Replaces the legacy flowpilot_engine.escalate_session orchestration with
a single canonical path through HandoffManager. Every escalation now
creates a SessionHandoff row, fans out via the SSE bus, persists
AppNotification rows for the bell icon, dispatches to external channels
(Slack/Teams) via notify(), and emails per-user — regardless of whether
the call entered through /escalate (legacy URL) or /handoff (new URL).
The senior-pickup magic-moment screen now works end-to-end from the
EscalateModal bell-icon path the user just tested.
Backend
- HandoffCreateRequest gains optional target_user_id (the equivalent of
the legacy escalated_to_id field). Self-targeting rejected.
- HandoffManager.create_handoff handles intent='escalate' end-to-end:
sets escalation_reason + escalated_to_id, builds the legacy enhanced
AI escalation_package (Sonnet, lazy-imported from flowpilot_engine,
graceful fallback on failure), and merges handoff metadata into it.
Eager-loads session.steps and session.user via selectinload — required
by both the enhanced-package builder and notify() to avoid
MissingGreenlet on async lazy access.
- HandoffManager.finalize_escalation generates SessionDocumentation,
pushes documentation to PSA, and runs notify() — pre-commit so the
AppNotification rows persist atomically with the handoff.
- HandoffManager.dispatch_escalation_notifications keeps only the
fire-and-forget IO (bus publish, per-user emails) — runs post-commit.
Pulls engineer name via a separate User query rather than relying on
session.user lazy access.
- /handoff endpoint passes target_user_id through and calls
finalize_escalation pre-commit.
- /escalate endpoint is now a thin shim: owner-only session lookup,
HandoffManager.create_handoff(intent='escalate'), finalize_escalation,
commit, dispatch_escalation_notifications, return SessionCloseResponse
built from documentation + psa_result. flowpilot_engine.escalate_session
is no longer called by any endpoint.
- pickup_session accepts both 'requesting_escalation' (legacy in-flight
sessions) and 'escalated' (new canonical) so the migration is seamless
for sessions already in the queue.
- Escalation queue list and sidebar count now match either status.
Frontend
- useFlowPilotSession optimistic update flips status to 'escalated'
instead of 'requesting_escalation' so the page state matches the
unified backend response.
Verified end-to-end live: a fresh /escalate call from the junior produces
status='escalated', a SessionHandoff row, a SessionDocumentation, PSA
push attempted (no_psa for this test session), AND a bell-icon
AppNotification for the team admin with link
/pilot/{session_id}?pickup=true. Backend test suite: 1103 passed.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Two backend changes that unbreak the senior-pickup path from the
notification panel:
1. notification_service: session.escalated link template now ends with
?pickup=true so the senior lands in the handoff/pickup flow on
click. Without it, navigation hit /pilot/:id directly, which then
404'd on the GET because the senior isn't yet escalated_to_id —
the user perceives this as the bell-icon "just clearing the
notification".
2. ai_sessions GET access: any account member can now read an escalated
session's detail when status is requesting_escalation or escalated.
The owner-only guard was overly restrictive for explicitly-shared
in-transit states. Tenant boundary is enforced by RLS on the
underlying query, so account-scope is the right ceiling here. After
pickup, the existing handler/escalated_to_id checks still apply.
Verified live: re-login as the senior engineer and GET the active
escalated session — now returns 200 with full detail. Focused test
subset plus tests/test_sessions.py and tests/test_session_sharing.py
→ 94 passed in 43.26s, no regressions.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
First half of the WebSocket/SSE push slice. Paused mid-flight to hand
the branch to Codex for outside-voice review before stacking more
commits on top. See .ai/HANDOFF.md for the full pause context + what
to look at.
What's here:
- backend/app/core/escalation_bus.py — module-level singleton in-memory
pub/sub keyed by account_id. asyncio.Queue per subscriber with
64-event maxsize and drop-on-full semantics. Designed to be swappable
for Redis pub/sub when Railway scales past single-replica.
- backend/app/api/endpoints/session_handoffs.py — GET
/api/v1/ai-sessions/escalations/stream SSE endpoint. Auth via
require_engineer_or_admin. 25s heartbeat. Account-scoped subscribe
bound to current_user.account_id.
- backend/app/services/handoff_manager.py — dispatch_escalation_notifications
now publishes a `handoff_created` event to the bus BEFORE the email
fan-out, in a try/except so a bus failure can't block email delivery.
- backend/tests/test_escalation_bus.py — 7 unit tests, all green
standalone (0.14s). Cross-tenant isolation, drop-on-full, no-subscribers.
- backend/tests/test_handoff_manager.py — +1 dispatcher integration test
(publishes to bus, payload shape).
