pi-ui-extend 1.0.40 → 1.0.41

package/schemas/pi-tools-suite.json

@@ -145,10 +145,6 @@
             "enabled": {
               "type": "boolean",
               "description": "Enable manual DCP mode."
-            },
-            "automaticStrategies": {
-              "type": "boolean",
-              "description": "Run dedup/purge even in manual mode."
             }
           },
           "description": "Manual mode configuration."
@@ -358,79 +354,77 @@
                 }
               },
               "description": "Message-mode compression configuration."
-            }
-          },
-          "description": "Compression trigger and behavior configuration."
-        },
-        "strategies": {
-          "type": "object",
-          "properties": {
-            "deduplication": {
-              "type": "object",
-              "properties": {
-                "enabled": {
-                  "type": "boolean",
-                  "description": "Enable duplicate content deduplication."
-                },
-                "protectedTools": {
-                  "type": "array",
-                  "items": {
-                    "type": "string"
-                  },
-                  "description": "Tool outputs protected from dedup."
-                }
-              },
-              "description": "Deduplication strategy configuration."
             },
-            "purgeErrors": {
+            "autoCompress": {
               "type": "object",
               "properties": {
                 "enabled": {
                   "type": "boolean",
-                  "description": "Enable error input purging."
+                  "description": "Allow bounded automatic summary creation after pressure/opportunity gates."
                 },
-                "turns": {
+                "patience": {
                   "type": "number",
-                  "description": "Prune error inputs after N user turns.",
-                  "minimum": 1
+                  "description": "Completed actionable opportunities allowed before automatic compression.",
+                  "minimum": 0
                 },
-                "protectedTools": {
+                "summarizerModel": {
                   "type": "array",
                   "items": {
                     "type": "string"
                   },
-                  "description": "Tool outputs protected from error purge."
+                  "description": "Ordered summarizer model refs; empty uses the deterministic extractive summary."
+                },
+                "timeoutMs": {
+                  "type": "number",
+                  "description": "Per-summarizer deadline in milliseconds.",
+                  "minimum": 1
                 }
               },
-              "description": "Error purging strategy configuration."
-            },
-            "autoToolPruning": {
+              "description": "Bounded automatic compression fallback."
+            }
+          },
+          "description": "Compression trigger and behavior configuration."
+        },
+        "strategies": {
+          "type": "object",
+          "properties": {
+            "emergencyCurrentTurnPruning": {
               "type": "object",
               "properties": {
                 "enabled": {
                   "type": "boolean",
-                  "description": "Enable automatic tool output pruning."
+                  "description": "Enable bounded same-turn emergency planning and last-resort output pruning."
+                },
+                "hardContextPercent": {
+                  "type": "number",
+                  "description": "Context fraction that activates hard emergency pressure.",
+                  "minimum": 0,
+                  "maximum": 1
+                },
+                "targetContextPercent": {
+                  "type": "number",
+                  "description": "Context fraction the emergency path attempts to recover toward.",
+                  "minimum": 0,
+                  "maximum": 1
                 },
-                "maxOutputTokens": {
+                "patience": {
                   "type": "number",
-                  "description": "Maximum output tokens before truncation.",
+                  "description": "Completed emergency opportunities allowed before last-resort pruning.",
                   "minimum": 0
                 },
-                "keepRecentTurns": {
+                "keepRecentToolPairs": {
                   "type": "number",
-                  "description": "Recent turns to keep.",
+                  "description": "Newest complete tool-call/result pairs never selected by emergency cleanup.",
                   "minimum": 0
                 },
-                "readLikeTools": {
-                  "type": "array",
-                  "items": {
-                    "type": "string"
-                  },
-                  "description": "Tools treated as read-like (aggressively pruned)."
+                "minOutputTokens": {
+                  "type": "number",
+                  "description": "Minimum tool-result size eligible for emergency pruning.",
+                  "minimum": 0
                 },
-                "readLikeTurns": {
+                "maxSuggestions": {
                   "type": "number",
-                  "description": "Turns threshold for read-like tool pruning.",
+                  "description": "Maximum emergency message candidates shown in a reminder.",
                   "minimum": 0
                 },
                 "protectedTools": {
@@ -438,13 +432,13 @@
                   "items": {
                     "type": "string"
                   },
-                  "description": "Tool outputs protected from auto-pruning."
