docs(plans): TUI-mode latency floor — measured decomposition + backlog (#155)

* docs(plans): TUI-mode latency floor — measured decomposition + backlog

An external consumer measured OCP's prompt path at TTFT p50 30-32s and excluded
OCP on that basis. This documents where those 30 seconds actually go, with a
reproducible harness (n=15) that bypasses OCP and measures the underlying
subscription path's true first-token time.

Findings:
- boot -> input-ready is only ~1.0s; it is NOT the bottleneck
- true TTFT is 6-10s; the remaining ~20s is runTuiTurn polling the transcript
  until turn_duration (ADR 0007 step 4) — i.e. waiting for the WHOLE turn.
  There is no streaming.
- buildTuiCmd never passes --effort, so the spawned claude inherits the
  operator's global effortLevel (xhigh on this host) — every request runs
  extended thinking. Passing --effort low: TTFT p50 9.70s -> 6.17s (-36%),
  spread 7.85-13.07s -> 5.87-6.44s. Stays on Claude Max.
- ⚠️ --bare SILENTLY drops off the subscription pool (banner flips
  'Claude Max' -> 'API Usage Billing'). It does cut boot to ~0.5s, but defeats
  the entire purpose of ADR 0007. Failure is silent: all 5 --bare samples
  produced no answer at all (no error, no crash, just never a token).
  Anyone optimizing boot MUST diff the banner line.
- Floor after all fixes is ~6s (claude always injects the full CC system prompt
  + tool definitions). TUI mode therefore cannot serve real-time consumers —
  a constraint worth stating in the README.

Backlog ranked by value/effort: (1) OCP_TUI_EFFORT env var, default low;
(2) real streaming instead of turn_duration polling (~20s, the big one);
(3) warm pane pool (~1s); (4) prefill trim (probably not worth it).

Docs-only; no version bump (matches repo convention — bump lands in the
chore(release) commit).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dx5Ncq6wWBrF27vJKHZ9Hr

* docs(plans): address review — restore --bare evidence, qualify effort claim, add banner captures

Reviewer (fresh-context, Iron Rule 10) returned REQUEST_CHANGES. All four technical
conclusions survived independent verification (source-read + live repro); the defects
were in the evidence file, and they were real:

- H-1: measurements.jsonl claimed n=15 but held 10 rows, and the --bare group — the
  basis of this PR's headline warning — had ZERO rows. The author had stripped them
  as 'invalid samples' (ttft_ms:-1) when they were in fact the evidence. Regenerated:
  n=15, three groups × 5, all with tag/extra_args. --bare reproduces exactly (5/5 no
  answer, boot 0.43-0.45s).
- M-1: the effort-inheritance claim was written unconditionally, but it depends on
  resolveTuiHome()'s mode. Real-home (current service config) inherits the operator's
  effortLevel: xhigh; env-token scratch home (~/.ocp-tui/home) has no effortLevel in
  its settings.json and prepareTuiHome() never writes one, so the pane gets claude's
  built-in default. Now documented as a table — and the mode split makes passing
  --effort explicitly MORE valuable, not less.
- M-2: baseline rows were produced by a pre-parameterized script and lacked
  tag/extra_args. Re-run with the committed script. Recomputed effect: -40% (was -36%).
- L-1: documented that the harness suppresses OCP's periodic kill-server tick via the
  othersRemain coexistence guard (by design, resumes next tick).
- L-2: documented that floor.sh's readiness marker differs from OCP's tuiInputReady(),
  so the ~1.0s boot figure is not apples-to-apples with BOOT_MS.
- Direct-API reference figure now explicitly labeled as external (not in this dataset).
- New: billing-banner.txt captures all three configs live, including confirmation that
  --effort low stays on Claude Max (reviewer noted this was asserted but unevidenced).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dx5Ncq6wWBrF27vJKHZ9Hr

* docs(plans): scope the effort claim to TUI mode (currently off), drop nonexistent bin/

