Skip to content

Generate session titles with the configured provider - #21

Open
artcashin wants to merge 70 commits into
prime-radiant-inc:mainfrom
artcashin:feat/title-provider-wiring
Open

Generate session titles with the configured provider#21
artcashin wants to merge 70 commits into
prime-radiant-inc:mainfrom
artcashin:feat/title-provider-wiring

Conversation

@artcashin

@artcashin artcashin commented Aug 2, 2026

Copy link
Copy Markdown

Follow-up to #20. Draft — blocked on #19 and #20.

Session titles were a second hardcoded call to Claude Haiku through the Agent SDK. With summaries routed through summary_provider in #20, configuring a local model left titles silently still calling Anthropic. A provider setting that only half applies is worse than one that doesn't exist, because the surprise stays invisible until a bill or an offline box makes it visible.

generateTitle, titleSession and backfillTitles now take the provider and route through the shared complete() helper, so both summarize and backfill-titles honour it. Absent config still uses Claude Haiku, unchanged.

Why this is stacked rather than part of #20

src/titles.ts doesn't exist on main — it arrives with #19. So this wiring depends on both:

The branch is feature/react-frontend merged with #20's branch, plus one commit containing the wiring itself. Until both land, the diff against main shows all three; it collapses to the single wiring commit once they merge. Review that commit (6044e18) in isolation.

The merge commit resolves one conflict in summarize.ts, where #19 adds the titling block and #20 changes the upsertJournalEntry call. Resolution is the union, with titles deliberately left calling Claude so the follow-up commit is exactly the wiring and nothing else.

Testing

224 tests pass, typecheck clean. Written test-first: src/titles.test.ts runs generateTitle against a real local HTTP server and asserts the configured model is the one contacted, plus the answer-cleanup behaviour (quote stripping, first-non-empty-line).

🤖 Generated with Claude Code

krsnaa and others added 30 commits May 8, 2026 12:53
@krsnaa
feat: detailed ingest output with skip reasons, progress bar, and totals
0342462 
Replaces the three-line summary with a richer report:

- Per-source file counts during the scan phase
- Live progress bar (TTY-only, 100ms throttle, sub-char eighth-block fill)
- Splits skipped into already_ingested / empty / duplicate_id so the
  number is actionable instead of opaque
- Total messages ingested + elapsed time

Before:
  Scanning 2 source(s)...
  Found 4650 session file(s)
  Ingested: 4313, Skipped: 337, Errors: 0

After:
  Scanning 2 source(s)...
    4,294 in /Users/me/.claude/projects
      356 in /Users/me/.codex/sessions
  Found 4,650 session file(s)
    [████████████████████] 100% · 4,650/4,650
  Ingested 4,313 session(s) (812,540 messages) in 47.2s
  Skipped 337: 337 empty
@GradientCake @claude
feat: add Cursor session support (prime-radiant-inc#17)
94e167f 
Ingest Cursor session transcripts. Cursor records are {role, message}
with no `type` field, and content blocks share Claude Code's
{type:"text", text} shape, so the existing text extractors are reused.

Metadata absent from Cursor transcripts is derived after parsing:
- session id from the filename UUID
- start/end timestamps from file birthtime/mtime (Cursor stores none)
- project name from Cursor's encoded directory string (used verbatim)

`~/.cursor/projects` is not added to default sources; it stays opt-in
and is documented in the README along with the format's caveats.

