Merge pull request #2813 from Hack23/copilot/update-claude-opus-versions

Switch agentic workflows to claude-opus-4.8 (translation stays sonnet-4.6)

Author: pethers

.github/copilot-instructions.md

@@ -145,11 +145,12 @@ runtimes:
 ```
 
 ### Engine Configuration (All Workflows)
-All agentic workflows declare a Sonnet-class model:
+The 13 analysis/article-generating news workflows declare the Opus-class reasoning model; the high-volume `news-translate` fan-out keeps the faster Sonnet-class model:
 ```yaml
 engine:
   id: copilot
-  model: claude-sonnet-4.6        # Faster than opus 4.7 — adopted in the v0.71.3 refactor for throughput within the 60-min budget; carried forward to v0.74.3
+  model: claude-opus-4.8          # Content/analysis workflows — strongest reasoning for the 23-artifact pipeline
+  # news-translate.md keeps:  model: claude-sonnet-4.6  — faster throughput for high-volume translation fan-out
   # Note: engine.mcp.session-timeout was removed in the v0.71.3 era due to MCP Gateway v0.3.1 rejecting it; the v0.74.3 lock files now run MCP Gateway v0.3.9 — re-test before re-enabling.
 ```
 

.github/skills/gh-aw-mcp-configuration/SKILL.md

@@ -1793,7 +1793,7 @@ For Copilot coding agent sessions (not agentic workflows), MCP servers are confi
 - [ ] Implement graceful degradation
 - [ ] Use timeout for all MCP operations
 - [ ] **Prefer `repo-memory:` and `cache-memory:` over `@modelcontextprotocol/server-memory`** — gh-aw native tools are persistent across runs; generic MCP memory is ephemeral per process
-- [ ] **Skip `@modelcontextprotocol/server-sequential-thinking`** — modern LLMs (Claude Opus 4.7, GPT-5) have native CoT; it wastes context tokens
+- [ ] **Skip `@modelcontextprotocol/server-sequential-thinking`** — modern LLMs (Claude Opus 4.8, GPT-5) have native CoT; it wastes context tokens
 
 ---
 

.github/skills/threat-modeling/SKILL.md

@@ -656,7 +656,7 @@ Per ISMS Threat_Modeling.md § 7, all Hack23 projects maintain comprehensive thr
 - Chart.js/D3.js dashboard vulnerabilities
 - CSV data integrity threats (CIA platform data)
 - AWS CloudFront and S3 infrastructure threats
-- Agentic workflow threats (Claude Opus 4.7 news generation)
+- Agentic workflow threats (Claude Opus 4.8 news generation)
 
 **Use Riksdagsmonitor as reference for:**
 - Static website threat modeling

.github/workflows/README.md

@@ -109,7 +109,7 @@ Every news workflow declares the **same** tool & runtime surface for parity, res
 | Field | Value | Purpose |
 |-------|-------|---------|
 | `runtimes.node.version` | `"26"` | Pinned Node 26 for IMF CLI + render scripts |
-| `engine.id` / `engine.model` | `copilot` / `claude-sonnet-4.6` | Faster Sonnet model (adopted in the v0.71.3 refactor for throughput within the 60-min budget; carried forward to v0.74.3 — GPT-5.4 / GPT-5.4-mini eligibility now resolved upstream per v0.74.3 release notes #31695 + #32197 but not yet A/B-tested on this repo) |
+| `engine.id` / `engine.model` | `copilot` / `claude-opus-4.8` (13 analysis/article workflows); `claude-sonnet-4.6` (`news-translate` only) | Opus reasoning model for the 23-artifact analysis pipeline; the high-volume translation fan-out keeps the faster Sonnet model. (Sonnet was the repo-wide baseline through v0.74.3; GPT-5.4 / GPT-5.4-mini eligibility resolved upstream per release notes #31695 + #32197 but not yet A/B-tested here.) |
 | `engine.mcp.session-timeout` | ~~`1h`~~ **removed** | Was added in gh-aw v0.71.3 and rejected by MCP Gateway v0.3.1. v0.74.3 lock files now ship MCP Gateway v0.3.9; re-acceptance has not yet been validated on this repo, so the field stays removed until verified. |
 | `tools.github.toolsets` | `[all]` | Full GitHub MCP surface (issues, PRs, repos, code-search, actions, releases, discussions, …); see [`github-tools.md`](https://github.com/github/gh-aw/blob/main/docs/src/content/docs/reference/github-tools.md) |
 | `tools.bash` / `tools.edit` / `tools.web-fetch` / `tools.agentic-workflows` | enabled | Full local tool surface; `web-fetch` reaches non-MCP public sources (`statskontoret.se`, `riksdagsmonitor.com`) through the AWF firewall |

.github/workflows/news-committee-reports.lock.yml

@@ -282,7 +282,7 @@ steps:
       default-analysis-depth: deep
 engine:
   id: copilot
-  model: claude-sonnet-4.6
+  model: claude-opus-4.8
 ---
 
 # 📋 Committee Reports