@qvac/harness 0.2.8 → 0.2.10

package/dist-lib/spec/hyperschema/index.js

@@ -1,12 +1,12 @@
 // This file is autogenerated by the hyperschema compiler
-// Schema Version: 8
+// Schema Version: 10
 /* eslint-disable camelcase */
 /* eslint-disable quotes */
 /* eslint-disable space-before-function-paren */
 
 import { c } from 'hyperschema/runtime'
 
-const VERSION = 8
+const VERSION = 10
 
 // eslint-disable-next-line no-unused-vars
 let version = VERSION
@@ -143,7 +143,8 @@ const encoding4 = {
       (m.imageWidth ? 8192 : 0) |
       (m.imageHeight ? 16384 : 0) |
       ((version >= 5 && m.approvalMode) ? 32768 : 0) |
-      ((version >= 5 && m.disabledToolsets) ? 65536 : 0)
+      ((version >= 5 && m.disabledToolsets) ? 65536 : 0) |
+      ((version >= 10 && m.sandboxMode) ? 131072 : 0)
 
     c.uint.preencode(state, flags)
 
@@ -183,7 +184,8 @@ const encoding4 = {
       (m.imageWidth ? 8192 : 0) |
       (m.imageHeight ? 16384 : 0) |
       ((version >= 5 && m.approvalMode) ? 32768 : 0) |
-      ((version >= 5 && m.disabledToolsets) ? 65536 : 0)
+      ((version >= 5 && m.disabledToolsets) ? 65536 : 0) |
+      ((version >= 10 && m.sandboxMode) ? 131072 : 0)
 
     c.uint.encode(state, flags)
 
@@ -225,7 +227,8 @@ const encoding4 = {
       imageWidth: (flags & 8192) !== 0 ? c.uint.decode(state) : 0,
       imageHeight: (flags & 16384) !== 0 ? c.uint.decode(state) : 0,
       approvalMode: (version >= 5 && (flags & 32768) !== 0) ? encoding59.decode(state) : null,
-      disabledToolsets: (version >= 5 && (flags & 65536) !== 0) ? encoding4_16.decode(state) : null
+      disabledToolsets: (version >= 5 && (flags & 65536) !== 0) ? encoding4_16.decode(state) : null,
+      sandboxMode: (version >= 10 && (flags & 131072) !== 0)
     }
   }
 }
@@ -478,7 +481,8 @@ const encoding11 = {
       ((version >= 5 && m.grantedDirs) ? 2097152 : 0) |
       ((version >= 5 && m.grantedDrives) ? 4194304 : 0) |
       ((version >= 5 && m.payload) ? 8388608 : 0) |
-      ((version >= 5 && m.grantedWriteDirs) ? 16777216 : 0)
+      ((version >= 5 && m.grantedWriteDirs) ? 16777216 : 0) |
+      ((version >= 9 && m.captureInferenceCalls) ? 33554432 : 0)
 
     encoding10.preencode(state, m.type)
     c.uint.preencode(state, flags)
@@ -533,7 +537,8 @@ const encoding11 = {
       ((version >= 5 && m.grantedDirs) ? 2097152 : 0) |
       ((version >= 5 && m.grantedDrives) ? 4194304 : 0) |
       ((version >= 5 && m.payload) ? 8388608 : 0) |
-      ((version >= 5 && m.grantedWriteDirs) ? 16777216 : 0)
+      ((version >= 5 && m.grantedWriteDirs) ? 16777216 : 0) |
+      ((version >= 9 && m.captureInferenceCalls) ? 33554432 : 0)
 