+                  "description": "Additional tools protected from emergency pruning and manual sweep."
                 }
               },
-              "description": "Auto tool pruning strategy configuration."
+              "description": "Single bounded emergency cleanup strategy."
             }
           },
-          "description": "DCP pruning strategies."
+          "description": "Bounded DCP emergency strategy."
         },
         "protectedFilePatterns": {
           "type": "array",
@@ -452,23 +446,6 @@
             "type": "string"
           },
           "description": "File path glob patterns whose content is protected from pruning."
-        },
-        "pruneNotification": {
-          "anyOf": [
-            {
-              "type": "string",
-              "const": "off"
-            },
-            {
-              "type": "string",
-              "const": "minimal"
-            },
-            {
-              "type": "string",
-              "const": "detailed"
-            }
-          ],
-          "description": "Notification level when pruning occurs."
         }
       },
       "description": "DCP (Dynamic Context Pruning) configuration."
@@ -478,14 +455,14 @@
       "properties": {
         "defaultType": {
           "type": "string",
-          "description": "Default sub-agent type when not specified."
+          "description": "Preferred role for genuinely ambiguous router tasks and legacy resolver default. Not used as a spawn fallback for missing/invalid routes."
         },
         "routing": {
           "type": "object",
           "properties": {
             "enabled": {
               "type": "boolean",
-              "description": "Enable LLM-based automatic role routing."
+              "description": "Enable fallback LLM selection for omitted subagentType values. Explicit valid types bypass the router; when disabled, every spawn task must specify a valid type."
             },
             "model": {
               "type": "string",
@@ -524,7 +501,7 @@
               "description": "Show routing debug warnings."
             }
           },
-          "description": "LLM-based role routing configuration."
+          "description": "Fallback role routing for omitted types. Unknown explicit types or failed/incomplete routing reject the entire batch before any agents launch."
         },
         "vision": {
           "type": "object",
@@ -549,16 +526,27 @@
                   "type": "string",
                   "description": "Preset description."
                 },
+                "models": {
+                  "type": "array",
+                  "items": {
+                    "type": "string",
+                    "pattern": "^[^\\s/*]+/[^\\s*]+$"
+                  },
+                  "uniqueItems": true,
+                  "description": "Available model pool. Filter the agent's ordered models by membership; pool order is ignored. Empty intersection rejects spawn. Oracle also respects this pool."
+                },
                 "model": {
                   "type": "string",
-                  "description": "Default model for this preset."
+                  "description": "Legacy default model. Ignored when models is set.",
+                  "deprecated": true
                 },
                 "fallbackModels": {
                   "type": "array",
                   "items": {
                     "type": "string"
                   },
-                  "description": "Global fallback models for this preset."
+                  "description": "Legacy fallback list. Ignored when models is set.",
+                  "deprecated": true
                 },
                 "thinking": {
                   "type": "string",
@@ -616,7 +604,7 @@
                   "description": "Per-type overrides."
                 }
               },
-              "description": "Named spawn preset."
+              "description": "Named available-model pool. Legacy model/types overrides remain supported; prefer models for new presets."
             }
           },
           "description": "Named spawn presets."
@@ -631,16 +619,31 @@
                   "type": "string",
                   "description": "Role description for routing."
                 },
+                "icon": {
+                  "type": "string",
+                  "description": "Agent icon name rendered by UIs (pix TUI icon themes and Pix Desktop lucide icons): agent, search, code, flask, globe, sparkles, brain, wrench, terminal, bug, book, eye, zap, rocket. Unknown names render as the neutral agent icon."
+                },
+                "models": {
+                  "type": "array",
+                  "items": {
+                    "type": "string",
+                    "pattern": "^[^\\s/*]+/[^\\s*]+$"
+                  },
+                  "uniqueItems": true,
+                  "description": "Ordered model candidates. First usable member of the preset pool runs; only remaining compatible members can be used on quota failure. Replaces legacy model/fallbackModels/modelByParent selection."
+                },
                 "model": {
                   "type": "string",
-                  "description": "Model for this sub-agent type."