- backend/tests/test_session_handoffs_api.py — +2 endpoint tests (viewer
blocked, ready event handshake).
[gstack-context]
Decisions:
- SSE over WebSocket (one-way, browser EventSource semantics, fewer
moving parts behind Railway proxy)
- In-memory bus over Redis for v1 pilot (3 MSPs, single replica)
- Drop-on-full subscriber queue rather than back-pressure publishers
- Bus publish ahead of email send, both wrapped in try/except so
neither can break handoff creation
- Frontend will be a fetch-based ReadableStream reader matching the
existing streamDocumentation pattern, not native EventSource
(custom-header auth)
Remaining (post-Codex):
- Frontend SSE subscription in EscalationQueue.tsx (slide-in,
reconnect, tab-title flash, prefers-reduced-motion)
- Magic-moment handoff-context screen
- Re-run the full backend test suite to verify the SSE +
dispatcher integration tests (bus units already green standalone)
Tried:
- Running the full test suite repeatedly without xdist; the per-test
DROP SCHEMA + recreate fixture made wall-clock prohibitive when
multiple stale runs collided on the same Postgres test schema.
Resolution: -n auto next time.
[/gstack-context]
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
First half of the Escalation Mode notification dual-path. WebSocket/SSE
push is the second half (next commit) — email handles offline seniors,
push handles online ones for the magic-moment demo.
HandoffManager.dispatch_escalation_notifications:
- Pulls active engineer/admin/owner-role users in the same account_id
(excludes the escalator + viewers + soft-deleted)
- Sends via existing EmailService.send_notification_email, concurrent
via asyncio.gather; per-message failures don't block the rest
- Wrapped in try/except: any exception is logged + swallowed. Handoff
creation is authoritative; notification is advisory. This is the
graceful-degradation regression both eng + codex reviews flagged as
critical (handoff must succeed even if SMTP is down).
Endpoint wiring (POST /ai-sessions/{id}/handoff):
- Dispatch fires AFTER db.commit() — never email about a rolled-back
handoff. Trust-erosion bug if we got that wrong.
- Only fires for intent=escalate. Park is private to the escalator.
Tests (4 new):
- emails-engineer-recipients-in-account: viewer excluded, escalator
excluded, only the engineer/admin teammates get the message
- skipped-for-park-intent: park doesn't fan out
- graceful-degradation-when-email-raises: RuntimeError from the email
service does NOT bubble out of dispatch
- endpoint-dispatches-on-escalate: end-to-end wiring through POST
Per-channel delivery records (replacing the dead `notification_sent`
boolean per Codex correction) is a v1.x story — for now application
logs are the audit trail. See
docs/plans/2026-04-27-escalation-mode-wedge-design.md.
20 tests green across handoff_manager + session_handoffs_api +
flowpilot_analytics_escalations. No regressions.
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>
POST /script-builder/sessions now supports origin='pilot_inline':
- Requires ai_session_id; validates it against current user ownership.
- Get-or-create: returns existing row for (user, ai_session_id) pair.
- Partial unique index on the DB backs the invariant; races resolve to
the single winner row.
list_sessions + count_user_sessions default-scope to origin='standalone'
so inline scratch sessions don't pollute the /script-builder dashboard
or count against the 5-session cap.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Issue #1 from phase-8-review-issues.md. Cache invalidation alone isn't
enough — previews were also omitting outcome fields from the LLM bundle,
so a fresh regenerate still couldn't distinguish proposed / failed /
partial / success.
- PATCH /outcome now bumps ai_sessions.state_version (matches
record_decision's existing pattern).
- Resolution-note + escalation-package bundles now include status,
applied_at, verified_at, partial_notes, failure_reason on the active fix.
- Generator prompts prescribe outcome-aware phrasing (closure language
for success; what-we've-tried + next-steps for failed/partial).
- New end-to-end test asserts the regenerated preview reflects the
recorded outcome, not just that the cache key changed.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Tells the AI when + how to emit the [FIX_OUTCOME] marker that Task 4's
parser consumes. Placeholder-only per the anti-parrot pattern — no
literal UUIDs, outcomes, or reasons that could leak into unrelated
sessions.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The AI emits [FIX_OUTCOME] when the engineer indicates in chat that a
prior suggested fix worked, didn't work, or was partially applied. The
marker writes to session_suggested_fixes.ai_outcome_proposal (JSONB),
which the frontend surfaces as a "confirm outcome?" banner. The status
column is only updated when the engineer clicks confirm (via PATCH
/outcome endpoint from Task 3).
Placeholder-only system prompt wiring comes in Task 5.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The "AI parrots example content from system prompt" bug bit us twice in
one day across two different prompt sites. Patching individual prompts
is treating the symptom; this commit makes the rule structural.
