Commit Graph
59 Commits
Author SHA1 Message Date
james.maesandClaude Opus 5.5 0f34c8a1dc test(demo): the panel proposes a page change; screenshots of the card
The demo queues recorded answers that propose update_record on page 12
(READ_WRITE), so a question in the panel shows the confirmation card;
Save runs it through PATCH /qqq/v1/table/page/12 with the user's session.
Screenshots of the persona, the pending card and the confirmed write
(light/dark, 390/1440), taken locally against the demo server.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-13 14:34:36 -05:00
james.maesandClaude Opus 5.5 6634d88286 fix: log denied tool calls against their table; demo seeds persona and data access
- The tool's table is recorded before the call, so a call the UI API
  refuses still names its table in the log and in Recent denials.
- AssistantDemoServer seeds a default profile (Ada), an analysts profile,
  two skills (one linked) and data access rows (page READ_WRITE,
  media NONE).
- Screenshots of the Recent denials card, Explain access widget, Data
  access table, profile, skill and policy (light/dark, 390/1440).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-13 14:24:30 -05:00
james.maesandClaude Opus 5.5 0babaa7022 feat: profiles, skills, explain access and recent denials
Owner (2026-10-13): set a name, personality and extra skills for the
assistant, and the assistant stays limited to the UI API and to what the
signed-in user could do through it.

- assistant_profile (persona: display name, icon, bounded personality,
  greeting, starter prompts; default, app- or permission-scoped) and
  assistant_skill (admin Markdown instruction packs, read only when
  relevant, bounded) linked by assistant_profile_skill. Text only: it
  goes into the per-user system block and never reaches tool code.
- Explain access: GET /assistant/access and the assistantAccess home
  widget, per table and tool: allowed or why not, from GET /metaData with
  the user's own session plus data access and policy.
- Recent denials card on the Assistant home.
- Hard guarantee: ArchUnit forbids the tool / UI API / access packages
  from QQQ actions, the AI kernel and the profile/skill classes, and the
  store refuses any non-assistant_ table. A denial matrix proves query,
  get, insert, update and delete are denied identically via the UI API
  and via the assistant.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-13 14:10:47 -05:00
james.maesandClaude Opus 5.5 01cc719c5b feat!: assistant tools go through the /qqq/v1 UI API with the user's session
Owner decisions (2026-10-13): tools via the UI API, configurable and
verifiable data access, and confirmation for writes.

- Every data tool runs a spec'd /qqq/v1 operation (UiApiGateway, a
  loopback request carrying the user's own sessionUUID cookie), so it
  passes the UI's authentication, permissions, record locks, validation,
  audit and error mapping. LoopbackUiApiGateway is a stand-in for core's
  UiApiInvoker (QRun-IO/qqq#1128). navigate and search_help (no records)
  stay on the core kernel.
- Data access (assistant_data_access): NONE / READ / READ_WRITE per table
  or process; sensitive tables NONE and cannot be raised; it only narrows.
- Writes (create/update/delete_record) propose a pending action
  (assistant_pending_action) the owner confirms; confirm runs it once
  through the UI API with the confirming request's session.
- Policy: writesRequireConfirmation, allowedTools, maxRowsPerCall,
  redactPii. Tool-call log: UI API operation, HTTP status, audit link,
  pending action; inputs stored with secrets redacted.
- UiApiToolsSecurityTest proves a user without a permission gets the same
  denial through the assistant as through the UI; golden and red-team
  evals run through a real application server.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-13 13:56:18 -05:00
james.maesandClaude Opus 5.5 38bb123140 fix: stop sending every tool strict; surface provider error reasons
Every kof22 turn failed on its first model call with Anthropic 400
invalid_request_error "The compiled grammar is too large ... reduce the
number of strict tools". All ten read tools were strict, and the API
compiles every strict schema of a request into one grammar.

- Tools are not strict by default; hosts opt in with strictToolNames.
  The kernel validates every tool input (INVALID_INPUT) anyway.
- If a provider still refuses strict schemas, the turn retries once
  without strict tools and logs a warning.
- Provider errors carry the API error type, a sanitized message and the
  request id: logged at WARN on 4xx, request id kept on the usage row,
  the reason shown to assistant.admin holders and in Test connection.
- TurnEngine also catches Errors, so a turn never ends silently.
- AnthropicRequestContractTest checks the exact request against the
  Messages API constraints and a conservative strict-tool budget.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-13 13:25:28 -05:00
james.maesandClaude Opus 5.5 e54de89a49 feat: provider settings, per-call usage, model prices and the app home
- assistant_provider: type (registered AssistantProviderType; Anthropic),
  model, enabled/default, base URL override, cost cap, output and
  concurrency limits, last connection test. The key is never stored: the
  row names an allow-listed environment variable; apiKeyStatus is
  computed on read (last 4 at most) and dropped on save.
- Test connection: a record action (standard streamed ETL Review/Result)
  making one short live call; result saved on the row and as a TEST
  usage row.
- assistant_usage: one row per model call (turn steps and tests);
  assistant_model_price: editable USD/MTok used for every call's cost.
- The Assistant app home (health, providers, usage by day, costs vs caps,
  by user, top tools, recent failures); nav = home + main tables.
- AI exposure NONE on every assistant_* table.
- Tests, README, DESIGN, UPGRADE, CHANGELOG, reference DDL with the
  Anthropic price seed, demo server and screenshots.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-13 10:01:33 -05:00
james.maesandClaude Opus 5.5 e95fb90228 feat: red team, golden evals, developer panel, docs and CI
- ArchUnit rules: no system session, no QSession construction, data actions
  only in the persistence package.
- Permission red team (build gate): no-permission denial without leaks,
  other users' conversations, kill switch mid-turn, hard budget, hidden and
  password sentinels never sent, enveloped tool results, no thinking in SSE,
  cancel stops pending tools.
- Golden evals v1 (scripted faithful model) incl. example D and the read
  half of example A, plus an opt-in live run against Claude.
- Record Developer screen Assistant panel on the core developer-panel
  contract (QRun-IO/qqq#1076) fed by AiToolKernel.describeAccess, with the
  ask-the-assistant deep link.
- README, CLAUDE.md, CHANGELOG, reference DDL, CircleCI (qqq-orb 0.6.8).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-12 06:27:58 -05:00
james.maesandClaude Opus 5.5 003c66e14f feat: assistant qbit skeleton - config, tables, provider SPI, turn engine, SSE routes, Anthropic provider
Multi-module build (qbit-assistant, qbit-assistant-provider-anthropic) on
qbit-build-parent 2.0.0 with the qqq-snapshot BOM profile. Standard visible
assistant* tables with owner record locks, provider-neutral model SPI with a
scripted provider, turn engine on the core AiToolKernel, /qqq/v1/assistant
routes with SSE, and the Anthropic adapter with recorded-stream tests.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-12 06:10:59 -05:00
james.maes e62572b0d7 Initial commit 2026-10-12 05:32:28 -05:00