Skip to content

fix: complete V3 execution isolation and release candidate validation - #328

Open
EvanProgramming wants to merge 220 commits into
mainfrom
Evan/v3-panstar-finalization-20261111
Open

EvanProgramming wants to merge 220 commits into
mainfrom
Evan/v3-panstar-finalization-20261111

Conversation

@EvanProgramming

@EvanProgramming EvanProgramming commented Nov 12, 2026 •

Copy link
Copy Markdown
Owner

V3 release candidate

The signed candidate is ebe7173d86d15fef133bfb508c16532541e12e05. The obsolete-assumption check compares the test target and fixture workspace, with a narrow allowance for standard unittest output options. It rejects changed targets, test selectors, other working directories, environment overrides and additional commands. Verification still requires the original failing receipt, cancellation of the seeded task in sequence and a passing receipt bound to the completed replacement task.

Independent replay accepted the two recorded complete sequences and rejected the recording with premature cancellation. The benchmark also retains payload-free source locations for provider contract failures. Those diagnostics leave failure decisions unchanged.

Validation

  • 287 focused tests ran with four environment-specific skips. The candidate passed protected replay of both planning scenarios, including the original verbose failed test and subsequent verification.
  • Exact-candidate six-platform acceptance and isolation are running.
  • DeepSeek Flash is fixed for the 180 core and 54 planning rows. V4 Pro is authorized only in the Auto arm of the separate 36-row routing experiment. Previous campaigns and diagnostics remain separate from formal evidence.
  • The four live gates and main update remain pending. V3 remains unpublished.

@coderabbitai

coderabbitai Bot commented Nov 12, 2026 •

Copy link
Copy Markdown

Important

  • Trigger review

This repository does not receive automatic reviews because it has fewer than 10 stars.

Run configuration

  • Source mode: Auto
  • Repository: Unavailable
  • Branch: Unavailable
  • File: No configuration file from this repository applied
  • Commit: Unavailable
  • Layers: defaults
  • Review profile: CHILL
  • Plan: Advanced
  • Run ID: 1ba95e52-df08-4323-aed2-00b2c61343a8
  • Autofix · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

Share

@chatgpt-codex-connector

chatgpt-codex-connector Bot commented Nov 12, 2026 •

Copy link
Copy Markdown
Codex Review Summary: ✅ Completed

This comment shows the latest Codex review activity on this pull request.

Review Status Commit Review trigger
📝 Code Review ✅ Completed 2026-11-12T03:54:01.792376Z 1fd3f27 PR opened
ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 1fd3f270ef

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment on lines +923 to +928
data = receipt.tool_result.data if receipt.tool_result is not None else None
if (isinstance(data, dict) and isinstance(data.get("content"), str)
and data.get("truncated") is False):
read_content = data["content"]
else:
criterion_status = "unavailable"

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Preserve complete read evidence before archiving tool output

When a successful read_file result exceeds the 12,000-character serialized-output threshold, _make_execution_receipt replaces its data with an artifact reference before this check runs. Consequently, even a complete read with a matching acceptance predicate lacks content and truncated here and is marked unavailable. For example, a roughly 7 KB file containing the required text cannot satisfy its Working Plan read criterion, and reading the artifact cannot satisfy the original read_file contract either. Retain the trusted complete content for predicate evaluation separately from the bounded provider/journal representation.

Useful? React with 👍 / 👎.

Comment on lines +186 to +187
if sum(handle.process.poll() is None for handle in self._handles.values()) >= 32:
raise RuntimeError("session process handle limit reached")

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Bound retained handles when allowing completed-process replacement

In a long-lived session that repeatedly launches background commands, counting only running processes removes the previous bound on retained handles: every completed handle remains in _handles, and neither completion nor close() evicts it. Each handle retains up to one million characters from each output stream, so sequential commands can now grow session memory without limit despite never approaching 32 concurrent processes. An isolated run confirmed that 40 completed commands leave 40 retained handles and zero active processes. Add bounded retention or eviction for completed handles alongside the concurrent-process limit.

Useful? React with 👍 / 👎.

This branch has not been deployed

No deployments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

review: high ghfind author score; see https://ghfind.com

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant