Two small ergonomic fixes after the impeccable pass:
- TaskLane keyboard hints (⏎ submit · ⇧⏎ newline) under each open input
were rendered at text-muted-foreground/70, just shy of legible at a
glance. Drop the /70 opacity modifier so they read at full muted weight
on first look without becoming visually loud.
- 12 sites across the session screen had explicit font-sans utilities,
but the body default is already IBM Plex Sans (via --font-sans in
index.css and Tailwind v4's default-sans binding). None of the call
sites sit inside a font-heading or font-mono cascade, so every
font-sans there was a no-op. Drop them. ConcludeSessionModal also had
three "text-xs font-sans text-xs" triplets — drop both the redundant
font-sans and the doubled text-xs in one pass.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Multi-step UX refactor of the assistant chat session screen, run via the
$impeccable skill. Heuristic score moved 24/40 → 33/40 (+9), with the biggest
gains on Aesthetic & Minimalist (1→3), Consistency & Standards (1→3), and
Recognition Rather Than Recall (2→4).
Distill — chat region:
- Remove the "Suggested checks" chip strip + selected-chip detail card; the
TaskLane is the single canonical home for "what to do next"
- Add an inline Next steps · N pending cue above the latest action-bearing
AI bubble (anchors attention without duplicating the lane's items)
- Link banner ↔ script-panel lifecycle: collapsing or dismissing the
ProposalBanner now also hides the InlineNoTemplateDialog / TemplateMatchPanel
- Drop backdrop-blur on the handoff-context overlay (DESIGN-SYSTEM hard rule)
Quieter — drop decoration overshoot:
- Remove 3px side stripes on TaskLane done cards, all 6 ProposalBanner modes,
WhatWeKnowItem fact rows
- Drop bg-gradient surfaces on WhatWeKnow + every ProposalBanner mode
- Drop 2px accent borderTop on the TaskLane header
- Replace bordered avatar boxes in banners with inline state-colored icons
- Each surface now uses a single decoration channel (top border + inline icon)
Layout:
- Header consolidates to Resolve + Escalate + ⋯ kebab; Context, New Ticket,
Update Ticket, Pause now live behind the kebab on desktop, with feature
parity in the existing mobile overflow menu
- Messages column anchors to max-w-3xl mx-auto to match the composer
- Chat bubbles drop from rounded-2xl to rounded-xl for vocabulary alignment
Typeset:
- Unify text sizing from 14 distinct sizes (with sub-pixel oddities and
rem/px duplicates) to a 5-step scale: 10px / 11px / text-xs / 13px / text-sm
WhatWeKnow collapsible:
- Header is now a toggle; section body hides when collapsed
- Auto-collapses on first render when facts ≥ 5 so Questions / Diagnostic
Checks stay above the fold
- Engineer's choice persists in sessionStorage per session and beats the
auto-collapse heuristic on subsequent renders
- key=activeChatId on both render sites resets state cleanly across sessions
Polish:
- Split MessageCircleQuestion into Pencil (question Answer CTA, write
affordance) + HelpCircle (per-check Explain toggle, universal help icon) —
same icon for two different jobs was a discoverability bug
- Drop redundant text-xs from font-sans text-[0.625rem] / text-[0.6875rem]
double-class definitions; the more-specific size always wins
TaskLane keyboard flow:
- Enter submits and auto-advances to the next pending task; Shift+Enter
inserts a newline (consistent across question and action textareas — paste
events don't fire keydown, so paste-then-Enter still works as expected)
- Esc cancels (same as the Cancel button)
- After the last pending task is submitted, focus moves to the Send Responses
button so the engineer can fire the whole batch with one more keystroke
- Subtle hint row under each open input teaches the shortcut
Type-check, lint, and build all clean.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Page-level Resolve patches applied_pending → applied_success before
opening the resolution flow, so resolved sessions don't carry a
provisional pending fix.
- Page-level Escalate intercept now catches applied_pending in addition
to verifying/partial; intercept copy generalized from "Verifying state"
to "still needs an outcome."
- PendingBanner gains a Dismiss action, matching the PR body and the
backend's allowed pending → dismissed transition.
- resolution_note_generator and escalation_package_generator system
prompts no longer include real-looking pending examples (anti-parrot
guardrail compliance).
Verified via Docker: prompt anti-parrot 2/2, suggested-fix outcome suite
21/21, frontend tsc -b clean, npm run build clean.
Co-Authored-By: Codex <noreply@openai.com>
Engineer applies a fix but can't verify yet (waiting on client power-cycle,
AD replication, async sync). Today the verifying banner forces a synchronous
verdict (worked / didn't / partial) — anything else means leaving the banner
stale or guessing wrong. This adds a fourth outcome that parks the fix in a
non-terminal "Awaiting verification" state with a reason ("waiting on what?")
and exposes it on the chat-anchored banner so the engineer doesn't lose track.
Backend
- New non-terminal status `applied_pending` parallel to `applied_partial`.
- New `pending_reason` column (nullable Text) — the "what are you waiting on?"
prose, mirrors `partial_notes`. Required when outcome=applied_pending.
- Outcome endpoint allows pending in/out transitions; pending stamps
applied_at but NOT verified_at (it's parked, not verified).
- Resolution-note + escalation-package prompts handle the new status:
resolution note frames the fix as provisional; escalation package surfaces
pending verification as the leading hypothesis with reference to what's
being waited on.
- Migration: add column + extend status CHECK constraint.
Frontend
- New `BannerMode = 'pending'` + `PendingBanner` component (info-tone,
parallel to PartialBanner) with worked / didn't / update-reason actions.
- VerifyingBanner overflow menu adds "Waiting to verify…".
- Nudge banner's "Still checking" button now actually records pending with
a reason, instead of just silencing for the session.
