2 Commits

Include renames

Author	SHA1	Message	Date
taodengandClaude Fable 5	6848f9751c	docs(plans): TUI streaming is not achievable — prereq spike result + honest README constraints ... Backlog #2 of docs/plans/2026-07-13-tui-latency demanded a prereq spike before any streaming design: does the transcript JSONL grow during a turn, or only at the end? The spike was run. All three candidate sources are dead: (a) transcript JSONL — grows at EVENT granularity; the assistant's text event is written as ONE complete line, ~0.3s before the terminal turn_duration event (observed: turn_duration 7319ms; text event at t+7.0s, terminal at t+7.3s). (b) tmux capture-pane — the pane is a RENDERED view, not the text. Same turn, transcript T = '## Semaphore\n\nA **semaphore** is a synchronization…' pane = '⏺ Semaphore' / ' A semaphore is a synchronization…' '## ', '**' and ```-fences are absent from the pane entirely (rendered to ANSI, then stripped by capture-pane -p). T.startsWith(paneText) is FALSE both raw and indent-stripped — not on redraw, but on essentially every markdown answer. capture-pane -e recovers styling, never source spelling: no unique inverse. (c) --debug-file — byte-exact ('last_assistant_message':'## Title\n\n**alpha…'), but only inside end-of-turn Stop-hook payloads; zero content_block_delta / text_delta events; ~2.7MB per turn. --output-format stream-json, the only interface emitting token deltas, requires -p — the metered-billing path TUI mode exists to avoid (cc_entrypoint=sdk-cli). The constraint is structural. OCP's TUI SSE is, and remains, replay-only. Also corrects this plan's own "~20s waiting for the whole turn" decomposition, which was inferred from an external 30-32s report and never measured through OCP. Measured through a real OCP instance (TUI, claude-sonnet-4-6, n=5): median 11.30s before #156, 9.55s after, vs a native turn_duration of ~7.3s → OCP's own overhead is ~2-4s, not ~20s. The remainder is generation time, which streaming would not shorten (it moves the first byte, not the last) — so a consumer needing the COMPLETE answer, which is the JSON-card case that motivated this work, would have gained nothing from streaming. Backlog #4 measured while here: --exclude-dynamic-system-prompt-sections gives ZERO marginal benefit (TTFT median 6.39s vs 6.17s for --effort low alone, n=5, one worse outlier). Do not adopt. Banner stayed on Claude Max. README: documents the ~6s TTFT floor plainly (TUI mode cannot serve interactive-latency consumers) and states that no-token-streaming is structural rather than a missing feature. No code change. No version bump (docs-only). Not endpoint-touching: no server.mjs diff, so no cli.js citation applies. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01VqgWJcjxrjjL9L9SkpZyXR	2026-07-13 15:32:41 +10:00
4 people	6854075c01	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>	2026-07-13 14:22:17 +10:00