     encoding10.encode(state, m.type)
     c.uint.encode(state, flags)
@@ -592,7 +597,8 @@ const encoding11 = {
       grantedDirs: (version >= 5 && (flags & 2097152) !== 0) ? encoding11_22.decode(state) : null,
       grantedDrives: (version >= 5 && (flags & 4194304) !== 0) ? encoding11_23.decode(state) : null,
       payload: (version >= 5 && (flags & 8388608) !== 0) ? c.json.decode(state) : null,
-      grantedWriteDirs: (version >= 5 && (flags & 16777216) !== 0) ? encoding11_25.decode(state) : null
+      grantedWriteDirs: (version >= 5 && (flags & 16777216) !== 0) ? encoding11_25.decode(state) : null,
+      captureInferenceCalls: (version >= 9 && (flags & 33554432) !== 0)
     }
   }
 }
@@ -613,13 +619,15 @@ const encoding12_enum = {
   "question-ask": 'question-ask',
   done: 'done',
   "tool-activity": 'tool-activity',
-  "drive-ask": 'drive-ask'
+  "drive-ask": 'drive-ask',
+  "inference-call": 'inference-call',
+  "inference-sent": 'inference-sent'
 }
 
 // @harness/completion-event-type enum
 const encoding12 = {
   preencode (state, m) {
-    state.end++ // max enum is 16 so always one byte
+    state.end++ // max enum is 18 so always one byte
   },
   encode (state, m) {
     switch (m) {
@@ -671,6 +679,12 @@ const encoding12 = {
       case 'drive-ask':
         c.uint.encode(state, 16)
         break
+      case 'inference-call':
+        c.uint.encode(state, 17)
+        break
+      case 'inference-sent':
+        c.uint.encode(state, 18)
+        break
       default:
         throw new Error('Unknown enum')
     }
@@ -709,6 +723,10 @@ const encoding12 = {
         return 'tool-activity'
       case 16:
         return 'drive-ask'
+      case 17:
+        return 'inference-call'
+      case 18:
+        return 'inference-sent'
       default: return null
     }
   }

package/dist-lib/spec/hyperschema/schema.json

@@ -1,5 +1,5 @@
 {
-  "version": 8,
+  "version": 10,
   "schema": [
     {
       "name": "empty",
@@ -151,6 +151,11 @@
           "array": true,
           "type": "string",
           "version": 5
+        },
+        {
+          "name": "sandboxMode",
+          "type": "bool",
+          "version": 10
         }
       ]
     },
@@ -446,6 +451,11 @@
           "array": true,
           "type": "string",
           "version": 5
+        },
+        {
+          "name": "captureInferenceCalls",
+          "type": "bool",
+          "version": 9
         }
       ]
     },
@@ -517,6 +527,14 @@
         {
           "key": "drive-ask",
           "version": 5
+        },
+        {
+          "key": "inference-call",
+          "version": 9
+        },
+        {
+          "key": "inference-sent",
+          "version": 9
         }
       ],
       "strings": true

package/dist-lib/spec/hyperschema/types.d.ts

@@ -1,5 +1,5 @@
 // This file is autogenerated by hyperschema-ts
-// Schema version: 8
+// Schema version: 10
 // Do not edit manually.
 
 export interface HarnessEmpty {
@@ -31,6 +31,7 @@ export interface HarnessAgentKnobs {
   imageHeight?: number
   approvalMode?: HarnessApprovalMode | null
   disabledToolsets?: string[] | null
+  sandboxMode?: boolean
 }
 
 export type HarnessMessageRole = "system" | "user" | "assistant" | "tool"
@@ -86,9 +87,10 @@ export interface HarnessCompletionFrame {
   grantedDrives?: HarnessGrantedDrive[] | null
   payload?: unknown | null
   grantedWriteDirs?: string[] | null
+  captureInferenceCalls?: boolean
 }
 