- AssistantChatPage banner-mode derivation maps applied_pending → 'pending'.
Tests: 4 new integration tests covering pending notes requirement, reason
storage + applied_at/verified_at semantics, pending→success transition,
and pending_reason update on re-PATCH.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Codex review pass on the escalation wedge. Reworks claim_session from
read-then-write to a conditional UPDATE so two seniors racing can't both
win, blocks the original engineer from claiming their own handoff, and
filters self-escalated sessions out of the dashboard escalation queue.
Also preassigns the handoff UUID before flush so the compatibility
escalation_package payload carries it. Removes legacy frontend pickup
state (claiming, handleStartHere) that broke tsc --noEmit.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Bundles four fixes from the live debugging session:
1. AssistantChatPage: replace urlSessionId === activeChatId gate with a
loadedChatIdsRef. After 8914391 made activeChatId initialize from
urlSessionId, the gate short-circuited fresh mounts and selectChat
never fired. Symptom: senior picks up an escalation, lands on a blank
chat surface with no conversation history and no sidebar entry. Fix
also adds loadChats() in handleStartHere so the picked-up session
appears in the sidebar (its escalated_to_id is null pre-claim, so
listSessions doesn't return it until claim_session sets it).
2. config: bump ESCALATION_AI_ASSESSMENT_TIMEOUT_SECONDS 15s → 45s.
Sonnet was hitting tail latency at 15s in the field, leaving the
magic-moment placeholder permanent. Background-task architecture
(e8ba74e) means this no longer blocks the user; it's just the budget
before publishing has_assessment=false. NOTE: live test still shows
assessment not populating — see HANDOFF for the consolidation plan
that supersedes this.
3. Enter-to-submit: chat-input convention (Enter submits, Shift+Enter
inserts newline) on the escalate-flow forms. RichTextInput gains an
optional onSubmit prop; EscalateModal wires it to handleSubmit;
ConcludeSessionModal gets the same handler on its plain textarea.
4. PendingEscalations: each row is now expandable. Click row body to
reveal the engineer's escalation reason, step count on record,
confidence tier, and PSA ticket number. Pick Up still clicks through
directly. Single-expand-at-a-time keeps the dashboard compact.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
The previous fix (8914391) only blocked the mount-time sessionStorage
restore when the page entered with prefill or ?pickup=true. It didn't
cover any path where the page was already mounted and activeChatId
flipped without the in-memory task-lane state going through reset+
repopulate cleanly — in-place URL navigation, mid-flight pickup,
HMR re-runs, the gap between setActiveChatId(B) and the AI response
that finally populates B's questions/actions.
Root cause: activeQuestions / activeActions / showTaskLane were never
intrinsically tied to a chatId. They were treated as "the active chat's
data" by convention, with no structural enforcement. Any window where
they survived past their owning chat leaked previous-session data into
the new view. The persistence effect made it worse: it stamped the
sessionStorage chatId field with activeChatId at write time, so a
mid-transition snapshot {chatId: B, questions: [A's]} would happily
restore A's data for B on the next mount.
Fix: introduce taskLaneOwnerChatId state that records the chatId those
in-memory questions/actions/show values BELONG to. Set at every site
that populates them (sendPrefill, selectChat, handleSend, handleTaskSubmit,
handleResumeNew, refreshFacts, handleApplyFix). Cleared in
resetSessionDerivedState. The persistence effect now writes ownerChatId
as the chatId tag, not activeChatId — so the snapshot is always
self-consistent.
Render gate: taskLaneIsForActiveChat = ownerChatId === activeChatId.
ANDed into all three render conditions (toolbar Tasks button, narrow-
viewport floating drawer, main side panel). The lane is structurally
unable to display data tagged with a different chat.
The mount-time skipTaskLaneRestore guard stays — it kills the flash
between component mount and the first sendPrefill effect run, which
the owner-gate alone doesn't cover.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Four items from the design-plan audit, all flagged as locked-design or
Codex corrections, shipped together so the GTM demo path covers them
end-to-end before bug bash.
1. Live AI assessment refresh on the magic-moment screen. Backend already
publishes handoff_assessment_ready when enrich_escalation_async commits;
wire the frontend listener so the senior sees the assessment populate
without a manual reopen. New event type + onAssessmentReady handler on
streamEscalations; AssistantChatPage opens a scoped SSE subscription
whenever it tracks a handoff missing its assessment, refetches on match,
and replaces magicHandoff / overlayHandoff in place. Closes the loop on
the async-assessment commit e8ba74e.
2. Suggested-step chips below the chat input. Locked design from the plan
(Codex correction). Chip strip renders above the composer post-claim
when ai_assessment_data.suggested_steps[] is non-empty. Click prefills
the input and focuses; first send or explicit X hides for the session.
3. Unread 6px dot on EscalationQueue cards. localStorage-persisted seen
set (rf-escalation-seen, capped 200). Dot top-right when not seen.
Cleared on open (card click) or claim (Pick Up) — NOT on hover, per
Codex correction. Pick Up stops propagation so it doesn't double-fire.
4. Race-condition toast on claim conflict. The /claim endpoint previously
silently overwrote claimed_by — both seniors thought they owned the
session. New HandoffAlreadyClaimedError carries the winner's id/name/
timestamp; claim_session rejects different-user re-claims (same-user is
idempotent for double-click safety); endpoint returns 409 with
structured detail. AssistantChatPage.handleStartHere extracts and
surfaces "Already claimed by {name} {time_ago}." via toast, drops
?pickup=true, dismisses magic-moment so the loser flows back to queue.
Tests: 2 new unit tests in test_handoff_manager.py (conflict raises,
same-user idempotent). Full handoff + escalation suite (34 tests) green.