Adds parser tests, an ingest regression test, fixtures, and docs.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
@artcashin @claude
docs: session groups design spec
567ca34 
Manual groups over coding sessions: a Groups nav tab, one group per
session, in-app create/rename/delete, membership in a separate table
that survives re-ingest.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
docs: session groups implementation plan
e6c6a60 
7 TDD tasks: schema, helper module, nav, views, routes, session
control, verification. Corrects spec FK note (foreign_keys=ON means
session_id must have no FK to survive re-ingest).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin
feat(groups): add groups and session_groups tables
20fef48
@artcashin
feat(groups): add group helper module (create/list/rename/delete/assign)
fbd7734
@artcashin @claude
feat(groups): add Groups tab to nav
ad479cc 
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin
feat(groups): add groups index and detail views
4c212d1
@artcashin
feat(groups): add group + session-assign routes
a770550
@artcashin
feat(groups): add 'Add to group' control to session view
1bbe0b5
@artcashin
fix(groups): harden assign route, use SQLITE_CONSTRAINT_UNIQUE, test …
f9206c9 
…listGroups ordering
@artcashin @claude
docs: Desktop group import (Phase 1) design spec
054537a 
One-way import of Claude Desktop groups (dframe-group-scopes) into the
notebook: reader + reconcile (mirror by desktop_id, manual groups
untouched), Ungrouped view, and a block-while-Desktop-open guard behind
a single policy switch. Write-back deferred to Phase 2.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
docs: Desktop group import (Phase 1) implementation plan
8c116bf 
7 TDD tasks: desktop_id migration, classic-level reader (schema pinned
against real store), reconcile/mirror, Ungrouped view, block-while-open
guard, import route+button+CLI, verification.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
docs: Show/Hide Thinking & Tools session-display design spec
4191bd4 
Approach A (re-parse source JSONL on demand). Default text-only; Show
thinking/tools via query params re-parses source_path, warns if the
file is unavailable. No ingest/schema change. Precedes the group work.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
docs: Show/Hide Thinking & Tools implementation plan
6286884 
4 TDD tasks: transcript parser, enriched session render + toggle
controls + CSS, route params, verification. Re-parses source_path on
demand; default view unchanged.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin
feat(session): add transcript parser (text/thinking/tool blocks)
5ab1ab3
@artcashin
feat(session): render thinking/tools on demand with toggle controls
1a38bf0
@artcashin
feat(session): wire thinking/tools query params into /session/:id
a7dd804
@artcashin @claude
fix(session): encode & in toggle href, dimension-specific no-data not…
2a118c1 
…es, param-preservation test

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
docs: transcript visual-match (React viewer) design spec
16e431f 
Core match: collapsible tool calls (name + preview, result paired
inside), thinking bubbles + token estimate, teal accent + rounded
styling on the notebook's light palette. No markdown/diff (deferred),
no new deps.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
docs: transcript visual-match implementation plan
692cfa4 
3 TDD tasks: parser tool id/input enrichment, collapsible-tool +
thinking-bubble render rework + CSS, verification.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin
feat(session): capture tool id/input and tool_result id in transcript…
c688f02 
… parser
@artcashin
feat(session): collapsible tool calls, thinking bubbles, teal accent …
f2f7236 
…styling
@artcashin
fix(session): pair tool results order-independently; style orphan res…
5f8b13e 
…ult box
@artcashin @claude
chore(session): drop dead inline style; align spec on duplicate-resul…
8900ee2 
…t edge

Final-review cleanups: remove redundant style="display:block" on the
orphan tool_result div; update spec edge-case wording to match the
implemented (extras-dropped) behavior.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
docs: combined-app vision & roadmap (React frontend on notebook backend)
0652709 
Umbrella doc: keep engineering-notebook backend, new React/Vite frontend
matching claude-session-viewer's session display, plus Desktop groups.
Recommends monorepo + a 5-phase roadmap (Phase 1 = session display
parity). Evidence-based session-chain findings (resume = same session;
subagents are the multi-file case). Each phase gets its own spec/plan.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
docs: Phase 1 spec — foundation + session display parity
56a154e 
React/Vite app in web/, Hono JSON API (session list, structured
transcript, subagent), polished session viewer (collapsible tools,
thinking, subagent nesting, client-side hide/show toggles), Tailwind.
Subagent->Task mapping via first-prompt match (viewer's strategy).
Spikes deferred to plan: on-disk subagent layout, Vite<->Hono wiring.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
docs: Phase 1 spec — exact subagent mapping via .meta.json (spike)
96ed3e5 
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
docs: Phase 1 implementation plan (foundation + session display)
52835d0 
7 tasks: Vite/Hono scaffold+wiring, structured transcript endpoint,
subagent discovery via .meta.json + endpoints, session list, React API
layer + list view, session viewer (collapsible tools/thinking/subagents
+ toggles), verification. Additive-only; legacy views/DB untouched.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
feat(react): scaffold web/ Vite app + Hono /api router + wiring
8bcefa9 
- web/ Vite React-TS + Tailwind SPA; App pings /api
- createApiRouter mounted at /api; GET /api/ping
- createApp({react}) serves web/dist SPA (assets + index.html fallback),
  skipping legacy views; --react flag threaded through serve
- exclude web/ from backend tsconfig
Verified end-to-end: dev proxy + prod build; /api/ping, SPA, assets, and
client-route fallback all 200.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
artcashin and others added 20 commits July 19, 2026 14:11
@artcashin @claude
feat(react): resolve active conversation branch (port viewer tree.ts)
da6fe77 
Port claude-session-viewer's buildMessageTree + resolveActivePath: the
transcript endpoint now reconstructs the uuid/parentUuid tree (bridging
filtered meta/summary records) and returns the active branch instead of
every flat record. Header shows the active-path length. Codex/uuid-less
logs fall back to flat order.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
feat(react): show a 'redacted thinking' marker for signature-only blocks
ef10ca9 
Claude Code sometimes emits a thinking block with only a signature
(encrypted) and empty text. The viewer rendered these as blank boxes;
we dropped them. Now the parser keeps empty thinking blocks and
ThinkingBlock renders a "🔒 redacted thinking" marker, so it's visible
that reasoning occurred even when the text is encrypted. Same change
applied to the local claude-session-viewer's ThinkingBlock.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
perf(react): incremental rendering for large transcripts
22c238c 
Render the transcript in bounded batches (80) and grow as the reader
scrolls (IntersectionObserver sentinel), so a 1000+ message session no
longer freezes on first paint or when toggling thinking/tools. Small
sessions render in one batch (jsdom tests unaffected).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
feat(react): move Show/Hide thinking & tools to the top bar
d57c004 
Lift the toggle state into a TranscriptTogglesProvider (context) so the
buttons live in the always-visible top bar, left of the search box, and
stay usable no matter where you are in the session scroll. SessionView
reads the toggles from context instead of owning them.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
feat(sessions): session titles — Desktop titles + LLM-generated fallback
99e6324 
- sessions.title / title_source columns
- import captures each Claude Desktop session's title (titleSource
  desktop|user) from local_*.json (same files the group import reads)
- generate a Desktop-style title via the Claude Agent SDK for Claude
  Code sessions without one; stored as title_source=generated
- `engineering-notebook title [--generate --limit N]` CLI + POST
  /api/sessions/:id/title on-demand endpoint
- API exposes titles (session list, group sessions, journal/project
  entry sessions); panel 2 and Groups list show the name instead of
  "Session N"

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
fix(titles): exclude subagents from title backfill
18f52b1 
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
fix(api): include session titles in journal-entries endpoint too
1e8b1bc 
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
feat(titles): panel-3 title, summarize generates titles, sticky user …
f0c99b1 
…edits

- Panel 3 h1 shows the stored session title (Desktop/generated),
  falling back to the first prompt.
- summarize now generates a Desktop-style title for each summarized
  session that lacks one (applies Desktop titles first so it only
  LLM-generates where genuinely missing).
- User-edited Desktop titles are sticky (never overwritten by auto or
  generated); auto/generated titles refresh on re-import. Expose
  title_source in the session API.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
fix(transcript): hide local-command-stdout messages (command output)
d3fa01d 
A user record whose content is purely <local-command-stdout>…</…> is
machine output, not a user turn — it was rendering as a 'You' bubble.
Skip it in the tree build (bridging parentUuid through it), matching the
same fix applied to the local claude-session-viewer's buildMessageTree.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
feat(subagents): link subagent sessions to their originating parent
cefba3b 
Ingested subagent transcripts (<project>/<parentUUID>/subagents/agent-*.jsonl)
now record parent_session_id — taken from the records' own sessionId without
triggering the continuation prefix-skip (a separate continuationParentId drives
that). A new relinkSubagents() fills the link (from the column or recovered from
the path) and re-homes each subagent's project_id to its parent's project. It
runs at the end of ingest and is order-independent + idempotent, so it also
backfills. Adds idx_sessions_parent.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
feat(api): expose subagent links and keep subagents out of session lists
1f4c422 
/api/sessions/:id now returns the subagent backlink (parent_title, gated on
is_subagent so continuations aren't mislabeled), subtask_title, spawn_tool_use_id,
and the session's ingested subagents ordered chronologically. Journal, project,
and group rows carry their nested subagents via a shared ingestedSubagents()
helper (single batched query, filtered to ingested rows so there are no dead
links). Ungrouped and the flat /api/sessions list exclude subagents.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
feat(web): surface subagents across the 3-panel viewer
5b30dfb 
Panel 2 nests each session's subagents (revealed once the session is selected),
labelled by subtask title. Panel 3 gains: a compaction-proof SubagentIndex; a
"Subagent of …" backlink (shown only for subagents) that navigates to the parent
and scrolls/ring-highlights the exact spawn point, falling back to the index when
the spawn was compacted off the transcript; inline spawn links matched by
tool_use id (name-agnostic — Claude Code names the tool "Agent", not "Task"),
visible even with tools hidden; and subtask titles as the panel header. The
focus scroll fires once per target and the window grows-only, so reading past a
spawn no longer snaps back.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
fix(web): escape the date in legacy summary-card views
f540656 
The date was interpolated raw into the muted/error summary cards; wrap it in
escapeHtml() like the surrounding fields.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
fix(sync): ingest local sources even when no remote source is configured
d0e88f9 
Ingestion was nested inside the remoteSources block, so a purely local setup
never scanned/ingested on sync. Hoist the scanSources/ingestSessions call so it
always runs, appending any remote cached paths when present.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
feat(transcript): uncompacted-by-default view + compacted/uncompacted…
c6242ac 
… toggle

