Repository navigation
PR-8: verified viability probes for three targeted SDK/harness candidates (2026-09-22) - #70
Merged
seathatflowsinourveins merged 3 commits intoSep 22, 2026
Conversation
…andidates Adds the sanitised receipts and independent verifications of three bounded probes on the WSL2 host (evidence/artifacts/sdk-runtime-coverage-20260922/ probes-20260922.json), a viability_probes block in the coverage ledger, a Markdown section and a task-record note. The TypeScript Agent SDK 0.3.280 ran on the native Claude Code login with no API key (fixture write and a resumed session), so its api_key_required C1 label does not hold on this host; cli-agent-orchestrator v2.5.1 launched a plan-mode worker on the native login but misreported its waiting state; the agent-orchestrator v0.13.0 daemon ran headless on loopback but read the host's Codex account unprompted. All three receipts were partially confirmed by the verifier and its corrections are recorded; no disposition changes. Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
… summaries Resolves the PR #70 review: the agent-orchestrator daemon imported the host Codex login (refresh token included) into its probe data directory without being asked, which the verifier had missed; the ledger, Markdown table and task note now carry it, and the probe copy was deleted. The API-key wording now says the variables were reported unset by the executors and logged only for the Anthropic variables in the TypeScript SDK run. The Markdown rows carry every defect the verifier named, the headless and isolation wording matches the ledger, the remaining home-dir leftovers are listed, and session-id prefixes, the subscription tier and the usage line are redacted from the artifact. Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
seathatflowsinourveins
deleted the
claude/sdk-coverage-probes-20260922
branch
September 25, 2026 18:47
5 tasks done
2 tasks done
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
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.
Follow-up to #68: the verified viability probes for three targeted SDK/harness candidates.
Adds
evidence/artifacts/sdk-runtime-coverage-20260922/probes-20260922.json(sanitised executor receipts plus the independent verifier's findings and corrections), aviability_probesblock in the coverage ledger, a Markdown section and a task-record note.query()drove the nativeclaudebinary withapiKeySource: "none"; fixture write and a resumed sessionallowedToolsonly auto-approves, so every host tool was exposed and host SessionStart hooks ran (nosettingSources/tools); session files and ai-memory hook rows written under the user homeapi_key_requiredC1 label does not hold on this host; stays keep_but_compareawslabs/cli-agent-orchestratorv2.5.1CAO_HOME_DIRrelocated CAO's own state (not the worker's); plan-mode Claude worker on the native loginidle;cao shutdownhung; worker CLI state written under the user homeuntrivial-ai/agent-orchestratorv0.13.0ao daemonran with no Electron process on loopback and stopped cleanly (display independence untested:DISPLAYset)Evidence class: native execution on one WSL2 x86_64 host, pinned versions in a scratch prefix, bounded runner, native Claude login (API-key variables reported unset by the executors, logged only for the Anthropic variables in the TypeScript SDK run); each receipt verified against raw logs (all partially confirmed; the verifier's corrections are recorded). Viability only; no disposition changes; nothing promoted.
Review: independent evidence-reviewer pass found the credential import and several summary overclaims; fixed in the second commit.
Gate:
validate.pypassed (1,764 hashed files, 140 receipts);build_ecosystem.py --checkandvalidate_catalogs.pypassed;python3 -m unittest1,428 OK (204 skipped); guarded Gitleaks no leaks.🤖 Generated with Claude Code