Frontend tsc -b clean.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Two compounding bugs caused the previous session's questions/actions
to render briefly when entering a new chat — visible as "the new
session instantly pops with old session task-lane data" the user
reported.
The race
- AssistantChatPage's activeQuestions / activeActions / showTaskLane
useState initializers synchronously read sessionStorage's
rf-tasklane-meta. They restore the persisted task-lane state if its
saved chatId matches the freshly-resolved activeChatId.
- On dashboard prefill flow, the page mounts on /pilot with
location.state.prefill set; activeChatId initializes from
sessionStorage's rf-active-chat-id (the previous session). The
previous session's task-lane meta matches that chatId — so the
initializer restores it. First paint shows old questions/actions.
sendPrefill's resetSessionDerivedState fires later from a useEffect,
but only after the flash.
- Same pattern hits the senior-pickup flow: ?pickup=true means we're
about to render the magic-moment screen and discard whatever chat
the senior was previously on, but the underlying chat surface still
initializes with their old task-lane meta.
The amplifier
- resetSessionDerivedState wiped the in-memory state but never
removed sessionStorage's rf-tasklane-meta. Any remount or reload
before the next persistence-effect write could re-hydrate the
cleared state from the still-stale sessionStorage entry.
Fixes
- Initializer guard: when location.state.prefill is set OR
?pickup=true is in the URL, skip the sessionStorage restore
entirely. Kills the first-paint flash for both entry paths.
- Eager wipe: resetSessionDerivedState now also calls
sessionStorage.removeItem('rf-tasklane-meta'). The persistence
effect re-saves on the next state change anyway, so the only
window where sessionStorage is empty is the exact window where
stale-tag leakage was happening.
tsc -b clean. No backend changes.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Three improvements driven by live wedge testing.
1) Notification title now includes a problem snippet and PSA ticket
suffix when present:
"Escalation from Jane · #12345: Outlook is failing to sync email…"
Replaces the prior "Session escalated by Jane" copy that made every
escalation from the same junior look identical in the bell panel.
Snippet is trimmed to 70 chars with ellipsis. handoff_manager now
passes psa_ticket_id through in the notify() payload so this works
for both /escalate and /handoff entry points.
2) AI enrichment (assessment + enhanced escalation_package) moved to
a FastAPI BackgroundTask. The escalating engineer no longer waits
on 15-25s of Sonnet latency — handoff creation returns as soon as
snapshot, status flip, dual-write, documentation, PSA push, and
notify() are committed. enrich_escalation_async opens its own DB
session, runs both AI calls, updates handoff.ai_assessment +
session.escalation_package, commits, and publishes a new
`handoff_assessment_ready` event on the escalation bus. Frontend
doesn't yet listen for that event — the magic-moment screen still
shows a placeholder ("AI assessment is still generating. Reopen
this view in a few seconds…") which is honest about the state.
Live polling / auto-refresh on the bus event is the natural next
step.
3) ChatSidebar entries now surface the problem summary as a secondary
line and tag PSA-linked sessions with a monospace #ticket badge plus
an "Escalated" pill on in-transit sessions. ChatListItem grew
problem_summary, psa_ticket_id, and status fields; loadChats
populates them from listSessions. The user couldn't tell their own
sessions apart in the sidebar because they all rendered as "New
Chat" with no distinguishing detail — this fixes that for any
session, escalated or not.
Test plan
- Backend full suite: 1103 passed in 255.85s with -n auto.
- Frontend tsc -b clean.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
The /pilot/:id route renders AssistantChatPage, not FlowPilotSessionPage
(the latter is dead code with no active route). The earlier magic-moment
integration sat in the wrong file, so clicking Pick Up from the
dashboard navigated to /pilot/:id?pickup=true and AssistantChatPage
just loaded the chat surface with no claim — the senior never saw the
magic-moment screen and the handoff stayed unclaimed (status escalated,
permanently in the queue).
Adds full pickup awareness to AssistantChatPage:
- ?pickup=true on entry triggers a handoff fetch via
handoffsApi.listHandoffs (account-scoped, no claim required).
magicState transitions loading → visible (handoff found) or
loading → dismissed (no handoff or fetch failed). The dismiss path
also strips ?pickup=true from the URL so a refresh doesn't re-enter
loading state.
- The existing selectChat-from-URL effect is gated on magicState — it
skips while we're loading or showing the magic-moment so the chat
surface doesn't race the claim flow. After claim it re-fires and
populates messages from conversation_messages because the senior is
now escalated_to_id and GET succeeds.
- Magic-moment renders as full-page take-over (sidebar hidden) until
Start here. handleStartHere calls handoffsApi.claimHandoff, drops
?pickup=true, and dismisses — the regular chat then loads.
- Toolbar Context button (visible when magicHandoff is in memory)
re-opens the screen as a dismissible overlay. Lazy-fetches the
handoff when needed.
Verified tsc -b clean and Vite HMR picked the file up without errors.
The wire-level integration was already verified in earlier commits:
listHandoffs returns the unclaimed handoff for a senior pre-claim,
claimHandoff flips status escalated → active and sets escalated_to_id.
Note: the prior FlowPilotSessionPage magic-moment integration is now
in dead code (file is unreferenced from router). Left in place for
this commit; will come out in a follow-up cleanup once we're confident
the AssistantChatPage path is solid in production.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
The dashboard prefill flow in AssistantChatPage set activeChatId after
creating a new session but never updated currentChatRef.current. Every
later handleSend / handleTaskSubmit then tripped the
`currentChatRef.current !== sentForChatId` guard that was supposed to
discard responses for stale chats — and silently dropped the AI's
follow-up. The user saw their submitted message but no assistant
reply, no toast, no task-lane update.