+                  "description": "Legacy primary model; use models for new profiles.",
+                  "deprecated": true
                 },
                 "fallbackModels": {
                   "type": "array",
                   "items": {
                     "type": "string"
                   },
-                  "description": "Ordered model fallbacks."
+                  "description": "Legacy candidates after model; use models for a complete ranked list.",
+                  "deprecated": true
                 },
                 "thinking": {
                   "type": "string",
@@ -890,6 +893,84 @@
       },
       "description": "Settings for the opt-in credential-firewall module."
     },
+    "contextGateway": {
+      "type": "object",
+      "properties": {
+        "mode": {
+          "anyOf": [
+            {
+              "type": "string",
+              "const": "off"
+            },
+            {
+              "type": "string",
+              "const": "observe"
+            },
+            {
+              "type": "string",
+              "const": "enforce"
+            }
+          ],
+          "description": "Context Gateway mode. P01 implements off/observe; enforce is parsed but explicitly refused until later integration gates."
+        },
+        "budgets": {
+          "type": "object",
+          "properties": {
+            "maxInlineBytes": {
+              "type": "integer",
+              "minimum": 1,
+              "maximum": 67108864,
+              "description": "Initial inline byte budget used by Context Gateway policy experiments. Default 8192."
+            },
+            "maxResultBytes": {
+              "type": "integer",
+              "minimum": 1,
+              "maximum": 67108864,
+              "description": "Experimental delivered-result byte budget. P01 observe measures the available tool-result content boundary; later shaping must account for the final provider-visible serialization. Default 8192."
+            },
+            "maxExactReadBytes": {
+              "type": "integer",
+              "minimum": 1,
+              "maximum": 67108864,
+              "description": "Future exact-read byte budget. Default 32768."
+            },
+            "maxSearchBytes": {
+              "type": "integer",
+              "minimum": 1,
+              "maximum": 67108864,
+              "description": "Future search-delivery byte budget. Default 8192."
+            },
+            "maxSearchMatches": {
+              "type": "integer",
+              "minimum": 1,
+              "maximum": 1000,
+              "description": "Future search match budget. Default 12."
+            }
+          },
+          "description": "Context Gateway delivery budgets. In P01 only maxResultBytes is used for passive observe accounting."
+        }
+      },
+      "description": "Context Gateway configuration. Default mode is off."
+    },
+    "repoDiscovery": {
+      "type": "object",
+      "properties": {
+        "profile": {
+          "anyOf": [
+            {
+              "type": "string",
+              "const": "baseline"
+            },
+            {
+              "type": "string",
+              "const": "native-compact"
+            }
+          ],
+          "description": "repo_* runtime profile. baseline preserves historical argv/defaults; native-compact enables bounded native flags, cursors, validation, and an explicit per-call full override."
+        }
+      },
+      "description": "Repository discovery runtime policy. Default profile is baseline."
+    },
     "lsp": {
       "type": "object",
       "properties": {

package/external/pi-tools-suite/src/async-subagents/private-skills/browser-qa/references/auth-scaffold-spec.md

@@ -1,78 +0,0 @@
-# Spec: Browser QA form-auth scaffold
-
-## Type
-
-Change
-
-## Goal
-
-Let the browser-QA sub-agent prepare a target-specific form-auth configuration
-without reading, writing, receiving, or printing credential values. The user
-should only need to replace clearly marked secret placeholders.
-
-## Scope
-
-- Add a trusted runner command that inspects a public login form.
-- Generate `.pi/qa_auth.jsonc` with discovered field and submit selectors.
-- Keep generated values as non-secret placeholders until the user edits them.
-- Preserve the rule that agents never read or edit `.pi/qa_auth.jsonc`.
-
-## Non-goals
-
-- Collecting credentials interactively through the agent.
-- Guessing cookie, token, storage-state, MFA, or federated-login credentials.
-- Modifying an existing non-empty auth configuration.
-
-## Behavior
-
-- `auth scaffold` requires a project-local browser-QA sub-agent workspace, an
-  HTTPS login URL (or loopback HTTP for local development), and a safe profile
-  id.
-- The trusted runner opens the unauthenticated login page with fail-closed
-  origin routing and discovers the most likely login form, fillable fields,
-  submit control, and form container.
