Harden Strands demo adapter and document live validation results#3
Merged
Conversation
- Auto-detect ANTHROPIC_API_KEY and use AnthropicModel so the demo
runs without AWS credentials; falls back to Strands default otherwise.
- Tighten runtime envelope prompt to specify exact enum values for
tool_invocations.outcome ("success", "failure", "canceled") after
the live run showed the model returning descriptive sentences.
- Add robust AgentResult text extraction with markdown fence stripping
to handle non-text content blocks in the Strands response.
- Add evidence shape guard (isinstance dict check) and outcome
normalizer for live model responses.
- Mark live runtime validation complete in docs/public-launch-checklist.md
with full run results and adapter rough edges documented.
- Exclude launch-validation/ run artifacts from git.
- Add adapter changes to CHANGELOG [Unreleased].
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
What changed
`adapters/strands/demo/run_apd_with_aer.py`
`docs/public-launch-checklist.md`
`CHANGELOG.md` — changes noted under `[Unreleased]`
`.gitignore` — `launch-validation/` run artifacts excluded
Live validation verdict
The spec, schema, and conformance comparison logic all held up under real Claude-backed execution. The one `failed-check` difference on `invoice-logging` demonstrates the comparison machinery working correctly, not a defect.
Test plan
🤖 Generated with Claude Code