{
  "id": "page:docs-daily-updates-2026-05-29",
  "_kind": "Page",
  "_file": "wiki/docs/daily-updates/2026-05-29.md",
  "_cluster": "wiki",
  "attributes": {
    "nodeKind": "Page",
    "sourcePath": "docs/daily-updates/2026-05-29.md",
    "sourceKind": "repo-docs",
    "title": "Daily Update - 2026-05-29",
    "displayName": "Daily Update - 2026-05-29",
    "slug": "docs/daily-updates/2026-05-29",
    "articlePath": "wiki/docs/daily-updates/2026-05-29.md",
    "article": "\n# Daily Update - 2026-05-29\n\n## Summary of Changes\n\n### New Features\n- push all 10 adversarial dimensions to 100 (8cf40df99)\n- push all 10 adversarial dimensions to 95+ (f44398767)\n- server cache, barrel index, shared helper extraction (604adf0db)\n- 30 new tests, remove mock data, dynamic tool discovery (622b8060e)\n- fetch dedup, confirm dialog, unsaved changes, component docs (83343e4f5)\n- complete accessibility — 40→3 components with zero a11y (247665f4b)\n- router.refresh() migration, API route tests, force-dynamic fixes (fff3bfd54)\n- add meaningful accessibility attributes to 20 components (3031a8c4a)\n- add pagination to all list endpoints and UI (8beaf2162)\n- add evil fallback audit and here be dragons audit processes (1332cb106)\n- add route-level loading skeletons for 8 sections (f2a23c7d0)\n- add Getting Started onboarding page (332411dd4)\n- add transcript viewer to dispatch run detail page (7e5c0dafa)\n- rewrite external provider wizard and list for typed providers (3e783b005)\n- replace ExternalBackendProvider with 5 domain-scoped provider kinds (af3843f11)\n- add inference playground with side-by-side model comparison (58474fad1)\n\n### Bug Fixes\n- harden remaining critical+high evil fallbacks across repo (ddf00cfb8)\n- route opencode through proxy for non-bundled providers (184bda9b0)\n- cap CLI orchestration at 20 iterations, bail on no-effects loop (ebd83c458)\n- remove mini model silent substitution, log non-zero exit tolerance (eb67d3984)\n- paginate agent runs/sessions to 25 items, aria on issue editor (722d2073c)\n- write opencode config as file, not just env var (46cdb2450)\n- fix real audit issues — 5 unauthed GETs, 8 confirm(), 5 silent catches (dc3e3e4bb)\n- add GH_TOKEN, CURSOR_API_KEY, COPILOT_GITHUB_TOKEN to live-stack workflow (a9c29d5cb)\n- single-task process template and 120s iterate timeout (c31b6381d)\n- remove silent matrix defaults, assertion weakening, and config cascades (bace9627e)\n- add metadata to 3 issue pages, error boundaries to 10 route groups (8f40b2dbb)\n- remove 5 evil fallbacks that hide real problems (90df526cf)\n- add diagnostic logging to 49 critical+high evil fallbacks across all packages (5758e11df)\n- let hermes call Google directly, mark foundry/anthropic as blocked (4bbaed8cf)\n- use OPENROUTER_API_KEY and provider: openrouter for hermes (e33d6e123)\n- write hermes cli-config.yaml with proxy base_url (d8664b0e5)\n- add hermes provider translations for foundry/anthropic/google (2d62fab2e)\n- remove hermes custom provider config, use standard OpenAI env (0586b9b16)\n- disable proxy auth for hermes (like gemini-cli) (a5cd4a554)\n- log Gitea tree fallback instead of silently swallowing (70a0d6a55)\n- replace staging Atlas URL with production default (d31c2dc44)\n- replace silent .catch(() => {}) with console.warn logging (e9153da01)\n- revert hermes launch to stdin delivery with keep-open (8de323dd6)\n- adversarial audit fixes — security, errors, docs, accessibility (29c0dd327)\n- pass thoughtSignatureStore to /v1/responses and WebSocket paths (c14c4500d)\n- inject prompt flag in bridge-interactive for cli-flag harnesses (ece07b15f)\n- write hermes proxy config to ~/.hermes/ instead of temp dir (b550e3a54)\n- add auth to policy-reports, cache