Audit + sanitize:
- assistant_chat_service.ASSISTANT_SYSTEM_PROMPT — already cleaned in
prior commits, but the [FORK] schema still had literal "Brief reason"
/ "Short name" / "One sentence" placeholders. Replaced with
<angle-bracket> placeholders. Anti-parrot rule itself rewritten to
describe the failure mode abstractly instead of naming "jsmith" so
the rule no longer trips the guardrail (and so the model doesn't
see "jsmith" as a token at all).
- ai_chat_service.py — removed three concrete-example offenders:
"Get-Service ADSync" command literal, the "DC01 server_name" intake
form payload (in two places), and the inline interview demos using
"Azure AD Sync failures" / "Exchange Online mailbox migration".
Replaced with technology-neutral schema descriptions.
- ai_tree_generator_service.BRANCH_DETAIL_SYSTEM_PROMPT — replaced the
fully-fleshed DNS troubleshooting tree (with literal Dnscache /
ipconfig / google.com / Start-Service) with a placeholder schema
showing only ID-linkage shape.
- kb_conversion_service.PROCEDURAL_SYSTEM_PROMPT — replaced the worked
Server Manager + DC01 example payload with a placeholder schema.
Guardrail (tests/test_prompt_anti_parrot.py):
- Imports every module under app/services/ and app/core/ and walks
every uppercase string constant ending in _PROMPT, _SCHEMA,
_PROTOCOL, _FORMAT, or _CONTEXT.
- test 1: known-leaked-token list (jsmith, DC01, ADSync, Dnscache,
google.com, "Outlook keeps", "Teams drops") must not appear in any
prompt constant. Add to the list when a new leak shows up in prod —
the list IS the audit trail.
- test 2: marker blocks ([QUESTIONS], [ACTIONS], [SUGGEST_FIX], etc.)
must contain placeholders only. Distinguishes JSON keys (followed
by ':', allowed) from JSON values (followed by ',' / ']' / '}',
must be <placeholder>); allows pipe-separated enum types
(text|password|select) and a small set of fixed enum values
(question, diagnostic_check, decision, action, ...). Verified by
feeding the test a known-bad block — caught it correctly.
Documented the rule in CLAUDE.md → AI / FlowPilot lessons, naming
the test as the enforcement point so future contributors know how to
extend it (add to the known-leaked list when a new leak surfaces).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The system prompt had a "Complete example of a correct first response"
section with a specific Outlook/WiFi/jsmith scenario plus literal JSON
payloads in [QUESTIONS], [ACTIONS], [SUGGEST_FIX], and [PROMOTE]
markers. The model was emitting those literal strings (the same
WiFi/laptop questions, the same "Clear cached credentials" suggested
fix, the same "OWA login confirmed for jsmith" promote) on EVERY
unrelated chat — making the task lane look like it was leaking previous-
session data when in fact the AI was just reciting the prompt examples.
Replaced literal example content with `<placeholder>` schemas. Added an
explicit ANTI-PARROT RULE in the FINAL REMINDER section calling out
that the angle-bracket placeholders show SHAPE, not CONTENT, with
concrete examples of the failure mode (printer ticket → don't ask
about Outlook; user not named jsmith → don't name jsmith).
Same scrub applied to the FORK section's "Outlook AND Teams dropping"
and the worked fork-flow example.
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>
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>
Renames the chat caller to a name that signals its actual purpose, and
factors the reusable cached-system-block + cached-history + cache-usage-log
primitives out to app.core.ai_provider so they can be shared with the
provider-generic path without pulling MCP/beta/images into the abstract
interface.
Helpers added to ai_provider.py:
- `build_anthropic_chat_messages(history, new_message, images, format_reminder)`
— owns: copy history, apply cache_control to last history message,
append format reminder to new message, render images as multimodal blocks.
Anthropic-shaped by design; do not call from Gemini paths.
chat_call_cached keeps exactly the concerns that are unique to the one
MCP/beta/multimodal chat caller:
- Anthropic beta endpoint invocation
- Microsoft Learn MCP server wiring (ENABLE_MCP_MICROSOFT_LEARN)
- Retry-without-MCP fallback
- Format-reminder content string (declared as module constant)
- Phase 0.5 telemetry (mcp.turn, mcp.fallback)
Documents in the module docstring AND at the function site that this is
the ONE MCP/beta chat caller and should not become the general provider
path. MCP/beta/images are features of exactly one optional Anthropic beta
endpoint; routing them through AnthropicProvider would leak a provider-
specific concern into the abstract interface that also serves Gemini.
