v0.80.6

🌟 Release Highlights

v0.80.6 focuses on safe-outputs reliability, GHES host support, and new agentic workflow capabilities — with dozens of targeted fixes that make credential handling, asset uploads, and compilation more robust.

✨ What's New

• Headroom context compression — A new shared agentic workflow compresses agent context when headroom is low, reducing token burn for long-running workflows. (#40223)
• Tool output previews in Copilot CLI — The conversation renderer now shows inline previews of tool outputs, making it easier to follow what an agent did at a glance. (#40116)
• AWF reflect summary surfaced to GitHub Actions — awf reflect output is now written to core.info, making reflection results visible in the Actions run log without extra steps. (#40069)
• Auto-detect GHES host in compile — gh aw compile now automatically detects GitHub Enterprise Server hosts, so GHES users no longer need manual host configuration for correct repo validation. (#40030)
• Cached owner-type API call — The compiler now caches the repository owner-type lookup once per compilation run, eliminating redundant API calls on large workflows. (#40258)
• gh aw init aligned to Copilot MCP schema — The MCP suggestion emitted by gh aw init now matches the official .github/mcp.json schema used by GitHub Copilot. (#40327)
• External threat-detect binary — Threat detection has migrated to an external threat-detect binary behind a feature flag, improving isolation and upgrade flexibility. (#40166)

🐛 Bug Fixes & Improvements

Safe-outputs & credential handling:

• Fixed git credential loss in safe_outputs job checkouts — credentials are now reliably preserved throughout the job. (#40161, #40147)
• Fixed duplicate Authorization header (HTTP 400) on git operations in push_to_pull_request_branch. (#40281)
• Checkout manifest relocated into safeoutputs/ so the containerized safe-outputs MCP server can read it. (#40025)
• Cross-repo checkout directories from the manifest are now trusted, resolving dubious-ownership errors. (#40080)
• Base branch is now validated with git check-ref-format before use in safe-outputs jobs. (#40001)
• Corrected stale 1 MB default for safe-outputs max-patch-size in schema and derived files. (#39999)
• Added configurable URL sanitization policy for code-region-safe suggestion handling. (#39927)

Compilation & workflow correctness:

• Fixed compiler incorrectly passing undeclared payload inputs for call-workflow steps. (#40154)
• Fixed invalid YAML generated for GitHub App token checkout steps in safe_outputs jobs. (#40301)
• Fixed actions-lock.json accumulating orphaned entries on full compile. (#39905)
• Added regression guard to ensure deterministic actions-lock.json key ordering. (#40324)
• Enforced non-empty dispatch_workflow names across safe-output schema and MCP registration. (#40315)

Asset uploads & authentication:

• upload_assets now resolves staged assets via a single GH_AW_ASSETS_DIR, fixing a path mismatch between RUNNER_TEMP and /tmp. (#40122, #40062)
• Added fallback to unauthenticated GitHub API when a SAML-enforced token blocks requests. (#40250)
• push_repo_memory now seeds new memory branches via the GitHub API to satisfy signed-commit requirements. (#40188)

Observability & reliability:

• Fixed stdout/stderr interleaving in mcp_cli_bridge for large outputs. (#40037)
• Token usage table is now rendered to core.info in the parse_token_usage step for better visibility. (#40227)
• Improved Copilot harness classification for opaque exitCode=1 failures. (#39959)
• Improved Copilot 403 auth guidance for copilot-requests mode. (#40052)

⚡ Performance

• Memory efficiency — Replaced 187 map[string]bool sets with map[string]struct{} across the codebase, reducing allocations throughout the compiler and runtime. (#39954)

🔍 Code Quality & Linting

• errstringmatch linter extended to cover HasPrefix, HasSuffix, EqualFold, Index, LastIndex, and Compare — catching more brittle error-string comparisons. (#40248)
• New linter detects bare discarded json.Marshal/json.Unmarshal calls. (#39993)
• Hardened OpenTelemetry compatibility contract. (#40006)

Generated by 🚀 Release · 40.8 AIC · ⊞ 8.2K

---

What's Changed

• Require RUNNER_TOOL_CACHE for tool-cache discovery by @zarenner with @Copilot in #40157
• feat: add Monte Carlo forecast compliance test suite (P1–P13) and fix fixture AIC gap by @pelikhan with @Copilot in #40126
• fix: add configurable safe-outputs URL sanitization policy for code-region-safe suggestion handling by @pelikhan with @Copilot in #39927
• [community] Update community contributions in README by @github-actions[bot] in #40206
• Bump default gh-aw-firewall to v0.27.7 and refresh generated artifacts by @lpcox with @Copilot in #40208
• fix(push_repo_memory): seed new memory branches via GitHub API to satisfy signed-commit rules by @pelikhan with @Copilot in #40188
• Render token table to core.info in parse_token_usage step by @pelikhan with @Copilot in #40227
• fix: expand Network Mapping and Pattern Heuristics tables in agentic-workflow-designer SKILL.md by @pelikhan with @Copilot in #40249
• [jsweep] Clean update_pull_request_branches.cjs by @github-actions[bot] in #40246
• errstringmatch: extend brittle error-string detection to HasPrefix/HasSuffix/EqualFold/Index/LastIndex/Compare by @pelikhan with @Copilot in #40248
• [WIP] Fix failing GitHub Actions job for integration add by @pelikhan with @Copilot in #40239
• fix: fall back to unauthenticated GitHub API when SAML-enforced token… by @pelikhan in #40250
• [spec-extractor] Update package specifications for agentdrain, cli, console, constants by @github-actions[bot] in #40286
• [docs] Update glossary - daily scan by @github-actions[bot] in #40289
• [docs] Update documentation for features from 2026-06-19 by @github-actions[bot] in #40291
• [instructions] Sync instruction files with release v0.80.4 by @github-actions[bot] in #40275
• feat(workflow): cache repository owner-type API call once per compilation run by @pelikhan with @Copilot in #40258
• Add headroom context compression as a shared agentic workflow by @pelikhan with @Copilot in #40223
• logs: download only usage artifact by default by @pelikhan with @Copilot in #40259
• fix(constraint-solving-potd): prevent body: "." sentinel misuse in create_discussion by @pelikhan with @Copilot in #40300
• Add regression guard for deterministic actions-lock.json key ordering by @pelikhan with @Copilot in #40324
• build(deps): bump undici from 6.24.0 to 6.27.0 in /actions/setup/js in the npm_and_yarn group across 1 directory by @dependabot[bot] in #40326
• Align gh aw init MCP suggestion with Copilot .github/mcp.json schema by @pelikhan with @Copilot in #40327
• [dead-code] chore: remove dead functions — 1 function removed by @github-actions[bot] in #40329
• Fix invalid YAML from checkout GitHub App token steps in safe_outputs jobs by @pelikhan with @Copilot in #40301
• Migrate threat detection to external threat-detect binary behind feature flag by @pelikhan with @Copilot in #40166
• Enforce non-empty dispatch_workflow names across safe-output schema and MCP registration by @pelikhan with @Copilot in ...