Re-review (APPROVE_WITH_MINOR) caught two accuracy defects:
- MIN-1: 'every OCP request runs extended thinking' over-extrapolated. TUI mode is
  currently OFF on this host (CLAUDE_TUI_MODE=false; /health tui.enabled=false), so
  live traffic takes the -p path. The claim is about what happens WHEN TUI mode is
  enabled — now scoped, and the same qualifier applied to the kill-server interaction
  note (that reap tick is itself gated on TUI_MODE).
- NIT-2: the quoted grep included bin/, which does not exist in the repo (exit 2).
  Dropped; the zero-hit result over lib/ + server.mjs is unchanged.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dx5Ncq6wWBrF27vJKHZ9Hr

---------

Co-authored-by: dtzp555 <dtzp555@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

docs/plans/2026-07-13-tui-latency/README.md

@@ -0,0 +1,190 @@
+# TUI-mode latency: measured floor, and the four things worth fixing
+
+**Date**: 2026-07-13
+**Status**: findings + backlog (no code changed yet)
+**Measured on**: Mac mini / macOS 26.5.2 / Claude Code **v2.1.207** / Sonnet 5 / Claude Max subscription / **real-home mode** (no `CLAUDE_CODE_OAUTH_TOKEN`, no `OCP_TUI_HOME` in the service env)
+**Evidence**: [`measurements.jsonl`](measurements.jsonl) — **n=15** (3 configs × 5) · banner captures [`billing-banner.txt`](billing-banner.txt) · harness [`floor.sh`](floor.sh)
+
+## Why this exists
+
+An external consumer (the 知音 AI project) benchmarked OCP's prompt path and measured
+**TTFT p50 ≈ 30–32 s**, and excluded OCP as a backend on that basis. That number is real,
+but it is *not* the model being slow — this document decomposes where the 30 seconds
+actually go, and what OCP can do about it.
+
+**The harness deliberately does not go through OCP.** It spawns `tmux` + `claude` directly
+(session prefix `zhiyin-floor-`, never `ocp-tui-*`) and polls `tmux capture-pane` for
+incremental render, so it measures the **true first-token time** of the underlying
+subscription path — the floor OCP could reach if it were perfect.
+
+---
+
+## Measurements
+
+All rows in [`measurements.jsonl`](measurements.jsonl); every number below is recomputable from it.
+
+| Config | n | boot→input-ready (median) | **TTFT (median)** | TTFT range | full answer (median) |
+|---|---|---|---|---|---|
+| baseline (inherits global `effortLevel: xhigh`) | 5 | 1.07 s | **10.35 s** | 8.32 – 17.19 s | 11.32 s |
+| **`--effort low`** | 5 | 1.03 s | **6.17 s** | **5.87 – 6.44 s** | 9.98 s |
+| `--bare` | 5 | 0.44 s | **no answer at all** (5/5 `ttft_ms: -1`) | — | — |
+
+> **Not from this harness**: the direct Anthropic API reference figure (TTFT 0.84–1.64 s, n=2)
+> comes from the 知音 AI project's own smoke test, not from `measurements.jsonl`. It is quoted
+> only to size the gap; do not look for it in the evidence file.
+
+### Where the 30 seconds go
+
+```
+ ~1.0 s   spawn → claude's input bar is ready          ← NOT the bottleneck
+ ~6-10 s  true TTFT (first token rendered in the pane)
+ ~20 s    ████ waiting for the whole turn to finish ████  ← this is the 30s
+```
+
+`runTuiTurn` blocks on the native transcript until a terminal event (`lib/tui/session.mjs`
+"Block on the native transcript … until terminal"; `readTuiTranscript` in
+`lib/tui/transcript.mjs`; ADR 0007 step 4) — i.e. it waits for the **entire turn** to complete
+before returning anything. There is no streaming path. The ~20 s delta between this harness's
+real TTFT and OCP's reported 30–32 s is exactly that.
+
+---
+
+## ⚠️ Blocking constraint: `--bare` silently drops you off the subscription pool
+
+Captured live ([`billing-banner.txt`](billing-banner.txt)) — the startup banner is the **only**
+reliable indicator:
+
+```
+[]                     | Sonnet 5 with xhigh effort · Claude Max
+[--effort low]         | Sonnet 5 with low effort  · Claude Max
+[--bare]               | Sonnet 5 with xhigh effort · API Usage Billing     ← ❌
+```
+