-export type HarnessCompletionEventType = "content" | "thinking" | "tool-call" | "tool-result" | "approval-ask" | "metrics" | "error" | "aborted" | "attach-ask" | "fetch-ask" | "progress" | "rag-ask" | "question-ask" | "done" | "tool-activity" | "drive-ask"
+export type HarnessCompletionEventType = "content" | "thinking" | "tool-call" | "tool-result" | "approval-ask" | "metrics" | "error" | "aborted" | "attach-ask" | "fetch-ask" | "progress" | "rag-ask" | "question-ask" | "done" | "tool-activity" | "drive-ask" | "inference-call" | "inference-sent"
 
 export interface HarnessCompletionEvent {
   type: HarnessCompletionEventType

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@qvac/harness",
-  "version": "0.2.8",
+  "version": "0.2.10",
   "type": "module",
   "description": "An AI harness implementing generate(context) via @qvac/sdk. Knows nothing about workbench, hyperdb, or chunks — just inference in, events out.",
   "exports": {
@@ -12,6 +12,10 @@
       "types": "./dist-lib/lib/docx/index.d.ts",
       "default": "./dist-lib/lib/docx/index.js"
     },
+    "./office": {
+      "types": "./dist-lib/lib/office/index.d.ts",
+      "default": "./dist-lib/lib/office/index.js"
+    },
     "./lib/dns-lookup.ts": {
       "types": "./dist-lib/lib/dns-lookup.d.ts",
       "default": "./dist-lib/lib/dns-lookup.js"
@@ -555,9 +559,8 @@
   },
   "scripts": {
     "build:schema": "bare schema/build.ts",
-    "test": "npm run vendor:wheels && npm run test:node && npm run test:bare && npm run test:addons",
-    "test:node": "QVAC_NO_SKILL_BIN_PROBE=1 brittle-node test/all.ts | prettytap",
-    "test:bare": "QVAC_NO_SKILL_BIN_PROBE=1 brittle-bare test/all.ts | prettytap",
+    "test": "npm run vendor:wheels && npm run test:bare && npm run test:addons",
+    "test:bare": "QVAC_NO_SKILL_BIN_PROBE=1 prettytap -- brittle-bare test/all.ts",
     "format": "prettier . --write",
     "lint": "prettier . --check && lunte && tsc --noEmit",
     "build:bundle": "node scripts/build-bundle.mjs",
@@ -714,7 +717,7 @@
     "lunte": "^1.8.3",
     "prettier": "^3.6.2",
     "prettier-config-holepunch": "^2.0.0",
-    "prettytap": "^0.1.3",
+    "prettytap": "^0.2.0",
     "terser": "^5.51.2",
     "typescript": "^7.0.2"
   },
@@ -724,7 +727,8 @@
     "localwatch@1.4.3": "patches/localwatch@1.4.3.patch",
     "hypercore-blob-server@1.15.0": "patches/hypercore-blob-server@1.15.0.patch",
     "bare-stow@0.1.5": "patches/bare-stow@0.1.5.patch",
-    "@qvac/inference@0.19.0": "patches/@qvac%2Finference@0.19.0.patch"
+    "@qvac/inference@0.19.0": "patches/@qvac%2Finference@0.19.0.patch",
+    "brittle@4.1.0": "patches/brittle@4.1.0.patch"
   },
   "repository": {
     "type": "git",

package/.claude/skills/asana/SKILL.md

@@ -1,86 +0,0 @@
----
-name: asana
-description: Conventions for the QVAC Assistant Asana board when working through the Asana MCP server — what the MCP cannot do and what that silently breaks, the Context field that decides whether a task is visible at all, and the rule against consuming task descriptions. Use before creating, moving, or reading any Asana task for this project.
----
-
-# Asana — QVAC Assistant board
-
-Asana work here goes through the **Asana MCP server**. This skill is not a tool;
-it is the handful of things the MCP does not tell you and will not stop you
-getting wrong.
-
-- Workspace `45238840754660` (tether.to)
-- Project `1214754188814246` (QVAC Assistant)
-- Board: <https://app.asana.com/1/45238840754660/project/1214754188814246>
-
-## Do not create tasks through the MCP
-
-`asana_create_task` takes `resource_subtype` of only `default_task`, `milestone`
-or `approval`, and neither it nor `asana_update_task` accepts `custom_type` or
-`custom_type_status_option`. This board runs on the **QVAC Basic Task** custom
-type (`1214533632534265`), whose status options _are_ the workflow — the project
-has one real section and tracks status entirely through the custom type.
-
-So an MCP-created task is a plain default task that:
-
-- is not a `QVAC Basic Task`,
-- has no status (To Do / In Progress / In Code Review / Blocked /
-  Completed-Ready for QA / Fully Verified / Closed-Won't Fix), and
-- cannot be given one afterwards through the API.
-
-It lands on the board looking almost right and is undriveable. **Ask the user to
-create the task in the Asana UI**, where the custom type is the default, and then
-use the MCP to fill fields or comment on it. Do not create it yourself and
-promise to "fix the type later" — the API has no route to do that.
-
-Moving a task's status has the same limitation: the status lives on
-`custom_type_status_option`, which the MCP cannot set. Status changes are a UI
-action.
-
-## Context is mandatory, and the MCP will not warn you
-
-The project's Dev Board tabs are saved views filtered on the **Context** custom
-field. A task with Context unset appears only in "Full List" and "Overview" — it
-is invisible on every Dev Board tab and silently slips off the team's radar.
-
-Whenever you set fields on a task, set Context. Field `1214754188814251`:
-
-| Value          | GID                | For                                               |
-| -------------- | ------------------ | ------------------------------------------------- |
-| `harness`      | `1214754188814252` | engine, mesh and sync, storage, build and release |
-| `integrations` | `1214754188814253` | assistant runtime, agents, tools, skills          |
-| `other`        | `1214758268571416` | genuinely cross-cutting: org, legal, product docs |
-
-Surface which one you picked and why, and let the user correct it. Never guess
-silently, and never leave it blank to avoid choosing.
-
-## Release grouping
-
-Each Dev Board tab groups by **QVAC Workbench Release** (field
-`1214111405360914`) first. A task with none lands in an "Untitled" bucket at the
-bottom of every tab. Default to `tbc` (`1214757840453965`) when the release is
-undecided.
-
-**That field is the app's release, not a package version.** `@qvac/harness`,
-`@qvac/core` and `@qvac/skills` each ship their own `0.x` line; putting one of
-those numbers here files the task against a release that does not exist.
-
-## Never consume task descriptions
-
-Work from task metadata only: GID, name, permalink, completion state, assignee,
-memberships, custom fields, custom type and status, timestamps, and comments.
-
-- `asana_get_task` returns the description by default. Pass an explicit
-  `opt_fields` list that omits `notes`, `html_notes` and `description`.
-- Do not use Asana full-text search as a fallback — it matches descriptions.
-  Find tasks by the QVAC custom field (`1209150993228635`, text) or by GID.
-- If the user wants you to act on a description, ask them to paste the relevant
-  excerpt rather than fetching it.
-
-## Before any mutation
-
-Show the exact change and wait for a yes. That includes field edits, comments and
-completion — this board is shared with the whole team, and a comment cannot be
-unsent.
-
-Never put tokens, secrets or internal-only URLs in a task or comment.

package/.claude/skills/gh-stack/SKILL.md

@@ -1,181 +0,0 @@
----
-name: gh-stack
-description: >
-  Manages stacked PRs and splits multi-part work into reviewable branches with gh-stack.
-  Use for stack creation, viewing, edits, push, submit, sync, rebase, merge, or checkout;
-  when asked to split or isolate work for review; whenever a user mentions a stack,
-  branch layers, dependent PRs, or gh stack; or when a stack is checked out.
-metadata:
-  author: github
-  version: '0.1.0'
----
-
-# gh-stack
-
-`gh stack` is a [GitHub CLI](https://cli.github.com/) extension for stacked branches and pull
-requests. A stack is an ordered chain of branches rooted on a trunk, where each branch has one PR
-based on the branch below it, so a reviewer sees only that layer's diff.
-
-`gh stack` prints a stack trunk-first, left to right:
-
-```
-(main) <- auth <- api <- frontend
-```
-
-Left is the **bottom**, right is the **top**. `auth` is based on `main` and merges first;
-`frontend` merges last. `up` moves toward the top, away from trunk; `down` moves toward it.
-Foundational work belongs at the bottom, code that depends on it above. For how to choose the
-layers, read `references/stack-design.md`.
-
-## Setup
-
-```bash
-gh extension install github/gh-stack
-git config rerere.enabled true         # remember conflict resolutions
-git config remote.pushDefault origin   # required if the repo has more than one remote
-```
-
-## Non-interactive use
-
-`gh stack` branches on whether **stdout is a TTY**. Piped, most commands error cleanly or print
-static text; under a PTY the same commands open a prompt or a full-screen TUI and block forever.
-Agent harnesses differ, so always pass the flags below instead of relying on that detection.
-
-**Multiple remotes:** never run `push`, `submit`, `sync`, `rebase`, or `link` without
-`--remote <name>` unless `remote.pushDefault` is configured. `checkout` and `trunk` have no
-`--remote` flag and require the config.
-
-| Always run                                | Never run bare      | Why                                           |
-| ----------------------------------------- | ------------------- | --------------------------------------------- |
-| `gh stack view --json`                    | `gh stack view`     | opens a TUI under a PTY                       |
-| `gh stack submit --auto`                  | `gh stack submit`   | prompts for a title per new PR                |
-| `gh stack merge <target> --yes`           | `gh pr merge`       | `gh pr merge` cannot merge a stack            |
-| `gh stack init <branch>...`               | `gh stack init`     | prompts for branch names                      |
-| `gh stack add <branch>`                   | `gh stack add`      | prompts for a name, and fails even when piped |
-| `gh stack checkout <target>`              | `gh stack checkout` | opens a selection menu                        |
-| `gh stack up` / `down` / `top` / `bottom` | `gh stack switch`   | `switch` is menu-only                         |
-| —                                         | `gh stack modify`   | TUI-only, no non-interactive path             |
-
-- `view --short` is safe in both modes, but it is formatted for humans. Use `--json` to parse.
-- **`checkout <pr>` when a different local stack already covers those branches** cannot be forced.
-  Run `gh stack unstack --local` first (this keeps the stack on GitHub), then retry.
-
-## Branch placement
-
-- **Starting multi-part work:** create the stack before writing files. Do not implement every
-  concern on trunk and split it later. Put one dependent concern in each layer, bottom to top.
-- **Editing an existing stack:** check out the layer that owns the change before editing. Never
-  commit a lower layer's concern on the current top branch. Run `gh stack view --json`; if
-  ownership is unclear, inspect `git log --all -- <path>`. Then check out the owner, edit, commit,
-  rebase upstack, and return to top.
-
-```bash
-gh stack down                   # or: gh stack checkout api
-git add ... && git commit -m "Add get-user endpoint"
-gh stack rebase --upstack       # replay every branch above onto the change
-gh stack top                    # return to where you were
-gh stack push
-```
-
-## Core loop
-
-```bash
-gh stack init auth              # create the stack and check out its branch
-git add ... && git commit -m "Add auth middleware"
-gh stack add api                # next layer, branched from the current one
-git add ... && git commit -m "Add API routes"
-gh stack submit --auto          # push every branch and open draft PRs
-gh stack view --json            # confirm
-```
-
-Add `--open` to `submit` to create PRs ready for review instead of drafts. Branch names are
-verbatim — `gh stack add refactor/foo` creates `refactor/foo`.
-
-## Staying in sync
-
-```bash
-gh stack sync                   # fetch, reconcile with GitHub, rebase, push, refresh PR state
-gh stack sync --prune           # also delete local branches for merged PRs
-```
-
-Pruning never happens without `--prune` when non-interactive. If the local and remote stacks have
-diverged, `sync` prints both chains, makes no changes, and exits 0 with `Sync aborted` — see
-`references/troubleshooting.md`.
-
-## Merging
-
-Scope the merge with an argument:
-
-```bash
-gh stack merge 42 --yes          # PR #42 plus every unmerged PR below it
-gh stack merge 7 --yes           # every unmerged PR in stack #7
-gh stack merge 42 --yes --squash # or --merge, --rebase, --merge-method <method>
-```
-
-Pass a PR number to merge that PR and every unmerged PR below it, or a stack number to merge every
-unmerged PR in that stack. The operation is all-or-nothing: if any PR in that set cannot merge,
-none do.
-
-Without a method flag the last-used method is reused. If the base branch uses a merge queue, the
-stack is queued instead and the queue picks the method, ignoring any flag you passed with a
-warning; queued PRs may land in separate groups.
-
-## Reading state
-
-`gh stack view --json` writes JSON to **stdout**. Status messages go to **stderr** — do not parse
-them, branch on exit codes instead.
-
-```
-trunk           string
-currentBranch   string
-branches[]      name, head, base, isCurrent, isMerged, isQueued, needsRebase
-branches[].pr   number, url, state ("OPEN" | "MERGED" | "QUEUED"); absent when no PR exists
-```
-
-`base` is the saved SHA of the parent branch that this branch was last known to contain. It may be
-older than the parent's current tip. `needsRebase` is true when the current parent tip is no longer
-an ancestor of the branch.
-
-## Exit codes
-
-| Code | Meaning                    | Recovery                                                   |
-| ---- | -------------------------- | ---------------------------------------------------------- |
-| 0    | Success                    | —                                                          |
-| 1    | Generic error              | Read stderr                                                |
-| 2    | Not in a stack             | `gh stack init`, or `gh stack checkout <target>`           |
-| 3    | Rebase conflict            | Follow the Exit 3 recovery below                           |
-| 4    | GitHub API failure         | Check `gh auth status`, retry                              |
-| 5    | Invalid arguments          | Fix the invocation; see `<command> --help`                 |
-| 6    | Disambiguation required    | Branch is in several stacks; check out a non-shared branch |
-| 7    | Rebase already in progress | `gh stack rebase --continue` or `--abort`                  |
-| 8    | Stack file locked          | Another `gh stack` process is writing; retry after ~5s     |
-| 9    | Stacked PRs unavailable    | Not enabled on the repository; tell the user               |
-| 10   | Modify recovery required   | `gh stack modify --abort`                                  |
-
-**Exit 3 recovery:**
-
-- After `gh stack rebase`: resolve the files, run `git add`, then
-  `gh stack rebase --continue`; use `gh stack rebase --abort` to restore the stack.
-- After `gh stack sync`: the stack has already been restored. Run `gh stack rebase` to recreate the
-  conflict, then resolve and continue as above.
-
-## Constraints
-
-- Stacks are strictly linear: one parent, at most one child. Use separate stacks for parallel work.
-- There is no non-interactive reorder or removal. Errors may suggest `gh stack modify`, but it is
-  TUI-only — restructure with `unstack` then `init` instead.
-- PR titles and bodies are auto-generated. Use `gh pr edit` afterwards to change them.
-
-## More detail
-
-`gh stack <command> --help` is authoritative for flags and arguments. Note that
-`gh stack help <command>` does **not** work — it prints the top-level help.
-
-Open the reference whose trigger matches the task; no need to preload all three.
-
-- `references/stack-design.md` — read before creating a stack, when deciding how many layers to
-  use, what belongs in each one, or whether work belongs in a new stack.
-- `references/commands.md` — read when a command fails unexpectedly or you need its preconditions,
-  side effects, atomicity, or ordering guarantees.
-- `references/troubleshooting.md` — read on a rebase conflict, after a squash-merge, on local and
-  remote divergence, when restructuring a stack, or when driving stacks from another tool.