Merge remote-tracking branch 'origin/master' into chore/import-landlock-run

Conflict: doc-budgets manifest — master raised the AGENTS.md ceiling to 1600
(superseding this branch's 1377 bump for the native/ line), take master's
values.

.github/workflows/build-exe-for-python-sdk.yml

@@ -1,7 +1,7 @@
 name: Build single-exe
 
 # Native builds for the release targets; see
-# docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md.
+# .agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md.
 # A full target run retains one SDK wheel and three runtime wheels; subset
 # dispatch retains the SDK wheel and selected runtime wheels. Bare executables
 # and source closures are test inputs. Run manually or label a PR

.github/workflows/e2e.yml

@@ -23,7 +23,7 @@ name: E2E (real DeepSeek API)
 # in the BASE repo's context WITH secrets while still able to check out untrusted
 # fork code — a textbook key-leak vector, especially once this repo is public.
 # The fork/secret model and its public-repo implications are recorded in
-# docs/rfc/implemented/testing/2026-06-19-real-api-e2e-ci.md.
+# .agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.md.
 #
 # Note: scheduled triggers are auto-disabled after 60 days of repo inactivity;
 # push/pull_request/workflow_dispatch act as backstops.
@@ -110,9 +110,14 @@ jobs:
           fi
           echo "DEEPSEEK_API_KEY present."
 
+      # The e2e suites boot the example bins in `lib` mode (DSH_EXAMPLE_MODE=lib):
+      # the built artifact under plain Node, resolving plugins through real package
+      # exports — the shape a real consumer runs. That requires a prior build.
+      - name: Build (lib for the e2e example bins)
+        run: pnpm run build
+
       # Real-API end-to-end tests only. The keyless gates (lint/typecheck/
-      # coverage/snapshot/build/etc.) already run in ci.yml on every push/PR;
-      # no need to repeat them or build first (tests run unbuilt via tsx).
+      # coverage/snapshot/etc.) already run in ci.yml on every push/PR.
       # DEEPSEEK_BASE_URL is pinned to the external API; the secret is scoped to
       # this step (and preflight) only — never exposed to checkout/setup/install.
       - name: E2E tests (real DeepSeek API)
@@ -120,4 +125,5 @@ jobs:
           DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY_EXTERNAL }}
           DEEPSEEK_BASE_URL: https://api.deepseek.com
           DSH_E2E_MAX_WORKERS: 14
+          DSH_EXAMPLE_MODE: lib
         run: pnpm run test:e2e

.github/workflows/expected-filenames.yml

@@ -0,0 +1,21 @@
+name: Expected filenames
+
+on:
+  pull_request:
+    paths:
+      - '*[gG][oO][lL][dD][eE][nN]*'
+      - '**/*[gG][oO][lL][dD][eE][nN]*'
+      - '!vendor/**'
+
+permissions:
+  contents: read
+
+jobs:
+  expected-filenames:
+    name: no golden filenames
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Check tracked filenames
+        run: scripts/check-expected-filenames.sh

.github/workflows/pi-ai-provider-e2e.yml

@@ -0,0 +1,78 @@
+name: E2E (pi-ai Azure OpenAI and Anthropic)
+
+# This suite spends tokens against two external providers and is intentionally
+# opt-in. It has no push, pull_request, schedule, or workflow_call trigger.
+on:
+  workflow_dispatch:
+    inputs:
+      azure_openai_model:
+        description: Azure OpenAI model from pi-ai's installed catalog
+        required: true
+        default: gpt-5.5
+        type: string
+      anthropic_model:
+        description: Anthropic model from pi-ai's installed catalog
+        required: true
+        default: claude-opus-4-8
+        type: string
+
+permissions:
+  contents: read
+
+jobs:
+  e2e:
+    runs-on: ubuntu-latest
+    name: Azure OpenAI Responses + Anthropic Messages
+    timeout-minutes: 20
+    steps:
+      - uses: actions/checkout@v6
+
+      - uses: actions/setup-node@v6
+        with:
+          node-version: 24
+
+      - name: Enable corepack (pnpm)
+        run: corepack enable
+
+      - name: Resolve pnpm store path
+        id: pnpm-store
+        run: echo "path=$(pnpm store path --silent)" >> "$GITHUB_OUTPUT"
+
+      - uses: actions/cache@v4
+        with:
+          path: ${{ steps.pnpm-store.outputs.path }}
+          key: ${{ runner.os }}-node-24-pnpm-${{ hashFiles('pnpm-lock.yaml') }}
+          restore-keys: |
+            ${{ runner.os }}-node-24-pnpm-
+
+      - name: Install (immutable)
+        run: pnpm install --frozen-lockfile
+
+      # The tests self-skip locally when a credential is absent. A manually
+      # dispatched CI run must fail instead of reporting an all-skipped green.
+      - name: Preflight (require provider API keys)
+        env:
+          AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY_EXTERNAL }}
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY_EXTERNAL }}
+        run: |
+          set -euo pipefail
+          missing=0
+          for name in AZURE_OPENAI_API_KEY ANTHROPIC_API_KEY; do
+            if [ -z "${!name:-}" ]; then
+              echo "::error::${name} is empty. Configure the corresponding *_EXTERNAL repository secret."
+              missing=1
+            fi
+          done
+          exit "$missing"
+
+      - name: E2E tests (real Azure OpenAI and Anthropic APIs)
+        env:
+          AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY_EXTERNAL }}
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY_EXTERNAL }}
+          DSH_PI_AI_OPENAI_MODEL: ${{ inputs.azure_openai_model }}
+          DSH_PI_AI_OPENAI_BASE_URL: https://openai-routerhub-resource.services.ai.azure.com/api/projects/openai/openai/v1
+          DSH_PI_AI_ANTHROPIC_MODEL: ${{ inputs.anthropic_model }}
+          DSH_E2E_MAX_WORKERS: 2
+        run: >-
+          pnpm exec vitest run --config vitest.e2e.config.ts
+          packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts

.github/workflows/sandbox.yml

@@ -19,7 +19,7 @@ permissions:
   contents: read
 
 jobs:
-  # Keyless real-kernel sandbox proofs (sandbox RFC § Testing): each ladder
+  # Keyless real-kernel sandbox proofs (sandbox Agent Note § Testing): each ladder
   # rung is only provable on a host where it enforces, so this job fans out
   # an OS×runner matrix — bwrap and Landlock on Linux (separate legs: the
   # Landlock files force the bwrap rung off, so each leg proves exactly one