+`--bare` ("skip hooks, LSP, plugin…") **also skips the subscription-credential resolution
+path**. It really does cut boot to 0.43–0.45 s — but you are no longer on the subscription,
+which defeats the entire purpose of TUI mode (ADR 0007 exists solely to reach the
+subscription pool).
+
+**The failure is silent.** All 5 `--bare` samples reached input-ready (boot 0.43–0.45 s), were
+sent the prompt, and then produced **no answer at all** — 60 s timeout, no error, no crash, the
+pane simply never rendered a token (the API-billing account had no credit balance). Nothing in
+the transcript or the exit status reveals this.
+
+**Anyone changing spawn flags must diff the banner line before and after.**
+
+---
+
+## Backlog — four items, ranked by value ÷ effort
+
+### 1. Pass `--effort` explicitly on spawn — **do this first**
+
+`buildTuiCmd` (`lib/tui/session.mjs`) does not pass `--effort` — `grep -rn -- "--effort\|effortLevel" lib/ server.mjs`
+returns zero hits. What the pane's `claude` ends up using therefore depends on **which HOME mode
+`resolveTuiHome()` picked**:
+
+| mode | HOME | effort the pane gets |
+|---|---|---|
+| **real-home** (legacy default — *current* service config: no `CLAUDE_CODE_OAUTH_TOKEN`, no `OCP_TUI_HOME`) | `~` | **inherits the operator's `~/.claude/settings.json` → `effortLevel: xhigh` on this host** |
+| env-token scratch (`CLAUDE_CODE_OAUTH_TOKEN` set — the direction #146/#150 pushed) | `~/.ocp-tui/home` | that settings.json contains only `permissions.additionalDirectories`; `prepareTuiHome()` never writes `effortLevel` → **claude's built-in default** |
+
+**Scope note**: TUI mode is currently *off* on this host (`CLAUDE_TUI_MODE=false`; `/health` →
+`"tui": {"enabled": false}`), so live traffic takes the `-p` path today. The statement below is
+about what happens **when TUI mode is enabled**.
+
+On the current HOME config, **every TUI request would run extended thinking** — pure waste
+for the typical "generate this JSON" request, and it makes latency depend on an unrelated global
+setting the operator may have changed for their own interactive use. And the mode split means
+the effort level silently changes if the operator ever switches to env-token mode.
+**Passing `--effort` explicitly fixes both problems at once.**
+
+- **Effect (real-home, measured)**: TTFT p50 **10.35 s → 6.17 s (−40 %)**, and the spread
+  collapses from 8.32–17.19 s to **5.87–6.44 s**. For a proxy, the variance reduction matters
+  more than the median.
+- **Cost**: one flag. Suggested: a new `OCP_TUI_EFFORT` env var (default `low`), documented in
+  README § "Environment Variables" per `release_kit.new_feature_doc_expectations`.
+- **Risk**: none — banner confirms it stays on `Claude Max` (see `billing-banner.txt`).
+- ⚠️ Do **not** reach for `--bare` to shave boot: see above.
+
+### 2. Real streaming instead of blocking on turn-terminal — **the big one (~20 s)**
+
+Today `runTuiTurn` blocks on the transcript until the turn is *finished*. The pane is already
+rendering tokens incrementally the whole time — this harness proves you can observe first token
+at ~6 s by polling `tmux capture-pane`.
+
+- **Effect**: turns a 30 s wall into a ~6 s TTFT with progressive output; enables SSE streaming
+  on the OCP endpoint instead of a single blob at the end.
+- **Cost**: real work. Pane capture is ANSI/redraw-based and lossy for exact text (wrapping,
+  scrollback, spinner lines). Two candidate sources: (a) incremental reads of the transcript
+  JSONL, (b) `capture-pane` diffing with a stable start marker. (a) is much cleaner **if it
+  holds**.
+- **Prereq spike (do this before designing anything)**: does the transcript JSONL grow *during*
+  a turn, or only at the end? If only at the end, (a) is dead and you are stuck with (b).
+
+### 3. Warm pane pool — ~1 s
+
+Every request spawns a fresh tmux session + `claude` (`randomUUID()` + `new-session`, then
+`kill-session` in `finally`; `grep -rn "pool\|warm\|reuse" lib/tui/*.mjs` → zero hits). Boot to