invalidation imports to profile (884f0c093)\n- batch 3 color migration — 465 total replaced (1058→593) (d0a46db4d)\n- batch 2 color migration + add 'use client' to inference-helpers (c37b7fffe)\n- hermes back to -z headless mode — stdin TUI doesn't execute tasks (284871025)\n- harden hook sandbox, add error boundaries, 6 adversarial tests (e6f08431c)\n- replace 231 hardcoded hex colors with CSS variables (c02c0393c)\n- write hermes proxy config to cli-config.yaml not config.yaml — fixes #468 (0b2aafe0d)\n- use positional defineTask form in raw-session template (c29a7e82f)\n- auto-correct babysitter-sdk import to @a5c-ai/babysitter-sdk (3ec8d665c)\n- resolve agent prompt from both string and object formats (82c38ac84)\n- post raw text as CLI orchestration task result (230eaf3af)\n- instruct raw agent-core process to use fs.writeFile for file output (71300ad56)\n- pin gemini-cli to 0.43.0 — 0.44.x auth regression confirmed (118589cca)\n- add CJS require fallback to orchestrateIteration process loader (8d90a7178)\n- fallback to CJS require when ESM import fails for process modules (52d6f49c5)\n- ensure .a5c/processes has package.json type:module, use execFileSync (b0dbc67c2)\n- pin gemini-cli to 0.43.0 + revert proxy env — fixes #483 (fbea9028e)\n- hermes stdinBehavior keep-open + needsIdleKill — fixes #468 (8e29dd91f)\n- hermes prompt via stdin instead of -z flag — fixes #468 (25cb23739)\n- use execFileSync for CLI orchestration to avoid shell escaping (2e5381068)\n- move hermes --output-format jsonl to unconditional block — fixes #468 (a2f7a5a9f)\n\n### Refactors\n- split settings-providers (425→259) and inference-playground (528→319) (f315b7e64)\n- split kanban-enhanced (602→264) and runner-pool-manager (434→241) (07e894410)\n- split assistant-chat.jsx (656→225 lines) into 3 modules (d1c2495bd)\n- split workspace-panel.jsx (704→219 lines) into 3 modules (765e828b8)\n- split artifact-registry.jsx (753→112 lines) into 4 modules (c0d2bdc85)\n- split 1254-line agent-pages.jsx into 11 focused modules (c970bcf16)\n- extract shared phaseTone helper, remove 7 duplicates (46538b84f)\n- split inference-service-manager into 7 focused files (2d86aae98)\n\n### Documentation\n- mark fixed evil fallbacks in evil-fallbacks.md (69e00ef14)\n\n### Maintenance\n- add orchestration trace logging for genty CI diagnosis (d1bbc3916)\n- regenerate dist-types and apply linter auto-fixes (4a9c8597c)\n- track upstream agent versions (#545) (2f9063d8d)\n\n## PRs Merged\n\n- #545 Track upstream agent CLI versions - https://github.com/a5c-ai/babysitter/pull/545\n\n## Issues Opened\n\n- #563 Live-stack: BP mode gemini-3.5-flash model behavior — agent runs but doesn't create output file (OPEN) - https://github.com/a5c-ai/babysitter/issues/563\n- #562 Live-stack: cursor-cli CI integration — needs investigation (OPEN) - https://github.com/a5c-ai/babysitter/issues/562\n- #561 Live-stack: opencode fails — server startup error in CI (OPEN) - https://github.com/a5c-ai/babysitter/issues/561\n- #560 Live-stack: copilot-cli fails — no GitHub auth configured in CI (OPEN) - https://github.com/a5c-ai/babysitter/issues/560\n- #547 Live-stack: gemini-cli BP and BI modes fail — prompt not injected in PTY bridge path (CLOSED) - https://github.com/a5c-ai/babysitter/issues/547\n- #546 Live-stack: Google API thought_signature missing in /v1/responses and WebSocket proxy paths (CLOSED) - https://github.com/a5c-ai/babysitter/issues/546\n- #544 Track upstream amp-0.0.1780032159-g3925ab release (OPEN) - https://github.com/a5c-ai/babysitter/issues/544\n- #543 Track upstream droid-0.136.1 release (OPEN) - https://github.com/a5c-ai/babysitter/issues/543\n- #542 Track upstream omp-15.5.11 release (OPEN) - https://github.com/a5c-ai/babysitter/issues/542\n- #541 