-- It writes a private `0600` `.pi/qa_auth.jsonc` containing only generated
-  selectors and `__PI_QA_SECRET_n__` placeholders. It may replace the runner's
-  empty generated template, but never a non-empty profiles object.
-- By default, successful login means that the discovered form becomes hidden.
-  A form-less page requires an explicit success URL pattern or selector/state.
-- A run cannot use a profile while generated placeholders remain. The runner
-  returns `QA_AUTH_UPDATE_REQUIRED` without exposing selectors or values.
-
-## Invariants
-
-- No credential value is accepted through command arguments or environment
-  variables.
-- Scaffold status output contains only path, profile id, counts, and action.
-- The command never prints inspected DOM text, input values, URLs, or selectors.
-- Agents continue to treat `.pi/qa_auth.jsonc` as opaque and user-owned.
-
-## Edge cases
-
-- Reject pages without a discoverable fillable field or submit control, and
-  form-less pages without an explicit success condition.
-- Reject remote plain-HTTP login pages.
-- Reject cross-origin base URLs and malformed success options.
-- Reject symlinked or permissive auth paths.
-- Refuse to overwrite invalid or non-empty auth configuration.
-
-## Related files
-
-- `scripts/browser-qa-runner.mjs`
-- `../SKILL.md`
-- `../../../../../test/async-subagents/browser-qa-runner.test.ts`
-
-## Verification
-
-- Unit tests for discovery output, placeholder blocking, private permissions,
-  empty-template replacement, and non-empty-config refusal.
-- Existing browser-QA runner tests and repository checks continue to pass.
-
-## Evidence
-
-- Confirmed by code: current runner owns Playwright, origin isolation, private
-  auth-file creation, validation, and redacted status output.
-- Confirmed by tests: current runner rejects permissive/symlinked auth files and
-  creates its empty template with private permissions.
-- Confirmed by docs: the private skill forbids agents from reading or editing
-  `.pi/qa_auth.jsonc`.

package/external/pi-tools-suite/src/async-subagents/private-skills/browser-qa/references/qa-design.md

@@ -1,223 +0,0 @@
-# Designing deterministic browser QA flows
-
-Use this reference with the bundled declarative runner. It intentionally does
-not describe a separate browser CLI or executable Playwright scripts.
-
-## Build the proof before the steps
-
-Write down three things first:
-
-1. **Setup:** the page and state needed to expose the behavior.
-2. **Action:** the smallest user interaction that exercises it.
-3. **Oracle:** the observable state that proves success or reproduces failure.
-
-Good oracles are product-visible and specific: an exact URL, a stable status
-message, a field value, item count, enabled/disabled state, or checked state.
-Avoid treating “the click did not throw” or “the screenshot looks plausible” as
-proof.
-
-When verifying a fix, prefer a focused regression flow over a broad tour of the
-application. If multiple independent states matter, assert each one explicitly.
-
-For explicit exploratory/manual QA, keep exploration bounded rather than turning
-it into an open-ended crawl. Run at most three minimal rounds. Each round should
-start from one concrete hypothesis, produce a deterministic observation plus a
-meaningful screenshot, and use that evidence to decide whether another round is
-justified. Verification tasks remain one browser run per profile.
-
-## Choose resilient locators
-
-Prefer locators that match how users and accessibility APIs identify controls:
-
-1. `testId` when the product exposes a stable test contract.
-2. `role` with accessible `name` for buttons, links, headings, dialogs, and
-   similar semantic elements.
-3. `label` for form controls.
-4. `placeholder` or visible `text` when they are stable product copy.
-5. `css` only when no semantic contract exists.
-
-Use `exact: true` when duplicate or substring matches are possible. Avoid CSS
-that encodes DOM depth, generated classes, styling details, or element order.
-If a locator is ambiguous, inspect nearby source or rendered copy and choose a
-more specific product contract rather than adding arbitrary delays.
-
-## Wait for state, not time
-
-Runner interactions inherit Playwright auto-waiting. Usually an action followed
-by an assertion is enough. Use `waitFor` only when the next operation depends on
-a distinct attached/detached/visible/hidden transition.
