Content-verified turn attribution + model sets; silent TUI, --continue preload, version hash#44
Closed
lroolle wants to merge 4 commits into
Closed
Content-verified turn attribution + model sets; silent TUI, --continue preload, version hash#44lroolle wants to merge 4 commits into
lroolle wants to merge 4 commits into
Conversation
…ty UX Session reconstruction (devlog 2026-07-17): - Per-turn attribution is index-first, content-verified against the pair's assembled response (turnContentSig), content-scan on mismatch. Claude Code repacks history with ephemeral notice turns, so raw indices land on the wrong turns — the 5-model test session had three silently unattributed replies and two attributed by luck. - Pairs matching nothing classify REWOUND (prefix-divergent: /rewind or an edited turn) or UNATTRIBUTED — marked in the conversation, never silently blank. Rewound exchanges mark their divergence point and link to the kept wire pair. - A thread's model is a set (per-model requests/tokens/cost); the face model is the one with the most output tokens. "fable-5 · 63 turns" for five models' work becomes "fable-5 +4 models · 63 turns". - compact rewind guard: a request whose final history message appears nowhere in the keeper's packing holds the only copy of an erased exchange — kept full, never stubbed. Verified pre/post-compact: identical turns and attribution on the real trace. - Regression fixture cut from the controlled 5-model + /rewind session, sanitized with equality-preserving hash tokens (10KB zst, leak-swept). Launch & continuity UX: - cctrace is silent while the traced client owns the terminal: all output funnels through src/termlog.ts, buffered from spawn to exit, flushed after — mid-session continuity merges and crash-guard notes no longer corrupt the TUI. - --continue/--resume preloads the resumed session speculatively (newest prior session id, or the explicit --resume id), so the UI opens populated; the first live request confirms the guess or evicts the preload with a client re-init. - --version and the banner print the commit hash: baked in by make build --define, git fallback on source runs (guarded so an npm install inside another repo never reports that repo's HEAD). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
…n tab The Session tab gains the third grouping level (session-tab.md decision 1): messages -> threads -> sessions -> project. - Threads are session-scoped: the grouping key is <sid>|<wire key>, so two sessions whose first message is identical (/clear mid-run) never merge into one thread. "" stays an honest no-session-id bucket. - Threads pane: >=2 session ids render collapsible per-session sections, newest activity first — header carries short sid (click = copy full), wall-clock range, request count, error rollup. Fold state survives live re-renders keyed by sid. Single-session traces render flat: zero new chrome, the common case pays nothing. - Routes: #/session/<sid8>[/<thread-key>] resolves sid-prefix after the thread-key back-compat check; old links keep working. [ / ] switch sessions from the keyboard. - Default focus is the newest session's main thread; a NEW session id appearing mid-run follows only while tailing — reading history is never yanked. - Request rows (the selected thread's list) mark rewound / compact-folded / failed requests inline; thread meta counts rewound exchanges; assistant turns that switch models prefix "→ model". - grok recap classification now reads the conv header instead of a key prefix (the sid prefix broke the old check — caught by tests). Verified through the dom-stub (the real page script executes): zero-chrome single-session, ordered sections, sid-prefix routing, grammar-clean markup. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Member
Author
|
Third commit: the sessions layer (session-tab.md decision 1) — the Session tab is now the full hierarchy: Selection doubles as thread expand/collapse (the existing affordance); request rows gained rewound / folded / err markers. Thread keys are now session-scoped (sid|key) so /clear twins never merge — old #/session/ links still resolve, new #/session/[/] routes added, [ ] switches sessions. Single-session traces render byte-flat: zero new chrome. 430 tests green, including dom-stub renders of both paths. |
The default thread label was "fable-5 +4 models · 63 turns" — the model
occupied the identity slot, which read as "threads are grouped by model"
(they aren't; a thread is a conversation that can span models via
/model). Clean split:
- label names the conversation: "63 turns" / "[explore] search for..." /
"prewarm"; the kind badge already says chat/agent/utility
- the model becomes a quiet right-aligned chip on the card ("fable-5 +4"
after mid-thread switches, per-model split in the tooltip — one
modelTitle helper shared with the convo-pane chip)
- selection emphasis moves up to the SESSION container: a faint accent
wash on the section summary and the selected thread head, replacing
the accent border (edges read as chrome — same rule that fixed
user-turn emphasis)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The session card takes the bordered-box treatment threads used to have; threads flatten to divided rows inside it; the selected thread's request rows nest below. Containment is drawn by structure, not indentation. Header gets real hierarchy instead of a flat mid-dot line: identity left (short sid, strong, click-to-copy + conversation turns), quiet attributes right-aligned (HH:MM range — no seconds, no degenerate ranges — request count, errors). The word "session" is gone: the box is the session. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Member
Author
|
Superseded by #45 (v0.18.0): this branch was the base of sessions-layer-work — content-verified attribution, model sets, silent TUI, --continue preload, and the version hash all shipped in the 0.18.0 squash. Closing rather than merging a duplicate. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Two cohesive chunks, both regression-tested (424 tests green).
Session attribution (devlog 2026-07-17, decisions 2/3/4)
The 5-model controlled session exposed three bugs: per-turn attribution
indexed by history length silently missed turns when Claude Code repacked
history (ephemeral notice turns -> non-monotonic hist lengths 2,4,5,10,9,
11,...), the thread model was last-write-wins ("fable-5" named for five
models' work), and /rewind erased captured exchanges from the
reconstruction with no trace.
pair's assembled response (new turnContentSig, capped compare per the
devlog CPU tradeoff), content-scan on mismatch. Verified claims beat
index-only ones; stubs/errored streams stay index-primary.
Real-trace result: 39/40 assistant turns attributed, 0 mismatches; the
one hole is a reply whose Bash command was edited client-side before
entering history — truthfully rendered "unattributed", never blank.
"Okay." exchange classifies rewound-not-lost at its divergence index,
gets a quiet dashed marker in the conversation linking to the kept wire
pair, and rewound/unplaced counts join the thread chips.
most output tokens; label "fable-5 +4 models · 63 turns"; split in the
model chip tooltip.
history message appears nowhere in the keeper's packing holds the only
copy of an erased exchange — kept full. Sound because every history
message was once some request's tail. Response-only rewinds still stub
safely (responses are never touched); their class softens to "unplaced".
Verified pre/post-compact on the real trace: identical turns, identical
attribution.
thread sanitized with equality-preserving hash tokens (10KB, leak-swept:
no paths/names/text). 9 new tests pin models, recovered holes,
no-misattribution, rewound classification, and retry-vs-branch-tip
compact behavior. Note: the fixture is strictly harsher than live on one
pair (an edit beyond the 160-char sig cap that live prefix-compare
attributes) — documented in the test.
Still open, sequenced after: sessions layer (session-tab.md design in
flight), OpenAI histLen audit (needs a real multi-model codex trace).
Launch & continuity UX (ideas 11/12/13)
from spawn to child exit, flushed after. Kills the mid-session
"session continued — merged N pairs" line, update-check status, and
crash-guard notes corrupting the TUI.
newest prior session (or the explicit --resume id) so the UI opens
populated; the first live request confirms or evicts (client re-init —
reuses the existing init full-replace, zero new ws protocol).
binaries, git fallback for source runs, guarded against reporting the
host repo's HEAD from an npm install.
🤖 Generated with Claude Code