Track upstream pi-0.77.0 release (OPEN) - https://github.com/a5c-ai/babysitter/issues/541\n- #540 Track upstream opencode-1.15.12 release (OPEN) - https://github.com/a5c-ai/babysitter/issues/540\n- #539 Track upstream gemini-cli-0.44.1 release (OPEN) - https://github.com/a5c-ai/babysitter/issues/539\n- #538 Track upstream codex-0.135.0 release (OPEN) - https://github.com/a5c-ai/babysitter/issues/538\n- #537 Track upstream claude-agent-sdk-0.3.156 release (OPEN) - https://github.com/a5c-ai/babysitter/issues/537\n- #536 Track upstream claude-code-2.1.156 release (OPEN) - https://github.com/a5c-ai/babysitter/issues/536\n- #535 Track Amazon Nova 2 Pro model version (OPEN) - https://github.com/a5c-ai/babysitter/issues/535\n- #534 Track Gemini image model records and Gemini 2.x lifecycle deprecations (OPEN) - https://github.com/a5c-ai/babysitter/issues/534\n- #533 Track OpenAI GPT-5.5 Instant and chat-latest lifecycle updates (OPEN) - https://github.com/a5c-ai/babysitter/issues/533\n- #532 Track Claude Opus 4.8 model version (OPEN) - https://github.com/a5c-ai/babysitter/issues/532\n- #531 claude plugin update is a silent no-op — plugin version in marketplace.json never bumps across releases (OPEN) - https://github.com/a5c-ai/babysitter/issues/531\n\n## Issues Closed\n\n- #547 Live-stack: gemini-cli BP and BI modes fail — prompt not injected in PTY bridge path - https://github.com/a5c-ai/babysitter/issues/547\n- #546 Live-stack: Google API thought_signature missing in /v1/responses and WebSocket proxy paths - https://github.com/a5c-ai/babysitter/issues/546\n- #486 Live-stack: gemini-cli BI fails on Ubuntu/Windows (PTY fallback issue) - https://github.com/a5c-ai/babysitter/issues/486\n- #483 Live-stack: gemini-cli NI regression — \"Invalid auth method selected\" since May 28 - https://github.com/a5c-ai/babysitter/issues/483\n\n## CI Status Summary\n\n- Publish: pending - docs: update here-be-dragons.md with fix status (https://github.com/a5c-ai/babysitter/actions/runs/26657175843)\n- Publish: completed / cancelled - refactor(kradle-web): split inference-service-manager (473→224) with R… (https://github.com/a5c-ai/babysitter/actions/runs/26657147290)\n- Live Stack: in_progress - Live Stack (https://github.com/a5c-ai/babysitter/actions/runs/26657082415)\n- Publish: in_progress - docs: mark all remaining critical+high evil fallbacks as fixed (https://github.com/a5c-ai/babysitter/actions/runs/26657024915)\n- QA Daily: in_progress - fix: harden remaining critical+high evil fallbacks across repo (https://github.com/a5c-ai/babysitter/actions/runs/26657002229)\n- Publish: completed / cancelled - fix: harden remaining critical+high evil fallbacks across repo (https://github.com/a5c-ai/babysitter/actions/runs/26657002165)\n- Publish: completed / cancelled - refactor(kradle-web): split settings-providers (425→259) and inference… (https://github.com/a5c-ai/babysitter/actions/runs/26656977591)\n- Live Stack: completed / failure - Live Stack (https://github.com/a5c-ai/babysitter/actions/runs/26656792817)\n- Publish: completed / failure - fix(adapters): route opencode through proxy for non-bundled providers (https://github.com/a5c-ai/babysitter/actions/runs/26656783686)\n- Publish: completed / cancelled - refactor(kradle-web): split kanban-enhanced (602→264) and runner-pool-… (https://github.com/a5c-ai/babysitter/actions/runs/26656767865)\n\n## Live-Stack Test Results\n\n- ./.github/workflows/live-stack-published.yml\n- ./.github/workflows/live-stack.yml\n- ./scripts/live-stack-coverage-report.cjs\n",
    "documents": []
  },
  "outgoingEdges": [],
  "incomingEdges": [
    {
      "from": "page:docs",
      "to": "page:docs-daily-updates-2026-05-29",
      "kind": "contains_page"
    }
  ]
}