+input-ready is ~1.0 s, paid on every request. A pool of pre-booted panes (single-use, replaced in
+the background) amortizes it to zero for any workload below the pool refill rate.
+
+- **Effect**: −1.0 s.
+- **Cost**: moderate; interacts with the session reaper and the per-port prefix scoping added in
+  #148 — pooled panes must not look like zombies to the sweep.
+- Lower priority than #1 and #2: it is the smallest slice.
+
+### 4. Trim the prefill — **probably not worth it; know the floor**
+
+After #1–#3, the floor is **~6 s**, and it does not go lower. `claude` always injects the full
+Claude Code system prompt + tool definitions (thousands to tens of thousands of prefill tokens)
+regardless of what you ask it. `--exclude-dynamic-system-prompt-sections` exists and may shave
+some of it — **unmeasured**; worth one spike, but do not expect to reach the direct API's
+~1 s.
+
+**Consequence to accept, and to state in the README**: even fully optimized, TUI mode has a
+**~6 s TTFT floor**, so it cannot serve real-time / interactive-latency consumers. It remains
+appropriate for batch, background, and cost-insensitive-latency use. The 知音 AI project
+excluded it on this basis (their prompt-latency budget is 2–4 s) *independently* of the ToS
+question already documented in the README.
+
+---
+
+## Reproduction
+
+```bash
+# harness never touches OCP's :3456 service or ocp-tui-* sessions, and never kill-server
+bash docs/plans/2026-07-13-tui-latency/floor.sh 5                                  # baseline
+TAG=effort-low EXTRA_ARGS="--effort low" bash .../floor.sh 5                       # −40 %
+TAG=bare       EXTRA_ARGS="--bare"       bash .../floor.sh 5                       # the trap
+
+# billing-pool check for ANY spawn-flag change — the banner is the only source of truth
+tmux new-session -d -s probe -x 200 -y 50 -c "$HOME" \
+  "claude --model claude-sonnet-5 --session-id $(uuidgen) <your-flags-here>"
+sleep 6; tmux capture-pane -p -t probe | grep -E "Claude Max|API Usage Billing"
+tmux kill-session -t probe
+```
+
+## Interaction with OCP while the harness runs
+
+- **Kill direction is safe both ways**: `reapStaleTuiSessions()` only `kill-session`s names
+  matching `ocp-tui-<port>-`, which `zhiyin-floor-*` never matches; and the harness only
+  `kill-session`s its own single session — it contains **no `kill-server`**.
+- **One benign interaction** (only when TUI mode is enabled — the reap tick is itself gated on
+  `TUI_MODE`): OCP's periodic `kill-server` (zombie reaping) is gated on
+  `othersRemain` — *any* foreign-prefixed tmux session suppresses it. So while the harness is
+  running, that sweep is skipped. This is the coexistence guard working as designed; it resumes
+  on the next tick.
+
+## Harness caveats (stated so the numbers are not over-trusted)
+
+- **n=5 per config**, single host, single model (Sonnet 5), single prompt size (~1850 tokens).
+  Enough to separate 6 s from 10 s from 30 s; **not** enough for a p95.
+- TTFT is "marker visible in `capture-pane`", which includes tmux render latency (small, but
+  nonzero) — it is an upper bound on the true first-token time.
+- **The harness's readiness marker is not OCP's.** `floor.sh` waits for `│ >|❯|Try "`; OCP's
+  `tuiInputReady()` matches `/\? for shortcuts/`. These are different events, so the ~1.0 s
+  boot figure is **not** directly comparable to OCP's `BOOT_MS` gate (default cap 4000 ms). It
+  does not affect the conclusions (1 s ≪ 6 s TTFT), but it is not apples-to-apples.
+- The first version of this harness reported TTFT **0.08 s** — a false positive: the prompt
+  literally contained the marker string it was grepping for, so the match fired the instant the
+  prompt was pasted. Fixed by describing the marker instead of spelling it. **The script exited 0
+  and "successfully" produced 5 samples both times** — exit status proves nothing here.