Mirrors what handleNewChat and handleResumeNew already do. Adds an
e2e regression test that drives the dashboard prefill, submits a
partial task-lane response, and asserts the second AI turn renders.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Brings in PR #141 (PSA ticket management) so FlowPilot can ship on top
of a unified main. Two manual conflict resolutions:
1. CLAUDE.md — kept the FlowPilot ai-handoff rewrite (`.ai/`-driven
protocol). The pre-rewrite reference content (CW integration notes,
lessons archive, env vars table) lives in `docs/connectwise/`,
`docs/LESSONS-ARCHIVE.md`, and DEV-ENV.md by design.
2. frontend/src/pages/AssistantChatPage.tsx — both conflict regions
were purely additive. Concatenated FlowPilot's Phase 2-9 state hooks
(facts, activeFix, preview*, scriptPanelOpen, templatizeQueue) with
PSA's spin-off ticket state (linkedTicket, showNewTicket, spinOffHint).
Both modal mounts (TemplatizePrompt, ShortcutsHelpOverlay,
NewTicketModal) kept. All setters wired by either branch are intact.
Verification:
- `tsc -b` clean across the merged tree.
- Browser smoke-test (Session B fixture): Phase 9 ProposalBanner
("Run AI-drafted PowerShell to recover SSL VPN") renders alongside
PSA's new Tickets sidebar icon. Console clean.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
1. EscalateInterceptDialog clipped off-screen.
The dialog was positioned with `absolute bottom-full mb-2 left-0`
under the assumption the Escalate button would have room above it.
In practice the button lives in the chat-page action bar near
y≈105, so the 302 px dialog overflows the top of the viewport
and only the last option is visible.
Switch to `top-full mt-2 right-0` — anchors the dialog below the
button and aligns its right edge with the button (avoids overflow
off the right when the button is in the right-side action cluster).
2. TemplateMatchPanel never renders on a fresh session.
`handleApplyFix` for the script_template_id branch only sets
`scriptPanelOpen=true`, but TemplateMatchPanel is mounted inside
`TaskLane.bottomSlot`. On sessions with no questions/facts the
lane defaults closed, so the panel exists in the React tree but
inside an unrendered TaskLane — the user clicks Apply fix and
nothing visibly changes.
Fix: also `setShowTaskLane(true)` in that branch so the lane
opens alongside the panel. The ai_drafted_script branch is fine
(InlineNoTemplateDialog renders in the chat region, not in the
lane), so it's left alone.
Both bugs were latent — they only surface on sessions that haven't
accumulated TaskLane state yet (questions/facts). Fresh sessions
created from the StartSessionInput hide them because the AI's first
turn populates questions and the lane auto-opens. Caught using the
new seed_phase9_qa_fixtures.py harness.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Addresses docs/FlowAssist_Migration/Issues/phase-9-review-issues.md.
Issue #1 (High): "Applied partially" from the escalation intercept silently
dropped because the backend requires notes on applied_partial and the dialog
sent none. The catch was silent and the UI advanced into the conclude flow
as if the outcome were recorded.
- EscalateInterceptDialog now has a two-step flow: clicking the partial
choice reveals a notes textarea (autofocused, required non-empty) plus
Back / "Record partial & escalate" buttons.
- onChoose signature extended to (choice, notes?).
- handleInterceptChoice passes notes to patchOutcome; on failure it
surfaces a toast and does NOT advance to the conclude modal, so the
intercept stays open for retry.
Issue #2 (Medium/High): ScriptBuilderTab kept local state across active-fix
changes within the same pilot session, so a stale draft could PATCH against
a newer fix.id. Added key={activeFix.id} on the mount — forces a clean
remount per fix; backend get-or-create (keyed on user+ai_session_id) still
returns the same session row, which is the intended resume-on-refresh
semantic; but messages/editorBuffer/latestScript local state resets.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Per Phase 9 §5. Before: banner Apply click stamped applied_at
regardless of whether the engineer had committed to running anything,
starting the Verifying timer prematurely. After:
- handleApplyFix no longer calls applyFix(). It just routes to the
right surface (TemplateMatchPanel / InlineNoTemplateDialog / Script
Builder tab).
- handleScriptDecision stamps applied_at for one_off + draft_template
(both labels are 'Run now, …' — the click is the declaration).
build_template does not stamp.
- TemplateMatchPanel's new 'I ran this' button calls applyFix via a
new onMarkRun prop.
- Script Builder tab Submit does not stamp (a draft is not a run).
No backend change — the /apply endpoint is unchanged. Only call sites
move.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Wires the three new components into AssistantChatPage:
- ChatTabStrip renders when the active fix needs a script drafted.
- ScriptBuilderTab sits alongside chat via display:none toggling so
chat scroll position + builder state both persist.
- InlineNoTemplateDialog replaces the task-lane bottomSlot render for
the drafted-script evaluation case; three cards finally fit.
- Banner Apply routing updated: no-draft/no-template → Script Builder
tab; drafted → InlineNoTemplateDialog; template → unchanged path.
applyFix() call site moves land in the next task.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Issue #3 from phase-8-review-issues.md. 'Not yet' on the AI-confirming
banner was a local-state hide; the proposal re-surfaced on the next
refreshSessionDerived call.
Two-part fix:
- PATCH /outcome now clears ai_outcome_proposal on any terminal action
(engineer has taken a decision; stale AI proposal is moot).
- New DELETE /ai-sessions/:sid/suggested-fixes/:fid/ai-outcome-proposal
endpoint for explicit 'Not yet' rejection. Does not touch status
or state_version — pure UI state.
Frontend handleRejectAIProposal now calls the DELETE and setActiveFix
with the server response.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Issue #2 from phase-8-review-issues.md. Apply was client-side-only via
a bannerApplied flag. Refresh / chat reselect / multi-tab would drop
Verifying state back to Proposed.
- New POST /ai-sessions/{sid}/suggested-fixes/{fid}/apply stamps
applied_at without changing status (still 'proposed'). Idempotent
if already stamped; 409 if fix is past proposed (a terminal outcome
was already recorded).
- Bumps state_version so resolve/escalate preview bundles reflect that
the fix has entered verifying.
- Frontend handleApplyFix calls the endpoint and uses the returned
applied_at directly. bannerApplied client flag is removed.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Superseded by ProposalBanner (Phase 8). The import was already removed
from AssistantChatPage in the previous commit; this deletes the orphaned
file itself and strips the now-unused suggestedFixSlot prop from
TaskLane's interface and both call sites.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Replaces the task-lane SuggestedFix card with the ProposalBanner docked
above the chat composer. Wires:
- Resolve-while-verifying auto-marks applied_success (one-click resolve).
- Escalate-while-verifying opens EscalateInterceptDialog to capture the
real outcome (default: didn't work) before handoff.
- 3+ post-apply engineer messages trigger the passive Nudge banner.
- AI [FIX_OUTCOME] proposals surface in the AIConfirming state; one-click
confirm applies the outcome.
Banner state resets on session switch via resetSessionDerivedState.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- WhatWeKnow shows a "synthesizing" indicator + skeleton pulse while the
chat cycle is in-flight; task-lane header mirrors the signal with a
"thinking" pip so engineers know the AI is still working.
- Quiet-state hint when the lane is open (facts exist) but no open
questions, checks, or active fix — keeps the surface from looking
"finished" when the AI is about to follow up.
- Keyboard shortcuts: ⌘↵/Ctrl+↵ send in the composer (plain Enter still
sends), ⌘G toggles the Script Generator panel for the active fix,
`?` opens a new ShortcutsHelpOverlay listing all bindings. ⌘K palette
was already wired in TopBar.
- Responsive: below 1200px the task lane collapses to a bottom drawer
with a backdrop + a floating "Tasks ●" toggle button. TaskLane now
takes a `variant: 'side' | 'drawer'` prop; drawer variant drops the
resize handle and uses the shared slide-in-bottom animation.
- Build hygiene: fixed a pre-existing TS error in confirm-post error
handling (duplicate `response` type keys) and an unused-import warning
in TemplatizePrompt.
Verified: `npx tsc -b` and `npm run build` both clean against the dev
stack; Vite HMR applied each change without errors.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Closes the loop on the Phase 5 "Run now, templatize after resolve" path.
After a session resolves, drafts queued by the three-option dialog surface
as a modal that lets the engineer review the AI-proposed parameterization
and either save as a reusable team template or skip. A "don't ask again"
toggle writes to account_settings.preferences so the next resolve won't
pop the modal.
Backend:
- /api/v1/draft-templates:
* GET — list account drafts (pending_only default true; pass false for
audit view including accepted/rejected)
* GET /{id} — single draft
* POST /{id}/accept — promotes to a new script_templates row with
source_session_id / source_user_id / source_ticket_ref populated
(drives the Script Library "generated from CW #X · resolved by Y"
provenance chip). Draft flips to status=accepted,
promoted_template_id set, resolved_at stamped. 409 on re-accept /
already-rejected. 400 on unknown category_id.
* POST /{id}/reject — flips to status=rejected. 409 on re-reject.
- /api/v1/accounts/me/preferences (GET/PATCH) — thin wrapper over
AccountSettings.get_setting/set_setting. PATCH merges keys into the
JSONB column, preserving existing keys the client didn't touch.
Used by the "Don't ask again for this team" checkbox
(templatize_prompt_enabled=false) and, forward-looking, by
cw_resolved_status_id / cw_escalated_status_id from Phase 4.
- 13 tests: list filter, accept with/without edited_body, provenance
copy-through, reject, 409 on re-accept / re-reject, 400 on unknown
category, prefs round-trip with merge semantics.
Frontend:
- src/components/pilot/script/TemplatizePrompt.tsx — modal showing the
drafted script with proposed parameters in the Phase 5
ParameterizationPreview, editable name/category/description, an
individual-parameter remove button, and the "don't ask again" opt-out.
Accept posts to /draft-templates/{id}/accept + optionally PATCHes
preferences. Skip posts /reject.
- src/api/draftTemplates.ts — typed client plus accountPreferencesApi.
- AssistantChatPage: after a successful Resolve (external OR local),
fetches preferences + pending drafts for the session and queues the
modal one draft at a time. Escalate does not trigger this flow.
- Sidebar: Scripts nav shows the pending-draft count as a badge. Fetched
independently of the main sidebar stats so endpoint flakes don't
break the rest of the sidebar.
Verified live 2026-04-22: seed two drafts → GET sees both pending →
accept draft A (template created, provenance CW #99123 populated) →
reject draft B → pending count drops → PATCH opt-out → GET confirms
persistence.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Symptom: sidebar showed "User mjones got locked out … 0 messages" but the
conversation pane was rendering 2 messages from a different chat. The
task lane content matched what was displayed (so the AI was fine post-
prompt-sweep) — the leak was purely UI: messages from the previous chat
stayed on screen until the new chat's getSession returned.
selectChat resetSessionDerivedState() then awaits getSession before
calling setMessages(detail.conversation_messages). Between the reset
and that await, the prior chat's messages remain visible. handleNewChat
already had an explicit setMessages([]) call so it was unaffected;
selectChat did not.