Behavior change: chat_call_cached now reuses the singleton AnthropicProvider
HTTP client via `_get_anthropic_client(...)` instead of instantiating a new
`anthropic.AsyncAnthropic(...)` per call. Matches the provider's own pattern
and avoids burning connections per-turn. No user-visible difference.
No runtime verification from code-server. TODO(phase0-verify) in
ai_provider.py tracks the cache-hit verification owed on the new dev env.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Wraps each static system prompt in a single-block list so Phase 0.1's
AnthropicProvider applies cache_control: ephemeral automatically (policy α,
first block gets marked when no caller-authored cache_control is present).
Call sites:
- ai_tree_generator.scaffold_branches: SCAFFOLD_SYSTEM_PROMPT (~1k tokens)
- ai_tree_generator.generate_branch_detail: BRANCH_DETAIL_SYSTEM_PROMPT
(~2.5k tokens with few-shot example); retries inside the same function
re-read the cached block instead of paying full input cost on each attempt
- kb_conversion.convert_document: TROUBLESHOOTING or PROCEDURAL prompt
(each caches independently by text content)
- ai_fix.generate_fixes: FIX_SYSTEM_PROMPT on first attempt + corrective retry
- script_builder.send_message: SYSTEM_PROMPT_TEMPLATE (per-session language
substitution — same-language sessions share cache entries)
Each edit includes an inline comment explaining why the block is cacheable
(stable-constant, retry-reuse, per-language variant) so a future dev can
see the intent at the cache_control marker site.
script_builder history caching deliberately deferred — per Phase 0.1
decision (option i), AnthropicProvider does not automatically cache the
message list. If script_builder's growing 20-message history turns out
to be a visible cost driver via the anthropic.cache telemetry, route
that caller through the 0.4 chat wrapper which handles history caching.
No runtime verification from code-server; cache-hit behavior will be
confirmed against the new dev environment when it's up, per the inline
TODO(phase0-verify) in ai_provider.py.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Emits structured `mcp.turn` log events on every Anthropic-path chat turn,
capturing whether MCP was wired in (mcp_available), whether the model
actually invoked an MCP tool (mcp_invoked), which tool names fired,
and whether the silent retry-without-MCP fallback was triggered.
Adds a separate `mcp.fallback` event with error type/message for
fallback occurrences.
Establishes baseline data for deciding whether MCP investment is earning
its keep before Phase 2+ expands the product footprint. Scope: the one
MCP-using code path (`_call_anthropic_cached`) — not a general
instrumentation layer.
No new dependencies, no schema changes, no behavior change. Standard
library `logging` is the sink; PostHog is not wired on the backend.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The previous implementation PATCHed the `resources` string directly, which CW
silently ignores because `resources` is a server-derived read-only field (it's
populated from schedule entries of type/id=4, not freely writable).
Per CW docs (openapi line 70949): "Please use the
/schedule/entries?conditions=type/id=4 AND objectId={id} endpoint".
Behavior per spec:
- No owner + assign user → set owner (existing behavior kept)
- Has owner + assign different user → POST /schedule/entries with type/id=4,
member, objectId; owner untouched
- User already assigned (owner or schedule entry) → idempotent no-op
- Remove owner → clear owner (existing behavior kept)
- Remove co-assignee → DELETE /schedule/entries/{entry_id}
- list_resources now merges owner + schedule-entry members, deduped by id
Required CW security role permission on the API member:
- Service > Resource Scheduling > Add/Inquire/Delete
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Previous `resources`-string PATCH was silently ignored by CW — the
`resources` field is server-derived from the ticket's owner + schedule
entries, not freely writable. Status PATCH could also silently no-op
when a cross-board status id was sent.
- add_resource: when the ticket is unassigned, set the `owner`
MemberReference (the canonical writable primary-assignee field).
If already owned by someone else, append the identifier to the
`resources` co-assignee string best-effort.
- remove_resource: clear `owner` (with remove→replace:null fallback) if
the target is the current owner, otherwise strip from `resources`.
- list_resources: merge owner + resources string, deduped by member id,
so the UI reflects both single-owner and multi-resource assignments.
- update_ticket_status: verify CW applied the status by comparing the
response body's status.id — raises PSAError with a clear message when
CW silently rejects the change (e.g., status invalid for ticket's
board), instead of reporting spurious success.
- Frontend: surface the backend error detail in the toast so users see
the real reason instead of a generic "Failed to update" message.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Status update was returning only new_status (string) and the parent list's
onStatusUpdated only set status_name. The <select> was bound to status_id,
which never changed — so it visually reverted to the old status even though
the PATCH succeeded.
- Backend: include new_status_id in the status-update response.
- Panel: own currentStatusId/currentStatusName state so the select reflects
the change immediately and survives stale parent snapshots.
- Parent list: update status_id on both the row and selectedTicket so the
list row stays in sync when the panel stays open.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Status filter: aggregate statuses across all boards (deduped by name)
when no board is selected. Backend accepts status_name and filters by
status/name so the same status matches across boards.
- Resource assignment: CW has no /service/tickets/{id}/members endpoint —
assignees live in the ticket's comma-separated `resources` string field.
Rewrote list/add/remove to read/PATCH that field via member identifier.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Apply company_id filter in CW search_tickets conditions (was silently ignored)
- Sanitize query string to strip single quotes before CW condition interpolation
- Add psaError state to TicketsPage for permissions error surfacing
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- flowpilot_engine: pass account_id at all 5 AISessionStep instantiation
sites (_create_step_from_parsed x3, briefing step, status update step).
Phase 4 RLS blocked every INSERT with NULL account_id — this broke all
new FlowPilot sessions since the Phase 4 migration was applied.
- integrations: list_boards returns [] on PSAError instead of 502, stopping
the spurious 'Server error' toast on dashboard load (boards are optional).
- client.ts: 5xx global toast now shows backend detail when available.
- useFlowPilotSession: startSession extracts backend detail for error state;
suppresses duplicate toast for 5xx (global interceptor already handles it).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
CW resources field is a plain string of member identifiers (login names),
not a navigable object. resources/member/id was invalid syntax causing 403.
Now resolves the CW member identifier from the cached member list and
uses: resources contains '{identifier}' which is the correct condition.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Requires CW API member security role to have All scope on Service Tickets.
owner/id was incorrect for workflows using resources-based assignment.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
resources/member/id requires All scope on Service Tickets security role.
owner/id (primary assignee) works with standard Mine scope.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add PSABoard type + list_boards() to CW provider (cached 1h)
- Extend search_tickets with assigned_to_me, unassigned, board_ids, page, page_size
- New GET /integrations/psa/boards endpoint
- New TicketQueue dashboard component: My Tickets / Unassigned tabs,
multi-select board filter, Load more pagination, Start Session per ticket
- Add TicketQueue to QuickStartPage after active sessions
- FlowPilotSessionPage auto-starts with ticket context when navigated
from TicketQueue (psaTicketId + psaTicket in location.state)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Fix create_time_entry() using self._client instead of self.client
- GET /member-mappings now returns all active account users, not just mapped
ones — allows manual assignment when auto-match by email doesn't work
- PsaMemberMappingResponse mapping fields are now Optional (id, external_member_id,
external_member_name, matched_by) to represent unmapped users
- Frontend MemberMappingTab skips null external_member_id when building
localMappings, and derives user list from all returned entries
- Add docs/connectwise-psa-testing-checklist.md
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat: add device_types table with system seed data
Creates DeviceType SQLAlchemy model and migration 073 that provisions the
device_types table with 28 system-seeded device types across 7 categories
(network, compute, storage, cloud, endpoint, infrastructure, security).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add network_diagrams table
Create NetworkDiagram SQLAlchemy model with JSONB nodes/edges, team-scoped with client/asset metadata, and Alembic migration 074.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add Pydantic schemas for device types and network diagrams
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add device types CRUD router
Adds GET/POST/PUT/DELETE endpoints at /device-types with team-scoped access. System types are read-only; custom types are scoped to the creating team.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add AI generation service for network diagrams
Adds network_diagram_ai_service.py with generate_diagram() function that
calls the AI provider to convert plain-English network descriptions into
structured DiagramNode/DiagramEdge data. Registers the action in
ACTION_MODEL_MAP as a standard-tier route.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add network diagrams CRUD + AI generate + export/import router
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add TypeScript types for network diagrams
Adds all interfaces for network diagrams and device types including
DiagramNode, DiagramEdge, DeviceProperties, NetworkDiagramResponse,
AI generate request/response, import/export shapes, and list item types.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat: add frontend API clients for device types and network diagrams
Adds deviceTypesApi (list, create, update, remove) and networkDiagramsApi
(list, get, create, update, archive, duplicate, exportJson, importJson,
aiGenerate, listClients) following the existing apiClient module pattern.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat: add device registry, DeviceNode, ConnectionEdge for React Flow
Creates the React Flow building blocks for the network diagram editor:
device type registry with icon/color mappings, DeviceNode component with
status indicators and connection handles, ConnectionEdge with per-type
styling, and nodeTypes/edgeTypes registration maps.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add DeviceToolbar panel with search, categories, drag-drop, custom type creation
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add PropertiesPanel for node and edge property editing
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add AIAssistPanel with replace and merge modes
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add NetworkCanvas wrapper and DiagramHeader components
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add DiagramEditor page assembling all panels with auto-save and AI generation
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add Network Diagrams list page with search, client filter, import
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add Network Maps to sidebar navigation and router
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: resolve TypeScript errors in DeviceToolbar and DiagramEditor
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: resolve stale selection bug in network diagram PropertiesPanel
Selection state now stores IDs and derives objects from live arrays,
so edits in PropertiesPanel inputs reflect immediately.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add React Flow UI foundation components for network diagrams
BaseNode (structured node shell with header/content/footer slots),
BaseHandle (styled connection handle), LabeledHandle (handle with
port label), NodeStatusIndicator (status border effect),
NodeTooltip (hover details via NodeToolbar).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add LabeledGroupNode and AnimatedSvgEdge components
GroupNode for subnet/VLAN/site grouping with positioned label badge.