Compacted sessions keep their full pre-compaction messages in the same file, but
active-path resolution prunes them (e.g. 1,036 shown of 3,122). Panel 3 now
defaults to the uncompacted view: the transcript parser gains a `full` option
(returns every message in file order, dropping the injected isCompactSummary
blob) and a `compacted` flag; the endpoint honors ?full=1. A third top-bar
toggle — "View compacted" / "View uncompacted" — switches modes, defaulting to
uncompacted so pre-compaction detail (and its subagent spawn links) is shown.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
style(transcript): put the compacted toggle first in the top bar
45751c9 
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
feat(transcript): disable the compacted toggle when the session isn't…
1023a33 
… compacted

Plumb the transcript's `compacted` flag to the toggle bar. The "View compacted"
button is disabled (and greyed) unless the open session actually has a compacted
view to switch to. Non-compacted sessions are forced back to the default
uncompacted view so the disabled toggle never strands the reader in compacted
mode; the toggle re-disables when leaving the session.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
style(transcript): color the compacted toggle by availability
22e9392 
Light green (matching the other toggles) when the session has a compacted view;
gray when it doesn't.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
feat(groups): drag a session onto a group to assign it (drop on Ungro…
fec99dc 
…uped to remove)

Adds POST /api/sessions/:id/group ({ groupId } assigns, { groupId: null }
unassigns; 404s on missing session/group). In the Groups view, panel-2 session
rows are draggable and panel-1 group rows (and Ungrouped) are drop targets with a
hover highlight; dropping assigns/unassigns the conversation and refreshes the
counts and current list. Subagent rows stay non-draggable.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@artcashin @claude
fix(ci): scope bun test to the backend and run the web suite in CI
660aad8 
`bun test` collected web/src/**/*.test.tsx and failed 18 of them with
"document is not defined". Those are React component tests that need a DOM,
which is configured for vitest in web/vite.config.ts — a file Bun's test
runner does not read. Nothing was wrong with the tests themselves: they pass
under their intended runner.

The failure was invisible locally because the pre-commit hook runs the scoped
`bun test ./src`, while both CI workflows run a bare `bun test`. main has no
web tests, so this branch would have turned CI red on merge.

bunfig.toml scopes Bun's runner to src/, leaving it responsible for the
backend suite alone. That also excludes web/src/session/adapt.test.ts, which
is DOM-free and did run under Bun, so CI now runs the web suite with vitest —
covering all 20 web tests, which CI never executed at all. web/ is not a
workspace of the root package, so its dependencies install separately.

