Add SDK evolution agent - #7
Merged
Merged
Conversation
ebarti
force-pushed
the
sdk-evolution-agent
branch
from
June 21, 2026 21:02
f40f37e to
c57e2e7
Compare
ebarti
marked this pull request as ready for review
June 21, 2026 21:03
ebarti
force-pushed
the
sdk-evolution-agent
branch
2 times, most recently
from
June 21, 2026 22:39
3a4a5c3 to
0052ff2
Compare
ebarti
force-pushed
the
sdk-evolution-agent
branch
from
June 22, 2026 08:12
0052ff2 to
2d1d2a2
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
python -m examples.sdk_evolution_agent.AgentTask,RuntimeRegistry, output schemas, permission profiles, event sinks, and structuredAgentResulthandling.UV_EXCLUDE_NEWER, API snapshot/diff helpers, direction/architecture/review stages, recursive self-adaptation gates, local reports, and optional draft PR plumbing.CODEX_HOME=~/.codex_agent_runtime_sdkfor the SDK evolution agent's Codex runtime, creating the directory with private permissions before launch.finishtool so structured output can complete without unrelated workspace tool use.Real Runtime Validation
Current full SDK evolution-agent runs completed through two real runtimes:
Report from the pre-isolated Codex home validation:
After adding
CODEX_HOME=~/.codex_agent_runtime_sdk, a fresh isolated Codex home was created successfully but the real Codex run correctly failed with 401 until that new home is authenticated through supported Codex login/API-key/access-token flows. This PR does not copy or scrape credentials from the user's normal Codex home.Report:
The Antigravity run was executed from a non-hidden workspace copy because the Google local harness rejects hidden
.codexworktree paths. It completed successfully after the stage permissions were narrowed to thefinishtool for report-only reasoning stages.A real Claude adapter smoke test also completed through the local configured provider auth:
Provider availability diagnostics during validation:
claude-agent-sdk: available withauth_source=google-vertex-ai.codex-agent-sdk: available with provider-owned local auth; isolatedCODEX_HOMErequires its own supported auth setup.antigravity-agent-sdk: available withauth_source=application-default-credentials.Bedrock support was verified at the adapter/configuration boundary, not with a live AWS Bedrock invocation in this environment. The PR adds Claude runtime env pass-through for
CLAUDE_CODE_USE_BEDROCK=1and AWS SDK credential-chain configuration, Codex env pass-through plusmodel_provider=amazon-bedrockdiagnostics, tests for both paths, and docs pointing users to the supported vendor auth mechanisms.Validation
env -u UV_EXCLUDE_NEWER uv run ruff check .env -u UV_EXCLUDE_NEWER uv run mypyenv -u UV_EXCLUDE_NEWER uv run pytest(93 passed, 3 skipped)UV_PROJECT_ENVIRONMENT=/tmp/ark-ci-core-venv uv run mypyandUV_PROJECT_ENVIRONMENT=/tmp/ark-ci-core-venv uv run pytest(84 passed, 12 skipped)openspec validate add-sdk-evolution-agentenv -u UV_EXCLUDE_NEWER uv run python -m examples.sdk_evolution_agent --runtime codex-agent-sdk --refresh-preview --report-dir /tmp/ark-sdk-evolution-real-codex-current/opt/homebrew/bin/timeout 300 /Users/eloibarti/.codex/worktrees/b0df/agent-runtime-kit/.venv/bin/python -m examples.sdk_evolution_agent --runtime antigravity-agent-sdk --refresh-preview --report-dir /tmp/ark-sdk-evolution-real-antigravityClaudeAgentRuntimewith the configured Vertex auth.Notes
The agent defaults to report-only mode and blocks implementation when reviewer, capability, evidence, or recursive self-adaptation gates fail. It does not auto-merge, auto-publish, or scrape unsupported credentials.