AnimatedSvgEdge for traffic flow visualization with animated SVG
shape along edge path. Both registered in type maps.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* refactor: DeviceNode uses BaseNode, BaseHandle, StatusIndicator, Tooltip
Replaces hand-rolled node layout with composable React Flow UI
components. Status is now a border effect instead of a dot.
Hover tooltip shows hostname, IP, vendor, role, notes.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add grouping toolbar items and traffic flow toggle
DeviceToolbar gets Subnet/VLAN/Site/DMZ grouping section with
drag-drop. PropertiesPanel gets Show Traffic toggle that switches
edges between connection and animated types. DiagramEditor handles
both device and group node drops.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: address code review findings for React Flow UI integration
- Use screenToFlowPosition() for drop coordinates (fixes zoom/pan bug)
- Remove duplicate selection border from DeviceNode (BaseNode handles it)
- Add w-full to GroupNode for proper container sizing
- Remove unused 'selected' destructuring from DeviceNode
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add ISP icon to network diagram device registry
Globe icon with accent color, under cloud category.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: improve drag-and-drop feel in network diagram editor
Grip icons on draggable toolbar items, press effect on drag start,
dashed border overlay with 'Drop to add' text when dragging over canvas.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add ContextMenu component for network diagram editor
Charcoal-styled context menu with action factories for node
and canvas variants. Viewport-clamped positioning, auto-dismiss
on click outside, escape, or scroll.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add useCanvasShortcuts hook for copy/paste/duplicate
Keyboard shortcuts with preventDefault and input guard.
Clipboard stores nodes with relative positions and edge indices.
Paste computes canvas center via screenToFlowPosition.
Duplicate offsets +30px. Supports both device and group nodes.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: wire context menu and keyboard shortcuts into diagram editor
Right-click context menus for nodes (copy/duplicate/delete) and
canvas (paste/select-all/fit-view). Right-click selects the node
per spec. serializeNodes now handles group nodes correctly.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: context menu dismisses on pane click, ISP in toolbar
Context menu now closes when clicking anywhere on the canvas via
onPaneClick prop. ISP device added as built-in toolbar item under
Internet section so it's always available without a database entry.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: backend code review fixes for network diagrams
- Replace legacy Optional imports with modern str | None syntax
- Type JSONB columns as Mapped[list[dict[str, Any]]]
- Escape SQL LIKE wildcards (%, _) in diagram search
- Type DiagramNode.position as Position(x, y) Pydantic model
- Wrap AI response parsing in KeyError handler for clean 422 errors
- Remove unused Optional/TYPE_CHECKING imports from schemas/models
- Extract _get_available_slugs helper to DRY duplicate queries
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: network diagram editor UX — straight edges, snap-to-grid, ISP in Cloud, group resize
- Straight edges: replace SmoothStepEdge with BaseEdge + getStraightPath so
connections draw direct diagonal lines instead of orthogonal bent paths
- Snap-to-grid: add snapToGrid/snapGrid=[20,20] to NetworkCanvas so nodes
align consistently when dragged
- ISP in Cloud: remove standalone "Internet" sidebar section, inject ISP into
the Cloud category loop with search support and correct item count
- Group node resize: add NodeResizer to GroupNode (subnet/VLAN/site/DMZ),
handles visible when selected; dimensions saved/restored correctly on
reload (also fixes group node load bug where type was always 'device')
- DiagramNode type: add nodeType and style optional fields
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: network diagram team_id guard + multi-style edge routing
Backend:
- Guard create_diagram with 422 if current_user.team_id is None (prevents
NOT NULL constraint crash for accounts not yet assigned to a team)
- Add routing field to DiagramEdge schema (straight/curved/step)
Frontend:
- ConnectionEdge now supports straight (default), curved (bezier), and
step (smooth-step) routing per-edge via routing field in edge data