v0.80.4

🌟 Release Highlights

This release delivers a focused wave of reliability improvements, infrastructure hardening, and safe-outputs enhancements — making your agentic workflows more robust and predictable.

✨ What's New

• merge-pull-request schema parity (#39767) — The merge-pull-request safe-output now supports samples and cross-repo targeting, bringing it to full feature parity with other safe-output operations.
• GHES-friendly action pinning (#39908) — gh aw no longer applies its hardcoded action-pin fallback when GH_HOST targets a non-github.com host, removing friction for GitHub Enterprise Server users.
• Cleaner UX for personal repos (#39923) — The copilot-requests onboarding tip is now suppressed for individual (non-org) repository owners, reducing noise where it doesn't apply.

🐛 Bug Fixes & Improvements

• Fixed phantom asset failures (#39900) — Aligned the safe-outputs staging path with RUNNER_TEMP to eliminate spurious asset-not-found errors.
• Fixed MCP container tmp access (#39950) — Added the /tmp/gh-aw bind mount to the safeoutputs MCP container so tools that write there during workflow runs work correctly.
• Fixed assign-to-agent mutations (#39941) — Corrected the GraphQL mutations used to assign issues to agents, following the official API docs.
• Fixed silent add_comment skips (#39926) — add_comment no longer silently no-ops when the integration token lacks discussion write permissions; the error is now surfaced clearly.
• Fixed SDK driver timeouts (#39933) — Increased sendAndWait timeout in sample SDK drivers from 60 s to 10 min, preventing premature failures on longer agent tasks.
• Fixed null-byte corruption in step summaries (#39910) — Stripped null bytes from gateway.md before writing to the step summary to prevent rendering errors.
• Fixed unintended dependabot.yml writes (#39909) — gh aw no longer modifies dependabot.yml unless the --dependabot flag is explicitly passed.
• Hardened PR Sous Chef emission path (#39951) — Reinforced the safe-output emission path for PR Sous Chef to prevent dropped outputs under edge-case conditions.
• Isolated SDK driver test state (#39940) — copilot_sdk_driver tests now write session state in isolation, eliminating false-positive tool-denial failures.

📚 Documentation

• Terminology update (#39913) — Renamed "Copilot Skills" → "Skills" throughout the custom-agent-for-aw reference to align with current product naming.

Generated by 🚀 Release

---

What's Changed

• docs: rename "Copilot Skills" → "Skills" in custom-agent-for-aw reference by @Copilot in #39913
• fix: strip null bytes from gateway.md before writing to step summary by @Copilot in #39910
• Skip hardcoded action pin fallback when GH_HOST targets a non-github.com host by @Copilot in #39908
• fix: only touch dependabot.yml when --dependabot flag is used by @Copilot in #39909
• Fix phantom asset failures: align safe-outputs staging path with RUNNER_TEMP by @Copilot in #39900
• Skip copilot-requests tip for individual (non-org) repository owners by @dsyme in #39923
• safe-outputs: add merge-pull-request schema parity for samples and cross-repo targeting by @Copilot in #39767
• fix: add_comment silently skips when integration token can't write to discussions by @Copilot in #39926
• fix: correct assign-to-agent GraphQL mutations per official docs by @Copilot in #39941
• fix: isolate copilot_sdk_driver test session state writes to prevent false-positive tool-denial issues by @Copilot in #39940
• fix: increase sendAndWait timeout in sample SDK drivers from 60s to 10min by @Copilot in #39933
• Extract hardcoded file paths to named constants by @Copilot in #39938
• [aw] Harden PR Sous Chef safe-output emission path by @Copilot in #39951
• fix: add /tmp/gh-aw bind mount to safeoutputs MCP container by @Copilot in #39950

Full Changelog: v0.80.3...v0.80.4

v0.80.3

🌟 Release Highlights

v0.80.3 brings smarter MCP server configuration, improved Copilot billing detection in the setup wizard, and a focused set of reliability fixes across compilation, logs, and push workflows.

✨ What's New

• repo-memory JSON formatting (#39540) — New format-json: true option ensures AI-written JSON memory files are always pretty-printed before committing, making diffs reviewable and files easy to edit. Learn more

• mcp-scripts.dependencies fully wired (#39739) — The dependencies field in MCP script tool configs is now parsed, propagated through the runtime, and installed with pinned release-tag validation — eliminating late module not found failures.

• Smarter add-wizard billing detection (#39810) — The setup wizard probes the org's Copilot CLI billing status before rendering the auth prompt. copilot-requests is pre-selected when billing is enabled and visually blocked (with a clear label) when it is not.