Folded setMessages([]) into resetSessionDerivedState so any new chat-
switch entry point gets the wipe for free.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Two fixes from the Phase 5 shakedown:
1. Stale lane data leaking across chats. handleNewChat, sendPrefill, and
handleResumeNew were each missed when Phase 3/5 added activeFix,
previewKind, previewData, and scriptPanelOpen — only selectChat reset
the full set. Result: starting a new chat while a Suggested Fix card
was active showed the previous session's fix card (and any open
preview/script panel) until the next backend refresh swept it.
Consolidated all four entry points behind a single
resetSessionDerivedState() helper so adding new lane state in future
phases only requires touching one place.
2. CommandPalette TDZ on cold load. SCRIPTS_INLINE_QUICK_ACTION (line 66)
referenced PILOT_INLINE_SCRIPT_PATH declared at line 94 — module-level
evaluation hit the use before the declaration. Browser blanked with
"Cannot access 'PILOT_INLINE_SCRIPT_PATH' before initialization".
Moved the path const above its first use; also extracted
PILOT_INLINE_SCRIPT_EVENT into a tiny @/lib/pilotEvents module so
AssistantChatPage doesn't import the palette component just to read a
string — that mixed-export pattern broke Fast Refresh ("consistent
components exports") and added an unnecessary import edge.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Wires the SuggestedFix card to an inline panel that handles both cases:
template-matched fixes open the Script Library generator with parameters
pre-filled from session context; un-matched fixes open the three-option
dialog (one_off / draft_template / build_template). The decision endpoint
records the path choice with side effects: draft_template persists a
draft_templates row via a Sonnet-driven TemplateExtractionService;
build_template returns a redirect to the Script Builder; one_off just
records the choice.
Backend:
- TemplateExtractionService: drafts a parameter schema from a concrete
rendered script. Conservative by default ("prefer fewer parameters").
Round-trip-validates that templated_body only references declared
parameters; missing-key mismatch falls back to the original script
with no params. LLM/parse failures fall back identically — the
engineer can still create a draft and refine in the post-resolve
prompt (Phase 6).
- /suggested-fixes/{fix_id}/decision side effects:
* one_off → returns rendered_script (engineer's edited version or the
fix's ai_drafted_script verbatim)
* draft_template → same + creates draft_templates row with extracted
params, returns draft_template_id
* build_template → returns redirect_path=/scripts/builder?from_session=
&fix= so the frontend can navigate to the builder pre-loaded
- 400 when a non-template fix has no ai_drafted_script (template-matched
fixes take the dedicated /scripts/generate path, not this endpoint).
- 12 tests: TemplateExtractionService parse + fallback paths, all four
decision branches, edited_script override, missing-script 400.
Frontend:
- src/components/pilot/script/{TemplateMatchPanel, NoTemplateDialog,
ParameterizationPreview}.tsx — inline panels rendered in the task
lane's bottom slot when the engineer clicks a SuggestedFix card.
- TemplateMatchPanel: loads template via /scripts/templates/{id},
pre-fills params from fix.ai_drafted_parameters with cyan "from
session" tags, generates via existing /scripts/generate (already
bumps state_version on ai_session_id from Phase 3). 404 falls back
with a clear message instead of erroring.
- NoTemplateDialog: shows the AI-drafted script with proposed parameter
values highlighted in amber via ParameterizationPreview; three option
cards with the middle (draft_template) flagged Recommended; inline
edit on the script body before deciding.
- SuggestedFix card now clickable: onActivate toggles the inline panel.
- AssistantChatPage: scriptPanelOpen state + handleScriptDecision that
navigates on build_template and toasts on the other paths. Active fix
changes auto-close the panel so engineers don't act on stale state.
- Cmd+K → "Open inline Script Generator" palette entry surfaces only on
/pilot/:id routes; fires a window event the chat page subscribes to.
No Resolve shortcut added per Section 14 decision (browser ⌘R conflict).
Verified 2026-04-22 against the dev stack:
- one_off / draft_template / build_template all return the right shape
with real Sonnet TemplateExtractionService for the draft path.
- Conservative extraction confirmed: cmdkey + Restart-Process script
yielded zero proposed parameters as intended.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Wires the preview popover's Confirm & post action to ConnectWise (and,
via the provider pattern, any future PSA). Adds the parallel Escalate
flow with the handoff-oriented five-section markdown. Sessions without a
linked PSA ticket resolve/escalate locally — markdown stored, status
flipped, nothing posted externally.
Backend:
- EscalationPackageGeneratorService: Sonnet, five sections (Problem /
What we've confirmed / What we've tried / Current hypothesis /
Suggested next steps). Shares the preview_cache with a separate KIND
so Resolve and Escalate previews for the same state coexist.
- PSAWritebackService: post_resolution_note (RESOLUTION note type,
customer-visible), post_escalation_package (INTERNAL_ANALYSIS,
handoff for the next engineer only), transition_ticket_status with
mandatory re-fetch verification. PSAStatusVerificationError surfaces
loudly when CW silently rejects a status change — the
ConnectWise anti-pattern CLAUDE.md flags.
- Endpoints:
* POST /ai-sessions/{id}/escalation-package/preview
* POST /ai-sessions/{id}/resolution-note/post
* POST /ai-sessions/{id}/escalation-package/post
Outcomes: "resolved" / "escalated" with external_id + verified status,
"resolved_local" / "escalated_local" when no PSA linked.
- Target CW status IDs live in account_settings.preferences
(cw_resolved_status_id, cw_escalated_status_id). When unset, the post
proceeds without a status transition — response includes a
status_transition_skipped_reason rather than silently erroring.
- 7 tests: local-only path, PSA happy path with verified transition,
status verification failure → 502, skipped transition when
unconfigured, 409 on already-resolved re-post, escalate parallel path,
internal-analysis note type enforced.
Frontend:
- ResolutionNotePreview now kind-parameterized ('resolve' | 'escalate')
with inline edit + Confirm & post. Preview loads from the matching
backend endpoint; posting calls the matching endpoint; outcome toast
surfaces the verified CW status or the local-only result.
- AssistantChatPage: previewKind state replaces previewOpen; two toggle
buttons (Preview Resolve note / Escalate instead) in the lane's bottom
slot. handleConfirmPost dispatches by kind.
Verified 2026-04-22:
- Local-only Resolve + Escalate round-trip against the dev stack.
- Live Sonnet escalation-package preview; cache hit on repeat call
with no state change (separate cache kind from resolution-note).
- PSA post + status-verification paths covered by mocked-provider pytest
cases. Live CW round-trip pending a test CW instance.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
refreshSessionDerived's dep array referenced refreshActiveFix and
schedulePreviewRefresh before they were declared. React evaluates
useCallback deps synchronously during render, so the page blew up with
"Cannot access 'refreshActiveFix' before initialization" before a single
render completed. Moved the three leaf helpers above the aggregator.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds the AI-proposed resolution path and the inline preview of the
markdown that will be posted to the customer ticket on Resolve. The
preview is keyed on (session_id, ai_sessions.state_version) so back-to-
back fetches against unchanged state hit an in-process cache instead
of paying for a Sonnet call.
Backend:
- preview_cache: in-process LRU keyed on (kind, session_id, state_version).
No TTL — state_version is the source of truth. Soft-cap 5000 entries.
- unified_chat_service: [SUGGEST_FIX] parser (last-block-wins, JSON
payload, confidence clamped 0-100), supersession persistence (sets
superseded_at on prior active row), atomic state_version bump.
- ResolutionNoteGeneratorService: pulls session, facts, active fix, and
redacted script_generations into a structured input bundle for Sonnet;
produces the four-section markdown (Problem / What we confirmed /
Root cause / Resolution). Sensitive script parameters redacted via
ScriptTemplateEngine.redact_sensitive driven by the template's
parameters_schema.
- /api/v1/ai-sessions/{id}/suggested-fixes/active — 200 with the active
fix or 404.
- /api/v1/ai-sessions/{id}/suggested-fixes/{fix_id}/decision — records
one_off / draft_template / build_template / dismissed; dismiss
supersedes; bumps state_version. 409 on dismissing an already-
superseded fix.
- /api/v1/ai-sessions/{id}/resolution-note/preview — generates or returns
cached markdown; from_cache flag in payload signals cache hit.
- scripts.py POST /generate now bumps state_version on the linked
ai_session_id when present (third source of preview-cache invalidation
per Section 5.5).
- ASSISTANT_SYSTEM_PROMPT documents [SUGGEST_FIX] (when to/not to emit,
format, supersession semantics).
- 12 tests covering the parser (well-formed, last-wins, malformed,
confidence clamping), supersession + state_version invariant, all
decision branches, preview cache hit-on-no-change + miss-after-write.
Frontend:
- src/components/pilot/sections/SuggestedFix.tsx — amber-accented card
with confidence badge; dismiss action wired to the decision endpoint.
- src/components/pilot/ResolutionNotePreview.tsx — popover with refresh,
loading state, cached/fresh indicator, ticket-ref display.
- src/api/sessionSuggestedFixes.ts — typed client; getActive normalizes
404 to null so callers don't have to special-case.
- TaskLane gains suggestedFixSlot + bottomSlot props (rendered after
Diagnostic Checks; bottomSlot anchors the Resolve action).
- AssistantChatPage: refreshSessionDerived helper batches fact + fix
refresh; fact mutations and chat sends both schedule a 500ms-debounced
preview refresh per the Section 5.5 spec.
Verified end-to-end against the dev stack with a real Sonnet call:
- /active 404 → fact create → preview generates four-section markdown
grounded only in provided facts → second preview call hits cache
(from_cache=true, no LLM call) → fact write 2 → cache miss, regenerates.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds the load-bearing structural feature of the FlowPilot migration: a
"What we know" panel that holds confirmed facts for a session, fed by AI
[PROMOTE] markers and engineer-added notes. Facts feed the resolution
note preview (Phase 3) and survive across turns via stable UUIDs assigned
to pending_task_lane items.
Backend:
- FactSynthesisService: create/update/soft-delete facts with atomic
state_version bumps; LLM-backed synthesize_from_question/check on the
fact_synthesis (Haiku) action tier per Section 6.6.
- /api/v1/ai-sessions/{id}/facts CRUD + /facts/promote (proposed_text or
via synthesis). PATCH returns 403 for question/diagnostic_check facts
(edit the source item instead, Section 7.3).
- unified_chat_service: [PROMOTE] marker parser (JSON-block per Section
8.1 spec drift note), stable-UUID assignment for pending_task_lane
questions/actions preserved by exact text/label match across turns.
- ASSISTANT_SYSTEM_PROMPT: documents [PROMOTE] format, when to/not to
emit, hallucination guardrails, source_ref handling.
- 17 tests covering parser, stable IDs, service validation, CRUD,
editability rule, both promote modes, 422 null-synthesis path,
state_version invariant.
Frontend:
- src/components/pilot/sections/{WhatWeKnow,WhatWeKnowItem,AddNoteButton}
— green-gradient section above Questions, dashed-circle check, inline
edit/delete gated by the server's editable flag.
- TaskLane gains a whatWeKnowSlot prop (existing assistant/ folder kept
per the doc's "rename is opportunistic" guidance).
- AssistantChatPage fetches facts on selectChat and refetches after each
chat send (so [PROMOTE]-synthesized facts appear immediately); auto-
opens the lane when facts exist.
