@@ -0,0 +1,54 @@
+---
+title: "Weekly Update – October 5, 2026"
+description: "Work queues and built-in ledgers land in v0.90.3, alongside safer safe outputs and broader Copilot model support."
+authors:
+  - copilot
+date: 2026-10-05
+metadata:
+  seoDescription: "gh-aw v0.90.0–v0.90.3: work queues, built-in ledgers, hardened safe outputs, Copilot model routing, and a redesigned docs site."
+---
+
+Three releases shipped in [github/gh-aw](https://github.com/github/gh-aw) this week, headlined by work queues and built-in ledgers in [v0.90.3](https://github.com/github/gh-aw/releases/tag/v0.90.3). Here's what's new.
+
+## Release Highlights
+
+### [v0.90.3](https://github.com/github/gh-aw/releases/tag/v0.90.3)
+
+This release introduces **work queues and ledgers**, tightens safe-output guardrails, and broadens Copilot model support.
+
+- **Work queue & ledgers**: built-in log, set, map, table, and counter ledgers, plus Git-backed `work-queue` operator commands. See the [ledger compaction docs](https://github.github.com/gh-aw/experimental/ledger-compaction/). Related PRs: [#65494](https://github.com/github/gh-aw/pull/65494) adds selectable issue-backed queue storage, and [#65443](https://github.com/github/gh-aw/pull/65443) dispatches queued work to trusted worker workflows.
+- **Copilot engine**: AWF task-level model routing, `none` and `max` reasoning efforts, GPT-6.1 Sol support, Claude 5.5 and GPT-6 pricing, and a run-wide tool-call budget for Copilot SDK agents.
+- **Safe outputs**: `add-labels` supports separate call and per-call label limits, and several hardening fixes landed. [#65612](https://github.com/github/gh-aw/pull/65612) adds attributed issue creation for custom safe-output jobs.
+- **Docs**: a redesigned site with a new landing page, warm palette, and Mona Sans.
+
+Heads-up on behavior changes: GitHub App tokens now require explicit scopes at compile time, Claude defaults to strict MCP configuration, and `add-comment` fails when the triggering target can't be resolved.
+
+### [v0.90.1](https://github.com/github/gh-aw/releases/tag/v0.90.1)
+
+Standalone safe-output-backed ledgers arrived ([#64354](https://github.com/github/gh-aw/pull/64354)), along with richer audit artifacts covering ledger transactions and threat-detection outcomes ([#64509](https://github.com/github/gh-aw/pull/64509), [#64506](https://github.com/github/gh-aw/pull/64506)), and compile-time self-hosted runner enforcement ([#64173](https://github.com/github/gh-aw/pull/64173)).
+
+### [v0.90.0](https://github.com/github/gh-aw/releases/tag/v0.90.0)
+
+Step summaries now render friction cost, agents may emit two `noop` calls by default ([#64031](https://github.com/github/gh-aw/pull/64031)), and five new trajectory graders were added.
+
+## Other Notable Pull Requests
+
+- [#65423](https://github.com/github/gh-aw/pull/65423) adds a TLA+ workflow security model and fail-closed credential cleanup.
+- [#65564](https://github.com/github/gh-aw/pull/65564) emits incomplete outcomes with diagnostics when an agent produces no safe outputs.
+- [#65650](https://github.com/github/gh-aw/pull/65650) makes PR Sous Chef poll faster and start agents only for actionable work.
+
+## 🤖 Agent of the Week: daily-arxiv-researcher
+
+A daily scout that reads the latest arXiv papers and looks for ideas that could improve GitHub Agentic Workflows.
+
+Its recent runs have all succeeded in about five to six minutes. The October 2 and 3 runs used the Copilot CLI engine, and the October 4 run was the first on the Codex engine with web search and fetch tools, after a [recent change](https://github.com/github/gh-aw/pull/65383) moved it there. That run used roughly 84K tokens, versus 7K and 13K for the earlier runs.
+
+The new engine is evidently more curious: it read about six times as many tokens as its predecessor on the same morning schedule.
+
+💡 **Usage tip**: Pair a research workflow with a dedup cache, as this one does with `cache-memory`, so it never reports the same paper twice.
+
+→ [View the workflow on GitHub](https://github.com/github/gh-aw/blob/main/.github/workflows/daily-arxiv-researcher.md)
+
+## Try It Out
+
+Update to [v0.90.3](https://github.com/github/gh-aw/releases/tag/v0.90.3) and give work queues a spin. Feedback and contributions are welcome in [github/gh-aw](https://github.com/github/gh-aw).
@@ -48,8 +48,6 @@ import Video from '../../../components/Video.astro';
 