• MCP server tool allowlist (#39863, #39866) — github-agentic-workflows MCP server now explicitly exposes only its six declared tools (compile, audit, logs, inspect, status, audit-diff). The server now runs directly from the local binary, removing the need for a globally installed gh aw extension in dev and CI environments.

• Failure category filtering for report-failure-as-issue (#39721) — Workflows can now pass an array of failure categories to suppress transient infrastructure noise (Docker timeouts, AI 5xx, MCP image pulls) without losing signals from real failures.

• Improved outcome intent attribution (#39718) — A dedicated intent resolver replaces ad-hoc outcome root tracing, adding attribution status and source to reports and marking PRs with multiple closing issues as ambiguous rather than silently selecting one.

⚡ Performance

• Faster action pin resolution (#39707) — ActionResolver now checks the embedded action pins table first, eliminating ~1.2 s gh-api subprocess calls for built-in actions whose SHA is already compiled into the binary.

🐛 Bug Fixes & Improvements

• Compilation: Stale container pins are pruned before compilation and UpdateContainerPins runs after, preventing stale-pin conflicts (#39770).
• Git: Resolved "dubious ownership" errors on checkout by adding git safe.directory and moving git config to a shell script (#39771).
• Logs: Fixed pagination in all-workflows mode when a full batch filters to zero runs (#39741).
• Push: push_signed_commits now recovers gracefully from shallow/partial-clone object failures during rebase (#39859).
• Copilot assignment: Both GraphQL-Features flags are always sent when assigning Copilot to an issue (#39719).
• Safe-outputs: Rate-limit failures during PR review safe-output operations are mitigated (#39797).
• Linters: regexpcompileinfunction resolves package identity via the type checker; uncheckedtypeassertion now recognises safe comma-ok forms in var initialisers and parenthesised assertions (#39773, #39774).
• Installer: ANSI colour codes are suppressed in CI and NO_COLOR environments for cleaner log output (#39875).

📚 Documentation

• New billing reference page — detailed guidance on Copilot billing configuration. Read more
• Improved billing setup tip — the copilot-requests auth tip now includes the org requirement note and links directly to the billing docs (#39873).

Generated by 🚀 Release

---

What's Changed

• fix: always send both GraphQL-Features flags when assigning Copilot to an issue by @Copilot in #39719
• ci: store Windows Defender scan logs as artifact on cross-platform build by @Copilot in #39726
• Improve outcome intent attribution by @mnkiefer in #39718
• Use IssueOrPRNumber for submit_pull_request_review.pull_request_number by @Copilot in #39723
• Consolidate ~25 duplicate helper implementations by @Copilot in #39720
• Fix misplaced zizmor ignore comment in GHES host step generator by @Copilot in #39740
• logs: keep paging in all-workflows mode when full batches filter to zero runs by @Copilot in #39741
• chore: bump Claude Code 2.1.178→2.1.179, Pi 0.79.4→0.79.6 by @Copilot in #39772
• fix(regexpcompileinfunction): resolve package identity via type checker instead of identifier name by @Copilot in #39773
• perf(workflow): check embedded action pins before gh-api network call in ActionResolver by @dsyme in #39707
• fix: prune stale container pins and move UpdateContainerPins to after compilation by @Copilot in #39770
• uncheckedtypeassertion: recognize safe comma-ok form in var init and parenthesized assertions by @Copilot in #39774
• feat(repo-memory): add format-json option to pretty-print JSON files before commit by @Copilot in #39540
• Add failure category filtering to report-failure-as-issue by @Copilot in #39721
• Mitigate safe-output PR review rate-limit failures by @Copilot in #39797
• Fix Impact report objective mapping guidance to match resolver outputs and available datasets by @Copilot in #39784
• Implement mcp-scripts.dependencies end-to-end with runtime-manager install flow and pinned release-tag validation by @Copilot in #39739
• fix: retry defender scan on transient WinDefend service unavailability by @Copilot in #39847
• add-wizard: detect org Copilot billing and pre-select/disable copilot-requests accordingly by @Copilot in #39810
• docs: add billing reference page by @dsyme in #39854
• Add tools array to github-agentic-workflows by @pelikhan in #39863
• fix(push_signed_commits): recover from shallow/partial-clone object failures during rebase by @dsyme in #39859
• fix(daily-formal-spec-verifier): add sed -n to bash allowlist by @Copilot in #39864
• Update MCP server command and arguments by @pelikhan in #39866
• Suppress ANSI installer colors in CI and explicit no-color environments by @Copilot in #39875
• Improve copilot billing tip: add org requirement note and billing docs link by @Copilot in #39873
• Clarify Test Quality Sentinel safe-output comment invocation to prevent Copilot engine permission failures by @Copilot in #39867
• fix: add git safe.directory and refactor git config to shell script to resolve dubious ownership error by @Copilot in #39771

Full Changelog: v0.80.2...v0.80.3

v0.80.2

🌟 Release Highlights

v0.80.2 is a focused reliability and polish release that tightens Copilot API compatibility, hardens the safe-outputs tooling, clarifies CLI flag semantics, and improves documentation precision.

🐛 Bug Fixes & Improvements

• Copilot assignment API fix — Resolved an issue where only one of the two required GraphQL-Features header flags was sent when assigning Copilot to an issue, which could cause silent failures against the GitHub API. Both issues_copilot_assignment_api_support and coding_agent_model_selection flags are now always included. (#39719)
• Prevent placeholder release note submissions — update_release now enforces a minimum body length, blocking accidental placeholder payloads (e.g. {"body":"test"}) from overwriting real release content when max:1 is in effect. (#39713)

✨ What's New

• Mutually exclusive compile flags enforced — --gh-aw-ref, --action-tag, and --action-mode are now declared mutually exclusive in the compile command. Previously --gh-aw-ref silently overwrote the other flags; now the CLI returns a clear error. The help text also no longer lists the removed inline mode and correctly documents the valid action mode. (#39697)
• Safe-outputs runtime image pinned — The ghcr.io/github/gh-aw-node image used by safe-outputs is now included in the default container predownload list and recorded in the compiled gh-aw-manifest. Workflows automatically prefetch it and lock headers include it, improving cold-start reliability. (#39644)

📚 Documentation

• Safeoutputs deferred-write semantics clarified — Updated safe_outputs_prompt.md with explicit guidance: agents should trust a successful tool response without re-verifying the effect via gh or other read paths, since deferred writes are applied after the agent finishes. (#39694)

Generated by 🚀 Release

---

What's Changed

• fix: enforce minLength on update_release body to block placeholder submissions by @Copilot in #39713
• compile: clarify --action-mode/--action-tag/--gh-aw-ref relationship, enforce mutual exclusivity by @Copilot in #39697
• docs: clarify safeoutputs deferred writes by @pelikhan in #39694
• Include and pin safe-outputs gh-aw-node image in default container predownload and manifest by @Copilot in #39644

Full Changelog: v0.80.1...v0.80.2

v0.80.1

test

Generated by 🚀 Release

---

What's Changed

• docs: sharpen workflow-authoring guidance for PR scoping, backend compatibility checks, and coverage fallback networking by @Copilot in #39622
• chore: bump CLI tool versions (Claude 2.1.178, Copilot 1.0.63, Codex 0.140.0, Pi 0.79.4, GH MCP Server v1.3.0, Playwright v1.61.0) by @Copilot in #39624
• Add missing issues: read permission to pr-code-quality-reviewer by @Copilot in #39625
• chore: expand pr to issue tracing for impact report mapped outcomes by @Copilot in #39620
• Sync MCP server toolset/permissions mapping to v1.3.0 by @Copilot in #39650
• Propagate Copilot BYOK provider hosts into threat-detection allowlists by @Copilot in #39653
• Clarify github_api_calls provenance and recover snapshot-only core_consumed accounting by @Copilot in #39623
• Ensure inline sub-agents always trigger interpolation step generation by @Copilot in #39651
• Consolidate near-duplicate WorkflowListItem ⊂ WorkflowStatus structs in pkg/cli by @Copilot in #39637
• Add configurable OTLP resource attributes to workflow observability by @Copilot in #39636
• Support array/object runner specs for runs-on-slim and safe-outputs runner fields by @Copilot in #39654
• fix: restore interaction permissions for workflow_call workflows with reaction/status-comment by @Copilot in #39652
• schema: add normalize-closing-keywords to create-issue, add-comment, create-pull-request branches by @Copilot in #39643
• schema: allow required-category in safe-outputs.create-discussion and add regression coverage by @Copilot in #39640
• fix: sanitize HTML error pages in getErrorMessage to avoid noisy safe_outputs logs by @Copilot in #39655
• Record compiler ref in lock metadata for --action-tag compiles by @Copilot in #39687
• fix: restore MCP CLI concept explanation and fix safeoutputs framing by @dsyme in #39689

Full Changelog: v0.80.0...v0.80.1

v0.80.0

🌟 Release Highlights

v0.80.0 expands CI/CD orchestration to ARC/DinD environments, adds powerful new portfolio and centralization-optimizer workflows, sharpens AI-credit management, and raises the bar on observability and diagnostics.

✨ What's New

ARC/DinD Container Support — Agentic workflows can now run inside Docker-in-Docker environments (ARC runners). The compiler emits chroot.binariesSourcePath, chroot.identity, and the `(redacted) Docker host, enabling full end-to-end agent execution on self-hosted container runners. (#38911, #38913)

Copilot Centralization Optimizer — New workflows identify redundant or inefficient Copilot invocations across your org and surface consolidation opportunities, helping teams reduce costs and improve consistency. (#39394, #39437, #39439)
Learn more →

Portfolio Analyst Workflow — A revived strategic-reporting workflow that generates cross-workflow portfolio summaries for executive visibility. (#39450)

Objective Impact Report — Executive-grade reports now restrict outcomes to issues linked via PR, include a simplified summary table, and compute AIC efficiency metrics, making ROI measurement actionable at a glance. (#39484, #39490, #39535, #39543)

OTel cicd.automation.* Standard — Proposed new OpenTelemetry semantic conventions for CI/CD automation signals, with W3C TRACEPARENT now propagated through all engine execution steps for end-to-end distributed tracing. (#38953, #39435, #39596)

Expanded gh aw forecast — Forecast output now includes threat-detection credits, exposes monthly low/high/stdev ranges, and inspects all completed runs—giving a more complete picture of your AI-credit spend. (#39101, #39102)
Forecast reference →

Smarter AI-Credit Guardrail — The daily guardrail is now skipped for user-initiated and command-routed runs, eliminating false blocks during development and testing. An actions/cache-based usage cache removes the need to download artifacts on every run. (#39123, #38856)

runs-on-slim: Array & Runner-Group Support — runs-on-slim now accepts label arrays and runner-group object forms, matching the full GitHub Actions runs-on syntax. (#39579, #38965)

Max Patch Size Raised to 4 MB — The default max-patch-size is increased from 1 MB to 4 MB, with clearer error messages when the limit is exceeded. Larger diffs no longer cause silent truncation. (#39118)

Token-Optimization Hints in Failure Issues — When a guardrail triggers, failure issues now include an "Optimize token consumption" section with actionable guidance. Tool-denial issues also include the last 5 tool calls for faster root-cause analysis. (#39069, #39122)

Anthropic WIF Auth (Claude) — Workload Identity Federation is now a first-class Claude authentication option, documented alongside the existing token-based flow. (#39241)
Setup →

🐛 Bug Fixes & Improvements

• AIC usage cache always empty — Fixed an activation-job bug where cache entries were never written, causing unnecessary artifact downloads. (#39130)
• Bundle prerequisite commit fetch — gh aw bundle now fetches prerequisite commits by SHA instead of a broad --deepen, preventing shallow-clone failures. (#39466)
• time.After timer leaks eliminated — Looped time.After calls are replaced with proper ticker management; timeafterleak linter now enforces this in CI. (#39188, #39133)
• Copilot 429 quota-exceeded retries stopped — The Copilot harness no longer retries CAPIError: 429 quota exceeded responses, preventing runaway retry storms. (#39581)
• Codex active-goal router retries stopped — Codex harness no longer retries on active-goal router failures, avoiding wasted credits on unrecoverable states. (#39156)
• Script injection S7630 fixed — Maintenance workflow Record outputs steps are hardened against shell script injection. (#39578)
• set_issue_field discovery query fixed — Removed an invalid IssueField fragment that caused field-discovery failures. (#39586)
• Parallel-process test flakes fixed — Environment-dependent and parallel-process test failures in the test suite are resolved. (#39467)
• Preserve engine.env scalar types — Numeric and boolean engine.env values are now preserved through compilation instead of being coerced to strings. (#39582)
• Inline sub-agent frontmatter preserved — Sub-agent frontmatter is no longer dropped during extraction. (#39577)
• Cache-memory threat-detection narrowed — False positives from AIC guardrail steps in cache-memory assertions are eliminated. (#39281)
• Ambient-context token reduction — First-request token overhead in smoke-copilot and test-quality-sentinel workflows is significantly reduced. (#39157, #39280)

📚 Documentation

• Anthropic WIF is now a first-class Claude auth option in setup docs (#39241)
• experiments docs clarified with model, sub-agent, and subskill examples (#39226)
• Cache-memory branch scoping and default-branch fallback behavior documented (#39265)
• max-ai-credits: 5M removed from reference examples to prevent misconfiguration (#39128)
• Workflow authoring guidance tightened for trigger selection, noop behavior, and workflow_run scoping (#39119, #39583)

Generated by 🚀 Release

---

What's Changed

• Add logging to publish-safe-outputs-node scripts by @Copilot in #39085
• reduce node image cooldown from 7d to 1d by @Copilot in #39086
• fix: enforce 48h data retention on AIC usage cache entries by @Copilot in #39084
• Harden Defender signature update with retries and failure diagnostics in release workflow by @Copilot in #39096
• Clarify Appendix A AI credits example with explicit §3.5 cache-read deduction by @Copilot in #39098
• Use ✅ for run-success in Test Quality Sentinel messages by @Copilot in #39099
• Inspect all completed forecast runs in gh aw forecast by @Copilot in #39102
• Tighten workflow authoring guidance for trigger selection, scenario mapping, and visual-regression network scope by @Copilot in #39119
• Skip daily AI-credit guardrail for user-initiated and command-routed runs by @Copilot in #39123
• docs: remove max-ai-credits: 5M examples from reference docs by @Copilot in #39128
• Include last 5 tool calls in tool-denials failure issues by @Copilot in #39122
• Emit Copilot auth migration tip for copilot-requests workflows by @Copilot in #39129
• Include threat-detection credits in forecast totals, expose monthly low/high/stdev, and fix formal-verifier tool denials by @Copilot in #39101
• [linter-miner] linter: add timeafterleak — flag time.After in for+select cases by @github-actions[bot] in #39133
• Increase default max-patch-size from 1 MB to 4 MB and improve patch-size-exceeded error messages by @Copilot in #39118
• fix(unbloat-docs): fetch LFS objects during checkout to fix docs build by @Copilot in #39145
• Reduce ambient-context payload in daily/PR workflows and shared prompt imports by @Copilot in #39157
• [spec-enforcer] Enforce specifications for github, typeutil by @github-actions[bot] in #39219
• [docs] Update documentation for features from 2026-06-14 by @github-actions[bot] in #39214
• [spec-extractor] Update package specifications for envutil, fileutil, gitutil, logger by @github-actions[bot] in #39211
• [instructions] Sync instruction files with release v0.79.8 by @github-actions[bot] in #39207
• [docs] Update dictation skill instructions by @github-actions[bot] in #39195
• Fix AIC usage cache always empty in activation job by @Copilot in #39130
• Clarify the experiments docs and add model, sub-agent, and subskill examples by @Copilot in #39226
• Clarify sub-skill progressive disclosure in token/cost optimization guidance by @Copilot in #39227
• Eliminate looped time.After timer leaks, propagate cancellation correctly, and enforce timeafterleak in CI by @Copilot in #39188
• docs: add Anthropic WIF as a first-class Claude auth option by @Copilot in #39241
• docs(playwright): align CLI visual regression version with npm package semantics by @Copilot in #39245
• Replace raw fmt.Fprintf output in outcomes_history.go with console package by @Copilot in #39248
• Replace raw fmt.Fprintf verbose debug output with console.LogVerbose in token_usage.go by @Copilot in #39247
• Extract inline lipgloss styles and harden ShowWelcomeBanner styling by @Copilot in #39246
• docs: clarify cache-memory branch scoping and default-branch fallback by @Copilot i...

v0.79.8

🌟 Release Highlights

v0.79.8 brings two new Go linters for code quality enforcement, a wave of targeted bug fixes improving reliability and portability, a performance boost for workflow run queries, and codemod improvements to complete the max-effective-tokens → max-ai-credits migration.