Verification: end-to-end smoke against the local docker stack confirms
all five endpoints (list/create/patch/delete/promote) plus the 403
editability rule. pytest suite verifies the same with mocked LLM. Live
[PROMOTE] flow remains untested until used in the UI — the marker shape
is covered by parser tests.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Three fixes from beta tester session feedback:
1. MCP error handling (backend/app/services/assistant_chat_service.py)
- The MCP Microsoft Learn integration was catching only BadRequestError.
Any other error type (APIStatusError, APIConnectionError, timeout) from
the external MCP server propagated as a 502, causing the generic error.
- Now catches all Exception types when MCP is active and retries without
MCP using the stable client.messages.create endpoint.
2. Frontend error UX (frontend/src/pages/AssistantChatPage.tsx)
- catch {} was silently swallowing all errors and inserting a generic
assistant message. Now: differentiates 429 (rate limit) vs 502/503
(AI unavailable), removes the optimistic user message on failure,
restores the failed message to the input so users can retry without
retyping, and logs errors to console for debugging.
3. Image attachments visible in chat (frontend/src/components/assistant/ChatMessage.tsx)
- Uploaded images were sent to the AI correctly but never shown in the
chat thread. Now captures preview URLs before clearing pendingUploads
and renders thumbnails above the user bubble, clickable to full size.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add persistent session header with title, status badge, Resolve,
Escalate, and Update Ticket/Share Update buttons — mirrors
FlowPilotSessionPage pattern exactly
- Update Ticket label when psa_ticket_id present, Share Update otherwise
- Full mobile support via ⋯ overflow menu (Resolve, Escalate, Update, Pause)
- Strip _(not yet completed)_ markers from stored conversation_messages
in unified_chat_service to prevent stale task lane items from prior
turns leaking into new sessions via the AI's re-include instruction
- Add currentChatRef guard to handleResumeNew (was missing unlike handleSend)
- Remove Update/Conclude from chatbar — toolbar is now input utilities only
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- .gitignore: keep both graphify-out/ entries and main's .gitnexus entry
- ScriptCodeBlock/ScriptPreviewModal: take main's border-border and text-accent-text
for filename labels; use neutral ghost style for Save button in ScriptCodeBlock;
use bg-accent (normalized from bg-primary) for Save button in ScriptPreviewModal
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The previous fix (990f044) moved state clears before the createChatSession
await but left currentChatRef.current pointing at the old session during the
entire network call. Any in-flight handleSend/handleTaskSubmit for the old
session would pass the guard (oldId === oldId) and re-apply stale task lane
data to the new empty session.
Setting currentChatRef.current = null before the await ensures in-flight
handlers from the previous session see a mismatch and bail — matching the
same pattern already used correctly in selectChat.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Three race conditions in AssistantChatPage:
1. handleNewChat cleared showTaskLane/activeQuestions/activeActions
AFTER the createChatSession await — old lane was visible during
the network call. Moved clears before the await.
2. handleResumeNew never cleared old TaskLane state at all. Added
upfront clears before the first await.
3. handleSend and handleTaskSubmit had no stale-session guard. If
the user switched chats while sendChatMessage was in flight, the
response would set showTaskLane on the wrong session. Added
sentForChatId snapshot + currentChatRef guard (same pattern
already used in selectChat).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Import and call clearTaskState before updating questions/actions in
handleSend and handleTaskSubmit so new AI tasks always replace stale
sessionStorage cache instead of being overridden by it
- Include pending (not yet completed) tasks in the AI message on partial
submit so the AI knows which tasks were left unanswered
- Fix stale closure in TaskLane saveTaskLane useEffect — use refs for
questions/actions so the debounced backend save always uses current values
- Add responses field to pending_task_lane TypeScript type, removing the
unsafe double-cast in selectChat
- Instruct the AI to re-surface incomplete tasks unless ≥75% confident
the information is no longer needed
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Race condition: on page remount, selectChat(oldId) loads session data async.
If the user clicks New Chat before the API returns, the old session's
pending_task_lane was being applied to the new session's state, showing
stale tasks and blocking new ones from appearing.
Fix: currentChatRef tracks the most recently requested chat ID synchronously.
All chat-creation paths (selectChat, handleNewChat, handleResumeNew) update it
immediately. After each await in selectChat, bail if the ref no longer matches.
Also documents the pattern as Lesson 106 in CLAUDE.md for future reference.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
orange-400→blue-400, orange-500→blue-500, orange-600→blue-600
across ~21 component files.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Mechanical find-and-replace: rgba(249,115,22,...) → rgba(96,165,250,...)
across ~40 component and page files.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Two issues fixed:
1. TaskLane useEffect on [questions, actions] was resetting all tasks
to pending with empty values, wiping restored user answers. Now
checks sessionStorage for saved state before resetting.
2. selectChat was setting activeQuestions/activeActions before writing
responses to sessionStorage, causing a race where TaskLane mounted
with new props but empty sessionStorage. Now writes responses to
sessionStorage first so TaskLane can restore them on prop change.
The backend saveTaskLane debounce (2s) persists responses to the DB,
and selectChat restores them via pending_task_lane.responses. This
chain now survives browser close.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The sendPrefill flow (dashboard handoff) did not clear activeQuestions/
activeActions before creating the new session. The task lane initializer
loaded stale data from sessionStorage keyed to the previous session ID,
showing old tasks while the new session was processing.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Wire StatusUpdateModal into AssistantChatPage with "Update" button in
the chat toolbar. Enhance ConcludeSessionModal pause/escalate outcomes
to offer ticket notes, client update, or email draft generation instead
of static messages.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
ConcludeSessionModal now resolves instantly (Phase 1) then streams
ticket notes via SSE (Phase 2), with skeleton loading and fallback.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
