- Runbook: pre-migration settings don't persist (not "saves fail"),
eligible statuses, 15 lines per quote, audit attribution, clone/template
behaviour, supplier kept, doubts dot, confidence guidance (Medium is the
default; raise to High if reps often change AI prices).
- quotes.assistant_fill added to docs/api-mcp-layer.md,
docs/audit/api-mcp-coverage.md and the Giellie skill.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- decideWithAi throws on stop_reason max_tokens instead of returning a
partial answer; fillQuote marks a requested line the AI did not answer
as error (retried after 1 h), never a permanent no_match.
- QUOTE_MAX_LINES 30 -> 15; the tick also caps lines per quote so the
60-line budget reaches other quotes.
- runAssistantTick stops starting quotes after a 90 s time budget and
returns reason running while a newer start than the last summary is
under 10 minutes old (lease).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Quote assistant card in Settings, AI (on/off, interval, min confidence,
editable prompt with reset, last-run line); parseSettingsForm handles the
qa_* fields. docs/quote-assistant.md has the runbook and the n8n tick
workflow spec; AGENTS.md gets a short section.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Aligns the tool policy, the system prompt, the MCP route and the skill
doc so they describe the same boundary, with tests pinning the policy
and prompt text.
The docs and the executable policy had drifted apart — the skill doc
advertised capabilities the policy does not grant, which is worse than
not documenting them: an agent reading the doc will plan around a tool
it isn't allowed to call.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
actor.id must be a 15-char user id (stock_ledger.created_by is a relation to
users; a non-user id left the cost patched but unaudited). Each updates[i].id
is validated, actor.name defaults to the actor id, and the Giellie prompt now
says to pass both selling_price and markup on create and to read the item
before a partial price change. Adds tests for null / numeric-string prices
and the explicit markup:0 default-markup behaviour.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
- Added an audit trail feature that logs every create, update, and delete action on delivery notes and orders, capturing detailed changes per field.
- Introduced the `AuditTimeline` component to display the history of changes for delivery notes and orders, enhancing traceability.
- Updated the `page.tsx` files for delivery notes and orders to fetch and display audit logs, ensuring users can view the history of modifications.
- Enhanced the `package.json` with a new migration script for setting up the audit log functionality.
This feature improves accountability and transparency in the management of delivery notes and orders.
Splits the quote attachment model along the seam that actually matters:
'operator-only references' (drawings the operator consulted, supplier
emails they filed away) vs 'customer-facing files' (supplier quotes,
drawings, NDAs that need to ride along on the email).
Schema (PB): new `internal_attachments` + `outbound_attachments` fields
on the `quotes` collection, maxSelect 10 each. Existing `attachments`
field kept for back-compat but is no longer the source of truth for
outbound emails.
API:
- GET/POST/DELETE /api/v1/quotes/[id]/internal-attachments[/{filename}]
- GET/POST/DELETE /api/v1/quotes/[id]/outbound-attachments[/{filename}]
- POST /api/v1/quotes/[id]/attachments/upload kept for legacy `attachments`
MCP: `quotes.send_email` description now correctly states
`selectedAttachmentIds` are PB file tokens from `outbound_attachments`
(supplier quotes, drawings, NDAs), not IDs of the legacy `attachments`
collection.
Frontend: `ProcessOutboundAttachmentsCard` component lets the operator
upload/remove customer-facing files during the process page; approval +
process pages now read the new fields.
Outbound Send workflow (deployed as `PIEAkPYYYZLGl6Pj`):
- Old workflow (id `WF_Email_Send_SMTP`) and stale repo file
(`WFDASH — Quote Outbound Send.json`) replaced.
- New revision intersects `quotes.outbound_attachments` with
`email_outbound_attachment_ids`, downloads each from
`/api/files/quotes/<id>/<token>`, and emits
`options.attachments: [{name, content, type}]` consumed by
`Send Email (SMTP)` (PO Send pattern).
- Failure path flipped from `send_failed` to `mail_failed` so
`retryQuoteEmail` can find failed sends (it only accepts the
latter). Previously failed sends were stranded.
Email Monitor (v5) workflow fixes:
- Reply-branch auth: any authenticated request now passes through;
pre-fix bug rejected branches that the IMAP trigger hadn't seen yet.