docs/plans/2026-07-13-tui-latency/billing-banner.txt

@@ -0,0 +1,3 @@
+[]                     | ▝▜█████▛▘  Sonnet 5 with xhigh effort · Claude Max
+[--effort low]         | ▝▜█████▛▘  Sonnet 5 with low effort · Claude Max
+[--bare]               | ▝▜█████▛▘  Sonnet 5 with xhigh effort · API Usage Billing

docs/plans/2026-07-13-tui-latency/floor.sh

@@ -0,0 +1,128 @@
+#!/usr/bin/env bash
+# OCP TUI-mode latency floor harness — see README.md in this directory.
+#
+# 目的：回答一个问题——如果把 OCP 现有的两个已知开销砍掉
+#   (a) 每请求 spawn + boot（可用预热进程池消除）
+#   (b) 假流式（等 turn_duration 才返回，可用增量读 pane 消除）
+# 之后，订阅池路径的**真实 TTFT 地板**是多少？
+#
+# 判据：地板 ≤ 4s → OCP 作为"省钱选项"可行；> 8s → 死透，不再讨论。
+#
+# 红线：
+# - 不经过生产 OCP 服务（:3456）—— 直接起 tmux+claude，OCP 进程零干扰
+# - tmux session 前缀用 zhiyin-floor-（**不是** ocp-tui-），避免被 OCP 的
+#   reaper 当成自己的会话杀掉，也避免我们杀到它的
+# - 用 real HOME（凭据）—— scratch HOME + symlink 凭据会 fork OAuth 导致 401
+#   （见跨机记忆 tui_scratch_home_credential_fork）
+set -uo pipefail
+
+N=${1:-5}
+MODEL=${MODEL:-claude-sonnet-5}
+EXTRA_ARGS=${EXTRA_ARGS:-}          # 额外 CLI 参数（如 --effort low --bare）
+TAG=${TAG:-baseline}
+OUT=${OUT:-$(dirname "$0")/measurements.jsonl}
+PROMPT_FILE=$(mktemp)
+PREFIX="zhiyin-floor"
+
+mkdir -p "$(dirname "$OUT")"
+
+# ── 构造提示：~2000 token 的假会议转写 + 明确的起始标记 ────────────────
+# 单行（多行会在 tmux send-keys 时提前触发 Enter）
+build_prompt() {
+  local seg="Speaker A said the quarterly pipeline is tracking behind plan and the enterprise segment needs a different motion. Speaker B replied that the current onboarding flow loses roughly a third of trial accounts before the first integration is complete. They debated whether the fix belongs in product or in customer success. "
+  local body=""
+  for _ in $(seq 1 22); do body+="$seg"; done
+  printf '%s' "You are a real-time meeting copilot. Meeting transcript so far: $body --- Task: produce ONE prompt card as compact JSON with keys: points (array of 3 short Chinese bullet points), keyline (one English sentence the user can read aloud). IMPORTANT: your reply MUST begin with three hash characters immediately followed by the uppercase word CARD (no space between them), then the JSON. No preamble, no markdown fences." > "$PROMPT_FILE"
+}
+build_prompt
+PROMPT_CHARS=$(wc -c < "$PROMPT_FILE" | tr -d ' ')
+
+now_ms() { python3 -c 'import time;print(int(time.time()*1000))'; }
+
+echo "配置: $TAG   参数: [$EXTRA_ARGS]"
+echo "模型: $MODEL   样本: $N   提示长度: ${PROMPT_CHARS} chars (≈$((PROMPT_CHARS/4)) token)"
+echo "输出: $OUT"
+echo
+
+for i in $(seq 1 "$N"); do
+  SESS="${PREFIX}-$$-$i"
+  SID=$(uuidgen)
+
+  # ── 冷启动：spawn + 等输入框就绪 ─────────────────────────────────
+  T_SPAWN=$(now_ms)
+  tmux new-session -d -s "$SESS" -x 200 -y 50 \