-
-After navigation and visible interactions, the runner also waits for DOM
-readiness, tracks requests causally started by that action through a bounded
-readiness window, waits for common visible
-`aria-busy`/progress/loading/spinner/skeleton markers, and keeps a 500 ms stable
-interval. EventSource/WebSocket traffic is ignored, and a long poll is not
-allowed to pin the entire flow timeout. A visible busy indicator may still hold
-readiness until `timeoutMs`. This is a safe baseline, not an application-specific
-oracle: explicitly wait for a custom loader to become hidden and assert the
-loaded content when the application uses different readiness semantics.
-
-`waitForTimeout` is bounded to five seconds and should be exceptional—for a
-known animation, debounce, or externally scheduled transition with no
-observable intermediate state. Sleeping longer hides races instead of proving
-behavior. If a normal operation legitimately needs more time, adjust the flow's
-`timeoutMs` rather than inserting repeated sleeps.
-
-All assertion actions retry until that timeout. This makes an action followed
-directly by `assertText`, `assertVisible`, `assertURL`, or another assertion
-safe for asynchronously rendered outcomes. `assertText` requires the locator to
-be visible and matches rendered `innerText`; use `assertTextContent` only when
-hidden/raw DOM text is deliberately part of the oracle. Use `assertAttribute` for
-observable state such as `aria-expanded`, `aria-invalid`, or `data-state`
-instead of reading DOM state through executable JavaScript.
-
-## Responsive and scrolling scenarios
-
-Set the flow's top-level `viewport` whenever the bug depends on a breakpoint or
-available height. Assert `viewportWidth` or `viewportHeight` with
-`assertDOMMetric` when the dimensions themselves are part of the proof; the
-runner also includes the applied viewport in its result.
-
-Use `wheel` to reproduce real pointer-wheel input. Add a locator when the wheel
-must target a nested scrolling container—the runner hovers it before sending
-the input. Because browser scrolling may be scheduled after the wheel event,
-wait only for a short known settling interval when a direct metric assertion is
-otherwise racy.
-
-Use safe `evaluate` `scrollTo`/`scrollBy` operations for deterministic setup or
-to distinguish input handling from layout behavior. Use the `metrics` operation
-to retain a named page/element snapshot in result `observations`, and use
-`assertDOMMetric` for pass/fail. Raw JavaScript expressions are intentionally
-excluded: flows remain declarative and cannot inspect authentication storage or
-execute arbitrary same-origin requests.
-
-## Deterministic browser environment
-
-Set top-level `environment` when locale, timezone, color scheme, or motion
-preferences can change the behavior. The runner otherwise uses stable defaults
-(`en-US`, `UTC`, `light`, `reduce`) instead of inheriting host settings. Prefer
-asserting product-visible copy or state derived from those settings; do not use
-screenshot pixels as the only oracle.
-
-## Causal network and dialog expectations
-
-Put `expectResponse` or `expectDialog` on the interaction that causes the event.
-The runner arms both listeners before the interaction, avoiding the race in a
-separate “click, then wait” sequence. Response expectations deliberately match
-only an exact allowlisted-origin pathname, HTTP method, and status. This proves
-that a matching request started and received a response within the action
-window without retaining its URL query, headers, or body.
-
-Dialog expectations match a fixed dialog type and exact/included message, then
-accept or dismiss it declaratively. A mismatch is dismissed before the step
-fails so the page cannot freeze. Actual event metadata is never included in
-failure diagnostics. Do not place secrets in expected messages or response
-paths even though the runner keeps diagnostics generic.
-
-## Drag, upload, and download scenarios
-
-Use `dragTo` for native DOM drag/drop and assert the resulting product state.
-Optional source/drop positions are relative bounded coordinates. Canvas-only,
-OS-native, or custom synthetic-event drag protocols remain unsupported; do not
-work around that with executable JavaScript.
-
-Uploads are memory-only base64 payloads declared in the flow. This intentionally
-prevents a flow from selecting arbitrary project files, credential config, or
-directories. Keep fixtures minimal and non-secret. An empty file list clears a
-file input.
-
-Use the atomic `download` action rather than clicking a download link directly.