 ## Adding an Automated Daily Status Workflow to Your Repo
 
-### YAML frontmatter
-
 GitHub Agentic Workflows lets developers define AI-powered repository automation in Markdown with YAML frontmatter (the configuration block between the `---` markers at the top of the file) and run AI agents through GitHub Actions. By the end of this guide, you will have a recurring agentic workflow running in your repository with GitHub Copilot, Claude Code, OpenAI Codex, Google Gemini, or Pi. This guide takes about 10 minutes and requires only the GitHub CLI.
 
 **⏱️ Estimated time: 10 minutes**
@@ -76,7 +74,7 @@ Before installing, ensure you have:
 - **Logged in to GitHub CLI** - Verify with `gh auth status` and run `gh auth login --scopes repo,workflow` if needed
 - **Operating System**: Linux, macOS, or Windows with WSL
 
-### Step 1 - Install the extension
+## Step 1 - Install the extension
 
 Install the GitHub Agentic Workflows extension:
 
@@ -97,7 +95,7 @@ gh extension install github/gh-aw
 > ```
 
 
-### Step 2 - Add the sample workflow and trigger a run
+## Step 2 - Add the sample workflow and trigger a run
 
 From your repository root, run this command:
 
@@ -128,7 +126,7 @@ This will take you through an interactive process to:
 5. **Optionally add skills for agentic authoring and debugging** - Adds additional files for interactive authoring and debugging of agentic workflows.
 6. **Optionally trigger an initial run** - Starts the workflow immediately.
 
-#### Configuring authentication
+### Configuring authentication
 
 **Copilot**
 
@@ -176,7 +174,7 @@ Pi chooses authentication from the provider prefix in `model:`. It uses Copilot
 
 Pi also requires `tools.github.mode: gh-proxy` and `tools.cli-proxy: true`. Follow [Using Pi with GitHub Agentic Workflows](/gh-aw/engines/pi/) for the complete setup.
 
-### Step 3 - Wait for the workflow to complete
+## Step 3 - Wait for the workflow to complete
 
 An automated workflow run can take 2-3 minutes.
 
@@ -201,7 +199,7 @@ import dailyRepoReportResult from '../../../assets/daily-repo-report-result.png'
 
 <Image src={dailyRepoReportResult} alt="Example of a Daily Repo Status Report issue created by the workflow" />
 
-### Step 4 - Customize your workflow (optional)
+## Step 4 - Customize your workflow (optional)
 
 With GitHub Agentic Workflows, you are in control! Your repository automation is fully customizable. You should shape your repo automation to match your priorities and your needs.
 
@@ -211,7 +209,7 @@ To customize it now:
 
 2. Edit the section "What to include" to list things you are having trouble with regularly in your repository: your issue backlog, your CI setup, your testing, the performance of your software, your roadmap. Any or all of these, or anything else you want to improve. You can also customize the style and process sections to guide the coding agent's behavior.
 
-3. If you changed the [frontmatter](#yaml-frontmatter) (the YAML configuration block between the `---` markers at the top of the file), regenerate the compiled workflow by running:
+3. If you changed the frontmatter (the YAML configuration block between the `---` markers at the top of the file), regenerate the compiled workflow by running:
 
    ```text
    gh aw compile