✨ What's New

• httpnoctx linter (#38888) — Automatically flags Go HTTP calls made without a context.Context parameter, helping catch a common source of non-cancellable requests before they reach production.
• hardcodedfilepath linter (#38742) — Detects hard-coded file path string literals in Go code, surfacing brittle path assumptions that break across environments.
• Code Simplifier budget caps (#38851) — Per-run hard budgets with graceful noop exit prevent runaway simplification loops from consuming unbounded AI credits.
• --gh-aw-ref resolved to commit SHA at compile time (#38689) — Branch and tag references passed via --gh-aw-ref are now pinned to their commit SHA during compilation, ensuring deterministic and auditable workflow builds.
• AOAI Entra smoke workflow (#38706) — New end-to-end smoke workflow validates Azure OpenAI Entra authentication for Copilot, extending CI coverage to AOAI-backed runs.

🐛 Bug Fixes & Improvements

• environment: propagation fixed (#38918) — Top-level environment: blocks are now correctly propagated to the detection job, resolving a compilation gap that silently dropped environment bindings.
• set_issue_field GraphQL fix (#38882) — Corrects an invalid GraphQL query in fetchIssueFields that caused set_issue_field calls to fail at runtime.
• String-form create_issue.labels handled (#38738) — Safe-output validation and schema definitions now correctly handle labels provided as a comma-separated string in addition to arrays, fixing label assignment failures.
• False-positive AI credits failures eliminated (#38737) — Prevents erroneous failure issues from being filed on successful runs that happened to trigger unknown-model detection logic.
• Copilot supports arbitrary HOME directories (#38725) — The Copilot engine integration no longer assumes /home/runner as the home directory, improving portability for non-standard runner environments.
• Designer Drift Audit permissions fix (#38855) — Added the missing pull-requests: read scope so the Designer Drift Audit workflow can read PR data without permission errors.

⚡ Performance

• Faster workflow run queries (#38779) — listWorkflowRuns pagination now stops as soon as the 24-hour cutoff is reached rather than fetching all pages, significantly reducing API calls on active repositories.

🔧 Migration

• max-effective-tokens: -1 codemod completed (#38850) — The effective-tokens-to-ai-credits codemod (gh aw fix --write) now correctly rewrites the -1 sentinel value for max-effective-tokens, closing the last gap in the legacy budget migration. Run gh aw fix --write if you still see max-effective-tokens: -1 in your workflows.

📚 Documentation

• Updated docs covering features shipped through 2026-06-12 (#38828) including spec audits for fileutil, constants, timeutil, and tty packages (#38848).

Generated by 🚀 Release · 110.8 AIC · ⊞ 28.8K

---

What's Changed

• Prevent false-positive AI credits/unknown-model failure issues on successful runs by @Copilot in #38737
• Scale homepage hero slides correctly on mobile by @Copilot in #38740
• Add hardcodedfilepath linter to detect hard-coded file path string literals by @Copilot in #38742
• fix(copilot): support arbitrary HOME directory, not just /home/runner by @Copilot in #38725
• Add AOAI Entra smoke workflow for Copilot by @Copilot in #38706
• Handle string-form create_issue.labels across safe-output validation and schema/tool definitions by @Copilot in #38738
• [community] Update community contributions in README by @github-actions[bot] in #38771
• Resolve --gh-aw-ref branch/tag to commit SHA at compile time by @dsyme in #38689
• Fix lint-go CGO failure by normalizing ResolveGhAwRef formatting and string construction by @Copilot in #38778
• [spec-enforcer] Enforce specifications for styles, syncutil, testutil by @github-actions[bot] in #38831
• [docs] Update documentation for features from 2026-06-12 by @github-actions[bot] in #38828
• [spec-extractor] Update package specifications for tty, types, typeutil, workflow by @github-actions[bot] in #38822
• optimize: stop paginating listWorkflowRuns once 24h cutoff is reached by @Copilot in #38779
• Add debug-scoped /tmp/gh-aw file inventory to setup post cleanup by @Copilot in #38780
• refactor: semantic function clustering — dedup, shared helpers, and generics consolidation by @Copilot in #38776
• deps(go): bump golang.org/x/tools to v0.46.0 by @Copilot in #38849
• Add SEC-004 transport-body exemption to artifact client by @Copilot in #38853
• docs: spec audit — add github README, update fileutil/constants/timeutil/tty specs by @Copilot in #38848
• Add missing pull-requests: read scope to Designer Drift Audit workflow by @Copilot in #38855
• [aw-compat] Migrate max-effective-tokens: -1 to max-ai-credits: -1 in codemod by @Copilot in #38850
• Add SEC-005 exemption annotation for apply_samples replay driver by @Copilot in #38852
• [dead-code] chore: remove dead functions — 1 function removed by @github-actions[bot] in #38858
• Cap Code Simplifier runaways with hard per-run budgets and graceful noop exit by @Copilot in #38851
• [jsweep] Clean validate_context_variables.cjs by @github-actions[bot] in #38785
• [linter-miner] feat(linters): add httpnoctx linter — flag HTTP calls without context by @github-actions[bot] in #38888
• ctxbackground: resolve Background() calls by package identity, not identifier text by @Copilot in #38854
• Refactor engine log parsing to canonical Copilot event format by @Copilot in #38781
• [caveman] Optimize instruction verbosity — serena-tool, skills, subagents (2026-06-12) by @github-actions[bot] in #38930
• Move auto-generated notice to first line with debugging skill URL by @Copilot in #38923
• fix: propagate top-level environment: to the detection job by @Copilot in #38918
• Correct OTLP CLI version attribution for scope/service/span fields by @Copilot in #38916
• fix(set_issue_field): fix invalid GraphQL query in fetchIssueFields by @Copilot in #38882

Full Changelog: v0.79.7...v0.79.8

v0.79.7

🌟 Release Highlights

This release focuses on AI credit management hardening, codemod reliability, and expanded tooling support — with stronger guardrail enforcement and cleaner failure diagnostics throughout.

⚠️ Notable Changes

• daily_effective_workflow_* metrics renamed to daily_ai_credits_* (#38611): Workflow run metrics are now standardized under the daily_ai_credits_* namespace. If you reference these metrics in dashboards, queries, or configurations, update them to the new names. See the migration guide for details.

✨ What's New

• Codemod exclusion flags for fix and upgrade (#38688): gh aw fix and gh aw upgrade now accept exclusion flags, giving you fine-grained control over which codemods are applied during automated maintenance runs.
• Pi CLI support (#38724): The @earendil-works/pi-coding-agent CLI is now tracked in the cli-version-checker, expanding agent compatibility monitoring.

🐛 Bug Fixes & Improvements

• Guardrail enforcement hardened (#38639): The max_daily_ai_credits guardrail now fails as a hard stop, preventing cost overruns while correctly preserving workflow conclusion failure handling.
• Guardrail coverage expanded (#38705): Daily AI credit guardrails now apply to label-triggered and slash-command-triggered workflows, closing a gap where these trigger paths were previously unenforced.
• Codemod shell comment handling (#38682): Shell comment lines are now correctly skipped when scanning run: blocks for expression hoisting, preventing false-positive codemod transformations.
• Actionable COPILOT_GITHUB_TOKEN error messages (#38722): When COPILOT_GITHUB_TOKEN is missing, agent failure issues now include a permissions.copilot-requests: write suggestion, making the fix immediately actionable.
• Faster OIDC api-proxy startup (#38718): The initial awf-reflect models probe is deferred until after startup, reducing cold-start latency for the harness.

📚 Documentation

• Azure Foundry OpenAI v1 BYOK (#38641): Documentation now covers Bring Your Own Key (BYOK) configuration for Azure Foundry OpenAI v1 deployments.

Generated by 🚀 Release · 111.2 AIC · ⊞ 28.8K

---

What's Changed

• [dead-code] chore: remove dead functions — 5 functions removed by @github-actions[bot] in #38640
• Add codemod exclusion flags to fix and upgrade by @Copilot in #38688
• Fail max_daily_ai_credits guardrail as a hard stop while preserving conclusion failure handling by @Copilot in #38639
• docs: Document Azure Foundry OpenAI v1 BYOK support by @Copilot in #38641
• chore: update slides and place on hero page by @mnkiefer in #38690
• fix: enhance slide loading and error handling in WorkflowHero by @mnkiefer in #38712
• fix(codemod): skip shell comment lines when scanning run blocks for expression hoisting by @Copilot in #38682
• fix: run daily AIC guardrail for label and slash command triggers by @Copilot in #38705
• Eliminate setup-time @actions/artifact install by inlining required artifact client features by @Copilot in #38684
• Remove legacy model_multipliers.json artifacts and file-based multiplier merge path by @Copilot in #38642
• [linter-miner] feat(linters): add timesleepnocontext linter by @github-actions[bot] in #38704
• feat(harness): defer initial awf-reflect models probe during OIDC api-proxy startup by @Copilot in #38718
• Track Pi CLI (@earendil-works/pi-coding-agent) in cli-version-checker by @Copilot in #38724
• Fix Smoke Pi: no safe outputs due to wrong prompt order and missing gh CLI instruction by @Copilot in #38719
• rename daily_effective_workflow_* → daily_ai_credits_* by @Copilot in #38611
• Suggest permissions.copilot-requests: write in agent failure issue when COPILOT_GITHUB_TOKEN is missing by @Copilot in #38722

Full Changelog: v0.79.6...v0.79.7

v0.79.6

🌟 Release Highlights

This release focuses on observability improvements, Windows CLI reliability, and security hardening for the AWF firewall runtime — keeping your agentic workflows stable and easier to debug.

✨ What's New

• AI Credit Observability — gh-aw.aic is now emitted as a doubleValue on OTLP conclusion spans, fixing Sentry EAP type inference and ensuring AI credit cap attributes appear consistently even when INPUT_JOB_NAME is absent. Richer data means faster cost diagnosis. (#38550, #38510, #38580)

• Go MCP Server Process Guardrail — A 4-process limit is now enforced on child gh invocations spawned by the Go MCP server, preventing runaway process trees and improving resource safety in constrained runners. (#38544)

• Prefetch Strategy A/B Experiment — The weekly-blog-post-writer workflow gains a prefetch_strategy experiment flag, enabling controlled rollout of prefetch optimizations across agentic runs. (#38622)

• Maintenance Trigger Logging — The first trigger reason for agentics-maintenance generation is now logged, giving operators clear visibility into what kicked off a maintenance cycle. (#38616)

🐛 Bug Fixes & Improvements

• Windows CLI Deadlock Fixed — A process wrapper deadlock in the Windows CLI integration has been resolved, unblocking workflows that stalled when spawning child processes on Windows. (#38592)

• Smarter Failure Titles — The conclusion job now uses failure-specific issue titles and detects the unknown_model_ai_credits failure mode, making auto-filed failure issues more actionable. (#38615, #38610)

• Windows Test Coverage Expanded — The Windows CLI integration test suite is restructured into a scenario matrix covering shell, environment, path, and chaos scenarios for broader coverage. (#38526)

🔒 Security & Reliability

• AWF 0.27.2 Update — Upgraded to the latest AWF firewall runtime, incorporating upstream security and stability fixes. (#38660)

• Digest Pinning Restored — Container image digest pinning for AWF 0.27.0 firewall sidecar images has been restored, and the release pipeline now gates on resolved SHA pins before pushing tags — ensuring supply chain integrity. (#38595, #38608)

📚 Documentation

• LLM/Agent Discovery — Replaced starlight-llms-txt with a custom llms.txt/agents.txt that points directly to .github/aw/*.md workflow sources, making this repo more discoverable by LLM-based tooling. (#38630)