-Always match the suggested filename and choose a tight `maxBytes`. Retain a
-download only when its contents are needed as evidence; otherwise the runner
-deletes it after validation. Retained downloads use generated private names,
-not server-provided paths, and are scanned for configured authentication before
-publication. `maxBytes` bounds the runner's private evidence copy and triggers
-cancellation while it grows, but it is not a network-bandwidth guarantee: the
-browser can receive temporary bytes before cancellation.
-
-## Same-origin frames and popups
-
-Use a scoped `target` for iframe or named popup interactions. The runner checks
-the live frame origin before every scoped step and checks a popup after it loads;
-both must remain in `allowedOrigins`. This supports embedded application UI and
-same-origin auxiliary windows without opening a route around the network guard.
-Cross-origin login, payment, and third-party widgets remain intentionally out of
-scope. Each popup adds a separate private video artifact, so open only the
-windows needed for the proof.
-
-## Authentication transitions
-
-Add `authRejectedIf` directly after initial navigation and after transitions
-that can redirect to login or display an expired-session marker. This converts
-stale credentials into an explicit update request instead of misreporting a
-product regression.
-
-Do not encode credentials, tokens, storage values, or login form secrets in the
-flow. The trusted runner applies the selected profile internally. For form auth,
-video starts on the login page and includes field filling and submission; password
-inputs remain masked, but visible identifiers can appear, so treat the video as
-sensitive private evidence. Tracing starts only after login succeeds and is
-sanitized before retention.
-
-## Evidence strategy
-
-The runner always attempts a final or failure screenshot, records video from the
-first page, and creates a sanitized post-auth trace. Add named `screenshot`
-steps only at states that materially help explain the result—for example before
-and after a destructive interaction, or when a transient success message is
-the oracle.
-
-Use evidence by purpose:
-
-- **Screenshot:** quick review of one meaningful visual state.
-- **Video:** chronological confirmation of the complete user flow.
-- **Trace:** action/DOM timing diagnosis for a failed or flaky interaction.
-
-Videos automatically show a transient cursor and yellow pulse for clicks and
-double-clicks. After a native `dragTo` gesture completes, its resolved
-source-to-target route is replayed over 450 ms with a large orange cursor and
-progressively drawn high-contrast trail, followed by a green drop marker. These
-annotations are
-runner-owned, pointer-transparent, and accessibility-hidden; they cover the main
-page, same-origin frames, declared popups, and form-auth submission. Their
-bounded animations finish within the normal post-action stable interval, so
-they explain the chronology without becoming screenshot or assertion oracles.
-
-Assertions determine pass/fail; evidence explains it. Preserve and link every
-artifact group returned on both passed and failed runs.
-
-For visual QA, do not stop at artifact generation. Open at least one meaningful
-PNG with the model's image-capable `read` path and inspect layout, clipping,
-overlap, state styling, and other visual defects relevant to the scenario. If
-the active model cannot read images, explicitly report visual inspection as
-unavailable rather than treating deterministic assertions as a visual pass.
-
-## Diagnose failures without weakening the test
-
-Classify the first failing step:
-
-- wrong target/setup or service unavailable;
-- authentication rejected or expired;
-- locator no longer matches the product contract;
-- expected state never appeared;
-- actual product behavior contradicts the expectation.
-
-Fix the flow only when its setup or locator is wrong. Do not replace a precise
-assertion with a vague one, increase timeouts reflexively, or remove the failing
-step to manufacture a pass. Keep the failure artifacts and state the expected
-versus observed behavior.
-
-## Cleanup and isolation
-
-Each runner invocation owns one isolated context and evidence directory and
-closes its browser resources in a `finally` path. Do not create parallel shared
-or default sessions outside the runner. Test multiple auth profiles with
-separate invocations so cookies, storage, traces, and evidence cannot mix.
-
-Keep the declarative flow and every generated screenshot, video, trace, and
-result manifest inside `$PI_SUBAGENT_AGENT_DIR/browser-qa/`. The launcher owns
-that path and the runner validates it before opening a browser. Do not override
-the environment path or copy evidence into shared `.pi/qa-runs`/`.pi/qa-flows`
-directories: the agent-local workspace is intentionally removed by the normal
-sub-agent shutdown and cleanup lifecycle. Authentication config remains a
-separate persistent input under project `.pi/`.