+    -e CLAUDE_CODE_DISABLE_CLAUDE_MDS=1 \
+    -e CLAUDE_CODE_DISABLE_AUTO_MEMORY=1 \
+    -c "$HOME" \
+    "claude --model $MODEL --session-id $SID --strict-mcp-config --disallowedTools 'mcp__*' $EXTRA_ARGS" 2>/dev/null
+  if [ $? -ne 0 ]; then echo "[$i] tmux spawn 失败，跳过"; continue; fi
+
+  # 轮询输入框就绪（claude TUI 的输入提示符）
+  READY=0
+  for _ in $(seq 1 150); do   # 上限 15s
+    PANE=$(tmux capture-pane -p -t "$SESS" 2>/dev/null || true)
+    if grep -qE '│ >|❯|Try "' <<<"$PANE"; then READY=1; break; fi
+    sleep 0.1
+  done
+  T_READY=$(now_ms)
+  BOOT_MS=$((T_READY - T_SPAWN))
+  if [ "$READY" -ne 1 ]; then
+    echo "[$i] 启动超时（${BOOT_MS}ms），pane 末 3 行:"
+    tmux capture-pane -p -t "$SESS" 2>/dev/null | tail -3 | sed 's/^/      /'
+    tmux kill-session -t "$SESS" 2>/dev/null
+    continue
+  fi
+
+  # ── 热态：粘提示 → 回车 → 量首 token ─────────────────────────────
+  tmux send-keys -t "$SESS" -l "$(cat "$PROMPT_FILE")" 2>/dev/null
+  sleep 0.4                       # 让粘贴落地（OCP 用 400ms 轮询粒度）
+  T0=$(now_ms)
+  tmux send-keys -t "$SESS" Enter 2>/dev/null
+
+  TTFT_MS=-1
+  for _ in $(seq 1 600); do       # 上限 60s
+    if tmux capture-pane -p -t "$SESS" 2>/dev/null | grep -q '###CARD'; then
+      TTFT_MS=$(( $(now_ms) - T0 )); break
+    fi
+    sleep 0.1
+  done
+
+  # ── 完整回答：pane 连续 2s 不再变化 ──────────────────────────────
+  COMPLETE_MS=-1
+  if [ "$TTFT_MS" -ge 0 ]; then
+    LAST=""; STABLE=0
+    for _ in $(seq 1 900); do     # 上限 90s
+      CUR=$(tmux capture-pane -p -t "$SESS" 2>/dev/null | cksum)
+      if [ "$CUR" = "$LAST" ]; then
+        STABLE=$((STABLE+1))
+        [ "$STABLE" -ge 20 ] && { COMPLETE_MS=$(( $(now_ms) - T0 - 2000 )); break; }
+      else
+        STABLE=0; LAST="$CUR"
+      fi
+      sleep 0.1
+    done
+  fi
+
+  printf '{"i":%d,"tag":"%s","model":"%s","extra_args":"%s","prompt_chars":%s,"boot_ms":%d,"ttft_ms":%d,"complete_ms":%d}\n' \
+    "$i" "$TAG" "$MODEL" "$EXTRA_ARGS" "$PROMPT_CHARS" "$BOOT_MS" "$TTFT_MS" "$COMPLETE_MS" | tee -a "$OUT"
+
+  tmux kill-session -t "$SESS" 2>/dev/null
+  sleep 1
+done
+
+rm -f "$PROMPT_FILE"
+echo
+echo "=== 汇总 ==="
+python3 - "$OUT" <<'EOF'
+import json,sys,statistics
+rows=[json.loads(l) for l in open(sys.argv[1]) if l.strip()]
+ok=[r for r in rows if r['ttft_ms']>=0]
+if not ok: print("无有效样本"); sys.exit()
+def s(k):
+    v=[r[k] for r in ok if r[k]>=0]
+    return f"n={len(v)} 中位={statistics.median(v)/1000:.2f}s 最小={min(v)/1000:.2f}s 最大={max(v)/1000:.2f}s" if v else "无"
+print(f"  冷启动 boot      : {s('boot_ms')}   ← 预热进程池可完全消除")
+print(f"  TTFT（首 token） : {s('ttft_ms')}   ★ 这就是地板")
+print(f"  完整回答         : {s('complete_ms')}")
+print(f"\n  失败样本: {len(rows)-len(ok)}/{len(rows)}")
+EOF