- Reply detection: bulletproof subject regex
(/Q-?\d{4}-?\d{2}-?\d{3}/) accepts both legacy `Q-2026-09-246`
and current `Q202609246` formats; canonicalised digits-only for
PB `~` substring match.
Delivery notes: new pricing endpoint at
/api/v1/delivery-notes/items/[id]/pricing + service-layer methods.
Snapshots kept for forensics: PRE-FIX-REPLY-{BRANCH-AUTH,DETECTION}.json
and push-payload.baseline.json are the previously-deployed workflow
shapes, retained so we can diff/rollback if regression hits.
Verified:
- PUT workflow PIEAkPYYYZLGl6Pj -> 200, active, 25 nodes
- quotes-service.test.ts: 117 pass (4 pre-existing failures unchanged)
- mcp/route.test.ts: 118 pass (2 pre-existing failures unchanged)
- node --check on new Code node JS passes
Docs: docs/quotes-outbound-attachments-deploy.md covers the deploy
procedure; docs/api-mcp-layer.md description sync.
PocketBase treats `max: 0` on a text field as "use the default 5000-char cap", not unlimited. A Redpath reply with a 5029-char body 400'd on every 2-minute poll for hours on 2026-09-08, wedging every RFQ behind it because the failed email stayed UNSEEN.
Added clampEmailBody (with a truncation marker) and routed email_body writes through it so oversized replies still become quotes instead of blocking the queue. The untruncated body remains in the mailbox, and attachments carry the detail. Raise this cap in lockstep with any PB admin change to the field's max.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Groundwork for the rep visit check-in feature: a rep taps "I'm on site",
the vehicle's tracker position surfaces which customers are there, and
the visit is logged against them.
Pure/unit-testable layers only — no PocketBase writes and no UI yet,
both of which are blocked on schema that has to be added in the PB
admin first. Design doc: docs/superpowers/specs/2026-09-05-rep-visit-check-in-design.md
- lib/visit-matching.ts rankNearbyCustomers: radius match around a
point, rep's own customers first
- lib/visit-stops.ts detectStops: breadcrumb trail -> stops.
Anchor-based clustering rather than a running
centroid, which would let a slow crawl chain
into one bogus stationary stop
- lib/tracker-parsing.ts Netstar FleetAI response decoding
- lib/server/tracker-service.ts
FleetAiAdapter + FakeTrackerAdapter behind a
TrackerAdapter seam. The fake is auto-selected
when no credentials are configured, so the rest
of the feature builds and tests without vendor
access.
- lib/geo.ts isRealGeoPoint, lifting the Null-Island guard
that was inlined identically in customers/[id]
and companies/[id]
Three FleetAI conventions drive real code here and are each pinned by a
test: errors arrive as HTTP 200 with a failure envelope; "--" means
"unavailable" and is not null (and for IGN, not false); timestamps are
platform-local UTC+2 with no offset marker, so parsing them naively puts
every fresh fix two hours in the past.
FleetAI has no position-history endpoint, so the design polls
getTokenBaseLiveData (whole fleet in one call) and keeps its own trail.
scripts/fleetai-probe.mjs is a throwaway read-only probe to confirm the
three account-shaped assumptions before more is built on top.
102 tests pass. The 9 pre-existing failing test files elsewhere in the
suite were verified identical on a stashed tree and are unrelated.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Covers the reorderable block-list editor for sale/delivery/cash-up
slips, per-letterhead persistence, and the delivery-note pricing
default, worked out via brainstorming with the visual companion.
Added support for discounts in the POS checkout process, allowing operators to apply either a fixed amount or a percentage off the gross total. Updated the state management to include discount details and modified the receipt and cart rendering to display pre- and post-discount values. Enhanced the checkout API to handle discount inputs and ensure proper calculations. Updated relevant tests to cover new discount logic.
The 'Total {sumQty}{unitSuffix}' header line now explicitly documents
how mixed / missing units are handled: suffix is omitted when all
items have empty/null units (operator defaults to 'EA'); when units
are mixed, no suffix is shown; when all items share a non-EA unit
(e.g. BOX), the suffix is shown.
Self-review pass; no other changes.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Click-to-expand on each delivery-note row reveals an inline items
panel (description + qty) below the row. Operator can match the items
against the printed DN paper in their hand before loading. Pure
client-side render — items already loaded by /api/v1/deliveries are
filtered by delivery_note == dn.id. Empty state with fallback link to
/delivery-notes/[id] for DNs whose items aren't in the page slice.
Single-file edit on src/app/(app)/deliveries/page.tsx. No server,
schema, API, or MCP changes.
Co-Authored-By: Claude Code <noreply@anthropic.com>
The plan + summary landed locally during the implementation but were
not committed alongside the code. Both documents describe the
rep-scoped Orders / Quotes / Invoicing / Delivery Notes list filter
work that already shipped (commits 8faa443, ed07617, 29eb003, 9cf8e39
etc).
- 2026-08-31-rep-scoped-list-filter.md — the implementation plan
- 2026-09-01-rep-scoped-list-filter-SUMMARY.md — post-implementation
summary with the commit log + verification notes + the known
limitation (Orders/Quotes tab counts are unfiltered for reps)
Co-Authored-By: Claude Code <noreply@anthropic.com>
Three bite-sized tasks with full code:
1. TDD the order-age util (test → impl → run)
2. Wire OrderAgeBadge into /orders (replace bare date)
3. Enrich /deliveries DN row subline (customer/order/paperclip)
All UI/rendering only. No server, no schema, no MCP changes.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Two small, independent rendering improvements for /deliveries and /orders:
1. /deliveries — each delivery-note row gets a compact subline with
customer name, company name, parent order number, and a signed-copy
indicator (paperclip + filename tooltip). All data already on the
row payload — no server-side changes.
2. /orders — order card right-aligned metadata slot gets a colour-
coded age badge (today / Xd old) replacing the bare date string.
New src/lib/order-age.ts as a pure function with bucket thresholds
(green <3d, amber 3-7d, orange 8-14d, red 15+d) and a unit test.
No PB schema changes. No /api/v1 route changes. No MCP tool changes.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Two spec-vs-implementation drifts caught by the final review:
- Move 'per-row validation → 200 with reason in results[]' out of the
'Reject 400' list. The route enforces body shape (json / empty /
too-many / bad id / missing actor) as 400; the service enforces
forbidden_field / non-finite / not_found / pb_error per row so one
bad sibling never aborts the rest.
- Move the 'realtime-conflict banner' from Page-behaviour to Out of
scope (the implementation deferred it; the spec still listed it).
Refine the handling of order_number values in the MCP API. Custom free-text order_numbers are now allowed to repeat across orders without triggering collision checks, while only values formatted as ORD-YYYY-MM-NNN will be subject to collision verification. Update tests to reflect this new behavior and ensure proper functionality.
Backend-first TDD plan (pos-auth, pos-service, /api/v1/pos/* routes)
followed by relocating and rewiring the existing static POS mockup
into public/pos/, removing the hardcoded PB superuser credentials.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Scopes hardening the existing POS mockup (superuser creds removed,
catalog moved to stock_items, checkout wired to stock_ledger) as a
route inside WFDASH-WEBAPP rather than a separate service.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Three documents behind the two features on this branch:
- specs/2026-08-30-non-invoiceable-order-extras-design.md — the design
the implementation followed, including why the flag must be named for
the exception (a positively-named field defaults to false and would
mark every existing row non-billable the moment it is created).
- plans/2026-08-30-non-invoiceable-order-extras.md — the task-by-task
plan, now fully implemented.
- specs/2026-08-30-quantity-handling-audit.md — the order_qty /
quantity audit that produced the preceding fix, plus the partial
collection findings that are still open.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The original sample scored 0.222 Jaccard — below the 0.3 candidate
floor — so it would have been dropped rather than tiered. Verified
0.333 for the replacement.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
13 TDD tasks across two phases. Phase 1 (backend) ends with orders
matched automatically at intake plus a backlog sweep; Phase 2 surfaces
the paired quote line's note and attachments on both order pages.
Resolves the spec's two open questions: `after` is stable in
next/server on Next 16.2.6, and PocketBase date filters take
`.toISOString()`.
Two deviations from the spec, both noted in the plan: line pairing
hooks into the existing setOrderQuote rather than a new
linkQuoteToOrder, and the per-line context extends the existing
matched-attachments response rather than adding an endpoint.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Design for closing three gaps in the existing order↔quote matcher:
- The matcher only runs when an operator clicks it, so the ~85% of
orders that arrive against a quote stay unlinked. Adds a call from
createOrder plus a catch-up sweep for the backlog.