- PropertiesPanel Connection section gets a Line Style toggle:
Straight | Curved | Step buttons, active state highlights in accent
- handleEdgeUpdate and serializeEdges now propagate the routing field
- DiagramEdge type gets optional routing field
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat: network diagrams UX overhaul — icons, empty canvas, properties panel
- Colorize: semantic category colors for all device types (network=blue,
security=orange, compute=emerald, endpoint=amber, storage=violet,
cloud=cyan, infra=steel); better icons (Router, ShieldAlert, Boxes,
Package, Gauge, PlugZap, Video, Radio); MiniMap uses category colors
- Onboard: centered AI generate prompt on empty canvas with 5 MSP-specific
example chips, ⌘↵ shortcut, spinner; AIAssistPanel only shown with nodes
- Arrange: properties panel — status badge grid at top, fields grouped into
Network (IP/Subnet/VLAN) and Hardware (Hostname/Vendor/Model/Role) sections
- Delight: segmented topology color bar on listing cards; backend returns
category_counts via single extra query on list endpoint
- Harden: real PNG export via html-to-image + getNodesBounds/getViewportForBounds
- Polish: ChevronDown replaces unicode ▾, click-outside for client filter,
consistent spinner in empty prompt
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore: drop changelog noise from network extraction
* fix: align network map builder with account isolation
* feat: add manual create option for network maps
* feat: make manual network map creation easier to discover
* fix(network-maps): address design critique — harden, normalize, clarify, polish
- Archive: two-step inline confirm in card dropdown menu
- Delete Device/Edge: two-step inline confirm in PropertiesPanel footer
- Context menu Delete: floating confirm bar instead of immediate deletion
- AI Generate New: two-step confirm when replacing existing diagram nodes
- DiagramHeader: show 'Unsaved changes' in amber when isDirty and not saving
- deviceRegistry: SECURITY_COLOR #f97316 → #f87171 (deprecated ember orange removed)
- CanvasEmptyPrompt: remove backdrop-blur (design system violation)
- CanvasEmptyPrompt: remove redundant 'Skip AI' bottom button (duplicate of Build manually card)
- CanvasEmptyPrompt: rounded-xl/rounded-2xl → rounded-lg, border-2 → border
- Topology bar: h-1 → h-2 + native tooltip with category breakdown
- AIAssistPanel: replace pulse-dot loading with spinner (consistent with rest of feature)
- ContextMenu: add shadow-lg (consistent with other dropdowns)
- DeviceNode tooltip: Position.Bottom → Position.Top (avoids canvas-edge clipping)
- CanvasEmptyPrompt: raise ⌘↵ hint from /50 opacity to full text-muted-foreground
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(network-maps): bring to front / send to back layering for nodes
Three entry points for z-index control:
- Right-click context menu: Bring to Front / Send to Back with ] / [ shortcuts, separated by dividers from copy/delete groups
- Properties panel: Layer row with Bring Front + Send Back buttons, tooltip shows keyboard shortcut
- Keyboard: ] brings selected node(s) to front, [ sends to back (skips when input focused)
Context menu also gains divider support (dividerBefore flag) for visual grouping.
Layering handlers use max/min zIndex across all nodes so repeated presses always stack correctly.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: swap switch icon from Layers → Network (Lucide)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat: icon size picker (S/M/L) on device nodes
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat: drag-to-resize device nodes + BrickWallFire for firewall
- NodeResizer on DeviceNode (same pattern as group nodes); icon scales
proportionally with node width, clamped 16–60px
- Removes S/M/L static picker — resize is now direct manipulation
- firewall: ShieldAlert → BrickWallFire
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore: trigger Railway rebuild
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: add missing hero_001.jpg to git (was untracked, broke Railway deploy)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: ShieldAlert still referenced in CATEGORY_DEFAULTS after icon swap
Removed ShieldAlert from imports when swapping firewall icon to BrickWallFire
but left it in CATEGORY_DEFAULTS — runtime crash, device toolbar empty.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(network): proportional node resize with locked aspect ratio
Nodes grew into rectangles because NodeResizer had no aspect ratio
constraint, minWidth != minHeight, and icon/text only scaled from width.