docs/plans/2026-07-13-tui-latency/measurements.jsonl

@@ -0,0 +1,15 @@
+{"i": 1, "tag": "effort-low", "model": "claude-sonnet-5", "extra_args": "--effort low", "prompt_chars": 7451, "boot_ms": 1077, "ttft_ms": 6172, "complete_ms": 9929}
+{"i": 2, "tag": "effort-low", "model": "claude-sonnet-5", "extra_args": "--effort low", "prompt_chars": 7451, "boot_ms": 1026, "ttft_ms": 6160, "complete_ms": 9996}
+{"i": 3, "tag": "effort-low", "model": "claude-sonnet-5", "extra_args": "--effort low", "prompt_chars": 7451, "boot_ms": 1010, "ttft_ms": 6437, "complete_ms": 9977}
+{"i": 4, "tag": "effort-low", "model": "claude-sonnet-5", "extra_args": "--effort low", "prompt_chars": 7451, "boot_ms": 1033, "ttft_ms": 5872, "complete_ms": 9944}
+{"i": 5, "tag": "effort-low", "model": "claude-sonnet-5", "extra_args": "--effort low", "prompt_chars": 7451, "boot_ms": 1154, "ttft_ms": 6387, "complete_ms": 9993}
+{"i":1,"tag":"baseline","model":"claude-sonnet-5","extra_args":"","prompt_chars":7451,"boot_ms":1300,"ttft_ms":8321,"complete_ms":9939}
+{"i":2,"tag":"baseline","model":"claude-sonnet-5","extra_args":"","prompt_chars":7451,"boot_ms":1070,"ttft_ms":10347,"complete_ms":11320}
+{"i":3,"tag":"baseline","model":"claude-sonnet-5","extra_args":"","prompt_chars":7451,"boot_ms":911,"ttft_ms":13061,"complete_ms":15163}
+{"i":4,"tag":"baseline","model":"claude-sonnet-5","extra_args":"","prompt_chars":7451,"boot_ms":1441,"ttft_ms":9981,"complete_ms":11066}
+{"i":5,"tag":"baseline","model":"claude-sonnet-5","extra_args":"","prompt_chars":7451,"boot_ms":1036,"ttft_ms":17189,"complete_ms":17985}
+{"i":1,"tag":"bare","model":"claude-sonnet-5","extra_args":"--bare","prompt_chars":7451,"boot_ms":429,"ttft_ms":-1,"complete_ms":-1}
+{"i":2,"tag":"bare","model":"claude-sonnet-5","extra_args":"--bare","prompt_chars":7451,"boot_ms":437,"ttft_ms":-1,"complete_ms":-1}
+{"i":3,"tag":"bare","model":"claude-sonnet-5","extra_args":"--bare","prompt_chars":7451,"boot_ms":444,"ttft_ms":-1,"complete_ms":-1}
+{"i":4,"tag":"bare","model":"claude-sonnet-5","extra_args":"--bare","prompt_chars":7451,"boot_ms":446,"ttft_ms":-1,"complete_ms":-1}
+{"i":5,"tag":"bare","model":"claude-sonnet-5","extra_args":"--bare","prompt_chars":7451,"boot_ms":441,"ttft_ms":-1,"complete_ms":-1}