- order_items.quote_item is only written when an order is created
from a quote, so post-hoc links never pair lines. Adds persistence
for confident pairs.
- findMatchedQuoteItem re-guesses the pairing at render time using
exact/substring matching, so buyer notes and per-line attachments
silently vanish on any wording difference. Replaced with the
tokenised matcher already in the repo.
Fuzzy candidates are windowed to 90 days before the order's own date
(widening to 12 months only when nothing clears the threshold);
exact-identifier lookups stay unwindowed.
No PocketBase schema changes required.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
- Updated the search input handling to improve responsiveness by integrating a debounced search mechanism, reducing latency from 550 ms to approximately 300 ms.
- Added keyboard shortcut support for focusing the search box, enhancing accessibility and usability for frequent users.
- Improved the search placeholder to reflect all searchable fields, providing clearer guidance to operators.
- Introduced a clear-search button to streamline user interactions, allowing quick resets of the search input.
- Enhanced the display of search results with a live result count badge, providing immediate feedback on search outcomes.
These changes collectively enhance the search experience for operators, making it more intuitive and efficient.
Companion to the design spec at docs/superpowers/specs/. Covers all 15
implementation tasks (windowRange helper, aggregations, rep-activity
pagination, route handlers, tests, PWA manifest, mobile layout,
dashboard view with realtime + bottom sheet) plus the final
verification step.
Co-Authored-By: Claude <noreply@anthropic.com>
Introduces the `person_hint` field to the `EmailIntakePayload`, allowing the system to resolve the actual customer when a rep forwards an email. The `findOrCreateCustomer` function now prioritizes `person_hint` over the sender's email, enabling a more accurate attribution of quotes. This change includes a case-insensitive substring match with a token-drop fallback for multi-token names, ensuring better matching against existing customer records.
Additionally, new unit tests have been added to validate this functionality, covering various scenarios including token-drop behavior and ensuring the correct customer is linked when a rep forwards an RFQ.
Co-Authored-By: Claude <noreply@anthropic.com>
Gary (and any future rep) forwards inbound RFQs to a shared mailbox.
Today the customer linked to the resulting quote is the rep (or the
Unknown Sender sentinel), because the only resolution path is exact
email match — the from_email resolves to Gary, not the actual customer.
Add person_hint to EmailIntakePayload. The AI extraction layer reads
the subject / body / signature for the customer being quoted FOR and
fills person_hint. findOrCreateCustomer now walks three resolution
passes in order:
1. Exact email match (existing behaviour — direct RFQs unchanged)
2. person_hint resolution: case-insensitive substring on
customer.customer, with a companyHint tie-break when multiple
candidates exist
3. Existing sender-based create-new path (Gary wins, quoter
reassigns in the WFDASH UI)
MCP schema for quotes.create_from_email surfaces the new field with
doc explaining the rep-forwarded case. /api/v1/quotes/from-email
doc updated. AI Agent system prompt in the n8n workflow doc now
extracts person_hint with worked examples.
Also extends the mock filter parser to accept PB's bare ~ operator
(production code uses ~; the mock previously only accepted =~).
5 new unit tests + 2 integration tests for the new path.
Co-Authored-By: Claude <noreply@anthropic.com>
Hermes filed WFDASH-dev-ask-quotes-create.md on 2026-08-26 claiming
`quotes.create` doesn't exist. It does — registered at
src/app/api/mcp/route.ts:1131, REST at /api/v1/quotes/create, added
2026-08-15 in Phase G gap-fill, documented as Recipe 7 in
docs/agents/workflows.md. The agent's actual failure was discovery,
not a real gap.
Two doc-only changes to keep this from recurring:
1. Tool count 125 → 141 (live count), recipe count 7 → 9 (live count)
2. New prominent "Three quote-creation tools — don't confuse them"
section right under the intro listing all three paths
(quotes.create / quotes.ingest_from_email /
quotes.create_from_email) with the common failure mode explicitly
called out. Recipe 7 already covers the walk-in workflow;
this surfaces the contrast up front so the agent sees it during
session-startup instead of after it has already picked the wrong
tool.
No code change. No FEATURE-REQUESTS.md entry — the tool isn't a gap.
Co-Authored-By: Claude <noreply@anthropic.com>