- DeviceNode: add keepAspectRatio + equal minWidth/minHeight (80×80),
maxWidth/maxHeight (280×280), scale icon and label/IP font sizes from
Math.min(width, height) so all content grows uniformly
- DiagramEditor: set explicit 120×120 style on dropped device nodes so
React Flow has a definite starting size for aspect ratio calculation
- DiagramEditor: persist device node style (width/height) in
serializeNodes and restore it on load so size survives save/reload
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(lint): suppress ESLint errors in network diagram components
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Service layer (production code):
- branch_manager: set account_id on SessionBranch (root + fork) and ForkPoint
from session.account_id; load session in create_fork for this purpose
- handoff_manager: set account_id on SessionHandoff from session.account_id
- ai_suggestions endpoint: set account_id on AISuggestion from current_user
- steps endpoint (/feedback): set account_id on StepRating from current_user
- ratings endpoint: set account_id on StepRating from current_user
Test infrastructure:
- conftest.py: seed PLATFORM_ACCOUNT_ID (00000000-...-0001) account after
Base.metadata.create_all so global categories and gallery items have a valid FK
- test_rls_isolation: add _ensure_rls_schema fixture that runs
'alembic upgrade head' before module tests — previous function-scoped
test_db fixtures drop the schema, leaving the RLS tests with no tables
- test_branding: create Account before User in helper functions
- test_admin_gallery: set account_id=PLATFORM_ACCOUNT_ID on Tree/ScriptTemplate
- test_public_templates: set account_id=PLATFORM_ACCOUNT_ID on Tree,
ScriptTemplate, TreeCategory
- test_resolution_outputs: set account_id=session.account_id on
SessionResolutionOutput
- test_analytics_phase5: set account_id on PsaPostLog
- test_draft_trees: replace account_id=None with PLATFORM_ACCOUNT_ID in
migration default test (NOT NULL now enforced)
- test_maintenance_schedules: set account_id on other_tree
- test_save_session_as_tree: set account_id on all 5 Session() constructors
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* docs: add tenant data isolation design spec
Complete architecture plan for multi-tenant data isolation across
all layers (PostgreSQL RLS, application-layer filtering, schema
migration, testing strategy, and phased rollout checklist).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* docs: add background job isolation policy to tenant isolation spec
Documents policy for all 5 existing background jobs:
- Knowledge Flywheel and PSA Retry flagged for account_id threading
- Chat Retention already follows correct pattern (model for others)
- Maintenance Schedule Firing needs account_id in queries + Session creation
- AI Conversation Expiry approved as cross-tenant with justification
Adds approved cross-tenant query registry and Phase 2 checklist items.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* docs: add tenant isolation Phase 0 implementation plan
8 tasks covering: CRITICAL copilot hotfix, tenant_filter() helper,
get_tenant_context dependency, analytics/category/AI session gap fixes,
full UUID endpoint audit, TargetList dead code audit, teams orphan
check, and CI grep check for missing tenant filters.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: CRITICAL — scope copilot tree query to current account
A user who knew another account's tree UUID could start a copilot
conversation, causing the tree's full node structure, names, and
descriptions to be sent to the AI as part of the system prompt.
Fix: add account_id (or is_default / visibility='public') filter to
the tree SELECT in copilot_service.start_conversation(). Returns 404
for inaccessible trees. Test added in test_tenant_isolation_p0.py.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <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>
- 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>
- Reformat PSA resolution/escalation notes: clean single-line header,
steps with engineer responses inline, remove duplicate timing blocks,
remove AI confidence section, add follow-up recommendations
- Standardize time display to decimal hours (e.g. 0.25 hrs) across all
note formatters and status update context
- Add follow_up_recommendations to SessionDocumentation schema and
surface in SessionDocView; extracted from resolution suggestion steps
- Add _build_what_we_know() helper: uses session.evidence_items when
cockpit branch merges, falls back to deriving findings from steps
- Fix option label lookup in generate_status_update (was passing raw
machine values to AI instead of human-readable labels)
- Add 'What We Know' section to status update ticket notes prompt
- Improve _build_session_context in resolution_output_generator to
include intake text and full step details instead of truncated chat
- Add request_info audience type: client-facing information request
that skips the length step and generates a numbered question list
- Improve client_update and email_draft prompts with per-context
guidance (status/resolution/escalation) and fix escalation subject
line from 'Specialist Review' to 'Specialist Assistance'
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- script_builder endpoint: pg_advisory_xact_lock on user_id before
session count check, preventing concurrent creates from both passing
the MAX_SESSIONS_PER_USER guard
- script_builder_service send_message: pg_advisory_xact_lock on session_id
before message count check, preventing concurrent sends from both
passing the MAX_MESSAGES_PER_SESSION guard
- script_builder_service save_to_library: replace check-then-insert slug
logic with IntegrityError retry loop (3 attempts with fresh UUID suffix);
add unique constraint on script_templates.slug (migration 070)
- ScriptBuilderPage: add creatingSessionRef to serialize concurrent
handleSend calls that would otherwise both call createSession() while
session is still null
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The generate_status_update service inserted AISessionStep with
step_type='status_update' which violated the DB CHECK constraint,
causing a 500 error. Also fix incorrect field name confidence_score
(should be confidence_at_step) and remove nonexistent confidence_tier.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