Verified: bare `bun test` 182 pass / 0 fail, `bun run test:web` 20 pass,
typecheck clean.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This was referenced Aug 2, 2026
Open
Closed
@artcashin
artcashin marked this pull request as ready for review August 2, 2026 20:03
artcashin and others added 6 commits August 2, 2026 16:11
@artcashin
Merge prime-radiant-inc#16 (verbose ingest output)
b30b853
@artcashin
Merge prime-radiant-inc#18 (Cursor session support)
7754159
@artcashin @claude
feat: import OpenCode sessions and make the summary model configurable
2ad49f2 
OpenCode source adapter
-----------------------
OpenCode keeps sessions in a single SQLite database rather than one file per
session, so it cannot be scanned like the Claude Code and Codex sources. An
opt-in adapter exports each session into a staging directory of JSONL files
during `ingest`, which the normal scanner then picks up — leaving dedup,
--force, grouping, summarization and the web UI untouched.

Three things the implementation has to work around, each found empirically
against OpenCode 1.18.0:

- `opencode session list` only reports sessions belonging to the current
  working directory's project, so no single cwd can enumerate them all.
  Sessions are enumerated from OpenCode's database; transcripts still come
  from `opencode export`, which works from anywhere. That keeps the fragile
  part (transcript shape) on the supported CLI, with only a five-column query
  touching the schema.
- `opencode export` yields empty stdout over a pipe but is complete when
  redirected to a file, and a single export can run to megabytes. Both call
  sites go through one runToFile helper.
- is_subagent was derived purely from Claude Code's /subagents/ path
  convention, so flat-staged files always read as 0. Formats that state it
  outright now win; Claude Code keeps path detection, because its
  parentSessionId also covers continuations and would otherwise misflag them.

Projects are keyed off each session's working directory, so OpenCode and
Claude Code work in the same repo on the same day lands in one journal entry.

Configurable summary provider
-----------------------------
Summaries were hardcoded to Claude Haiku via the Agent SDK. A summary_provider
config block now selects any OpenAI-compatible endpoint, including a local
llama.cpp server. Absent config keeps the previous behaviour.

The Claude auth preflight is skipped for non-Anthropic providers, which
authenticate with their own key and would otherwise be blocked on every run.
Entries record the model that actually produced them. API keys are referenced
by environment variable name and never stored in config. Reasoning models
spend completion tokens before emitting content, so an exhausted budget fails
loudly rather than writing an empty summary.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
@artcashin
Merge OpenCode import + configurable model (rebased on prime-radiant-…
a2304a2 
…inc#16, prime-radiant-inc#18)

# Conflicts:
#	src/summarize.ts
@artcashin @claude
feat(titles): generate session titles with the configured provider
44b4f26 
Session titles were a second hardcoded call to Claude Haiku through the Agent
SDK. With summaries routed through summary_provider, configuring a local model
left titles silently still calling Anthropic — a provider setting that only
half applies is worse than one that doesn't exist, because the surprise is
invisible until a bill or an offline box makes it visible.

generateTitle, titleSession and backfillTitles now take the provider and route
through the shared complete() helper, so `summarize` and `backfill-titles`
both honour it. Absent config still uses Claude Haiku, unchanged.

This could not ship in the standalone OpenCode PR because src/titles.ts only
exists on the React frontend branch, so it lands here on top of both.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
@artcashin @claude
fix(ingest): repair the counter lost when prime-radiant-inc#16 and pr…
b09ccb0 
…ime-radiant-inc#19 merge

prime-radiant-inc#16 replaced ingest's single `skipped` counter with alreadyIngested / empty /
duplicateId, deriving `skipped` from their sum, and dropped the no-start-time
guard. prime-radiant-inc#19 keeps that guard and still increments `skipped`.

Git merges the two cleanly: prime-radiant-inc#16's counters plus prime-radiant-inc#19's guard, referencing a
variable that no longer exists. Tests pass; `tsc` does not:

    src/ingest.ts(108,9): error TS2304: Cannot find name 'skipped'.

A session with no start time cannot be placed on a date, so it is as unusable
as one with no messages and is counted as empty, which flows into the derived
`skipped`. Keeping the guard rather than dropping it as prime-radiant-inc#16 did: without it a
session with no timestamp is inserted with an empty started_at and misgroups.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
@artcashin
artcashin force-pushed the feat/title-provider-wiring branch from 6044e18 to b09ccb0 Compare August 2, 2026 20:24
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@artcashin @krsnaa @GradientCake