• copilot-requests: write Permission Guidance — Instruction docs now recommend the copilot-requests: write permission for Copilot-targeted workflows. (#38410)

Generated by 🚀 Release · 107.7 AIC · ⊞ 28.8K

---

What's Changed

• Replace remaining sort.Slice call sites with type-safe slices.SortFunc by @Copilot in #38498
• [jsweep] Clean write_large_content_to_file.cjs by @github-actions[bot] in #38504
• Ensure gh-aw.aic is emitted on conclusion spans when INPUT_JOB_NAME is missing by @Copilot in #38510
• Restructure Windows CLI integration into scenario matrix with missing shell/env/path/chaos coverage by @Copilot in #38526
• Add AI credit cap observability attributes to OTLP conclusion spans by @Copilot in #38550
• [instructions] Sync instruction files with release v0.79.4 by @github-actions[bot] in #38567
• [docs] Update documentation for features from 2026-06-11 by @github-actions[bot] in #38593
• [docs] Update glossary - daily scan by @github-actions[bot] in #38585
• Recommend copilot-requests: write for Copilot-targeted workflows in instruction docs by @Copilot in #38410
• Fix Windows CLI integration deadlock in process wrapper by @Copilot in #38592
• release: gate on resolved container SHA pins before push_tag by @Copilot in #38608
• Restore digest pinning for AWF 0.27.0 firewall sidecar images by @Copilot in #38595
• fix: always emit gh-aw.aic as doubleValue to fix Sentry EAP type inference by @Copilot in #38580
• Add a 4-process guardrail for Go MCP server child gh invocations by @Copilot in #38544
• Log first trigger reason for agentics-maintenance generation by @Copilot in #38616
• Detect unknown_model_ai_credits failure in conclusion job by @Copilot in #38610
• Use failure-specific issue titles in conclusion job by @Copilot in #38615
• Add prefetch_strategy A/B experiment to weekly-blog-post-writer by @Copilot in #38622
• docs: replace starlight-llms-txt with custom llms.txt/agents.txt pointing to .github/aw/*.md by @Copilot in #38630
• updated to awf 0.27.2 by @pelikhan in #38660

Full Changelog: v0.79.5...v0.79.6

v0.79.5

🌟 Release Highlights

This release focuses on AI cost visibility and control: the legacy “effective tokens” metric is now called AI Credits across all surfaces, threat detection gets a configurable cost cap, and the add-wizard gains smarter Copilot org billing guidance. Several reliability improvements round out the release.

✨ What’s New

• AI Credits Terminology — “Effective tokens” is now AI Credits (AIC) throughout the UI and workflow metrics, providing clearer cost reporting aligned with the primary billing metric. (#38481)

• Threat Detection Cost Cap — safe-outputs.threat-detection now supports a max-ai-credits field (default: 400) with runtime override, giving you independent budget control over security-scan runs. Learn more (#38456)

• Smarter Copilot Org Billing Setup — gh aw add-wizard now asks Copilot users whether they want to use copilot-requests (org billing via Actions token, no PAT required) or a traditional PAT, simplifying enterprise onboarding. (#38449)

• AI Metrics in Failure Comments — Agent failure issue comments now include AI credit metrics from detection jobs, making cost attribution transparent even when runs fail. (#38453)

🐛 Bug Fixes & Improvements

• Fixed false secret validation warnings for Copilot org billing mode — no more spurious warnings when secrets are correctly configured. (#38459)

• Improved safe-outputs error surfacing — comment_memory now fails (instead of silently skipping) in non-PR contexts, and add_comment hard-fails on unrecognized message targets. (#38447)

• Fixed Docker Hub dependency in safe-outputs — Safe-outputs no longer pulls node:lts-alpine from Docker Hub, restoring reliability for environments with restricted container registries. (#38452)

• Fixed push_to_pull_request_branch — Branch derivation now always uses the PR’s actual head ref, resolving incorrect branch targeting. (#37863)

• Fixed numeric telemetry — gh-aw.aic is now always emitted as a numeric value for agent/detection spans, ensuring consistent OpenTelemetry ingestion. (#38432)

📚 Documentation

• Automated self-healing documentation fixes applied from issue analysis. (#38464)

Generated by 🚀 Release · 95.1 AIC · ⊞ 28.8K

---

What's Changed

• fix: always emit gh-aw.aic as numeric for agent/detection spans by @Copilot in #38432
• Update .github/aw guidance for frontier-model cost architecture (triage, context pull, bounded sub-agents) by @Copilot in #38429
• [caveman] Optimize instruction verbosity — network, pr-reviewer, report, reuse, workflow-health (2026-06-10) by @github-actions[bot] in #38440
• Creating integration tests for gh aw mcp server by @Copilot in #38448
• Fix #37835: always derive push_to_pull_request_branch from PR head ref by @dsyme in #37863
• fix: safe outputs — comment_memory fails instead of skips in non-PR context; add_comment hard-fails on unrecognized message target by @Copilot in #38447
• Include detection job AI metrics in agent failure issue comment footer by @Copilot in #38453
• Fix secret validation false warnings for copilot org billing mode by @Copilot in #38459
• fix: stop pulling node:lts-alpine for safe-outputs (Docker Hub unreachable) by @Copilot in #38452
• feat: add-wizard prompts Copilot users to choose copilot-requests (org billing) vs PAT by @Copilot in #38449
• [docs] Self-healing documentation fixes from issue analysis - 2026-06-11 by @github-actions[bot] in #38464
• Add threat-detection max-ai-credits with 400 default and runtime override by @Copilot in #38456
• Bump gh-aw-firewall to v0.27.1 by @Copilot in #38480
• Replace "effective tokens" with "AI Credits" in user-facing text by @Copilot in #38481
• [community] Update community contributions in README by @github-actions[bot] in #38493

Full Changelog: v0.79.4...v0.79.5