phases. The old detector treated ~5s of not-busy + prompt-present as done, so it killed interactive runs mid-answer, silently truncating both arms of the tmux A/B (low tool counts; the final assistant message left as a mid-investigation preamble). Now a run is done only when the captured pane stops changing for ~8s; while streaming, the pane changes every poll so stability never accrues. BUSY_RE stays as the immediate busy-reset for the thinking/tool/live-timer phase. Content-stability is model-agnostic — it survives future spinner re-wordings.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* docs(readme): refresh VS Code benchmark on v0.9.7 + Opus 4.8

Re-ran the VS Code A/B (headless median-of-4) on the current build and model. Cost savings held at 26% ($0.66->$0.89), but token/time/tool-call savings narrowed (78->63%, 52->20%, 85->69%) because Opus 4.8's without-CodeGraph arm explores far more efficiently than 4.7's did (16 tool calls vs 55, no Explore-subagent fan-out); the WITH arm is unchanged at 5 calls / 0 reads. Recomputed the average row and noted that the VS Code row is now a different model/version epoch than the other six.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat(resolution): synthesize gin middleware-chain edges (Next -> registered handlers)

Gin runs its entire handler chain through one dynamic line in (*Context).Next -- c.handlers[c.index](c), a slice-index dispatch tree-sitter can't resolve. So callees(Next) dead-ended at the len() helper and the flow ServeHTTP -> handleHTTPRequest -> Next stopped at the exact symbol a 'how does the middleware chain work' question is about, sending the agent to re-query and Read/grep (a measured gin WITH-arm rabbit-hole: 2/4 headless runs spiraled to ~5min, one mis-firing the opt-in Workflow orchestration tool). Find the chain dispatcher (a Go method invoking a handlers slice by index) and link it -> every HandlerFunc registered via .Use/.GET/.../.Handle, so callees(Next) and trace(ServeHTTP, handler) connect end-to-end. Gated on the dispatcher existing (inert on non-gin Go repos), named handlers only (inline closures skipped), capped; provenance heuristic / synthesizedBy gin-middleware-chain, registeredAt = the registration site. Validated: gin callees(Next) now surfaces Logger/Recovery/ErrorLogger + handlers (node count stable at 2,544; 5 precise edges); agent A/B (headless median-of-4, Opus 4.8) flipped gin from -58% cost / -129% time to +7% cost / +35% tokens / +8% time / 38% tool calls, all 4 WITH runs clean (0 Read/Grep/Bash). 167/167 unit tests pass incl. the new gin-middleware-chain test.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* docs(readme): publish uniform Opus 4.8 benchmark + per-repo breakdown accordion

Refresh all 7 benchmark rows to the v0.9.7 / Opus 4.8 headless median-of-4 (was a mix of the 4.8 VS Code row + six 4.7 rows). New average 18% cheaper / 51% fewer tokens / 16% faster / 57% fewer tool calls; headline + methodology note updated 4.7->4.8. The gap is smaller than the prior 4.7 numbers because Opus 4.8's native grep/read is more efficient (the without-arm no longer fans out into large Explore-subagent sweeps) -- not a codegraph regression; CodeGraph still cuts tool calls and tokens on all 7 repos, with cost marginal/negative only on django + okhttp. Adds a top-level 'Per-repo breakdown' accordion (per-metric Time/Reads/Grep-Bash/Tool calls/Tokens/Cost, WITH vs WITHOUT, per repo) directly below the condensed summary; methodology/queries/why-wins move to a second accordion.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* docs(changelog): note Gin middleware-chain synthesizer under [Unreleased]

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

scripts/agent-eval/itrun.sh

@@ -81,25 +81,38 @@ for _ in $(seq 1 120); do
 done
 [ "$started" = 1 ] || { echo "agent never started working"; cap; tmux kill-session -t "$SESSION" 2>/dev/null; exit 1; }
 
-# Poll for idle: not busy AND ❯ present, for 10 consecutive polls (~5s) to ride
-# out mid-conversation thinking gaps that briefly drop the spinner. Up to ~15min.
-consec=0
-for _ in $(seq 1 1800); do
-  pane=$(cap)
-  if echo "$pane" | grep -qE "$BUSY_RE"; then
-    consec=0
-  elif echo "$pane" | grep -q "❯"; then
-    consec=$((consec+1)); [ "$consec" -ge 10 ] && break
+# Poll for idle. CRITICAL: Opus 4.8 (extended thinking) renders NO spinner /
+# "esc to interrupt" / timer while it STREAMS its final answer — those appear
+# only during the thinking + tool-use phases ("✻ Marinating… (32s · ↓ 1.3k
+# tokens · thinking with max effort)"). So BUSY_RE reads "not busy" for the whole
+# 10-30s answer stream, and any short not-busy threshold kills the run mid-answer
+# (the truncation bug). We therefore detect "done" by CONTENT STABILITY, not by a
+# spinner string: while the agent streams, the captured pane changes every poll,
+# so stability never accrues; it accrues only once the agent has finished and the
+# static "✻ Brewed for 1m 9s" summary is all that is left. BUSY_RE still hard-
+# resets stability (covers thinking/tool-use/live-timer, where text can briefly
+# sit still). Need STABLE_NEEDED polls (~8s) of zero pane change + ❯ present.
+# Content-stability is model-agnostic — it survives future spinner re-wordings.
+STABLE_NEEDED=16
+prev=""; stable=0
+for _ in $(seq 1 2400); do            # up to ~20 min
+  pane="$(cap)"
+  sig="$(printf '%s' "$pane" | tr -s '[:space:]' ' ')"
+  if printf '%s' "$pane" | grep -qE "$BUSY_RE"; then
+    stable=0                          # thinking / tool use / live timer → busy
+  elif [ -n "$sig" ] && [ "$sig" = "$prev" ] && printf '%s' "$pane" | grep -q "❯"; then
+    stable=$((stable+1)); [ "$stable" -ge "$STABLE_NEEDED" ] && break
   else
-    consec=0
+    stable=0                          # answer still streaming → pane changing
   fi
+  prev="$sig"
   sleep 0.5
 done
 sleep 1
 
 tmux capture-pane -p -t "$SESSION" -S - > "$OUT"
 echo "captured $(wc -l < "$OUT") lines -> $OUT"
-grep -oE "Done \([^)]*\)" "$OUT" | tail -1
+grep -oE "Done \([^)]*\)|[A-Z][a-z]+ for ([0-9]+m )?[0-9]+s" "$OUT" | tail -1
 grep -oE "[0-9.]+k?/[0-9.]+M" "$OUT" | tail -1 | sed 's/^/Context /'
 tmux kill-session -t "$SESSION" 2>/dev/null