Repository navigation
feat(e2e-live): the north-star run on Codex and OpenCode (--host); run-summary records the host - #38
Merged
Merged
Conversation
…n-summary records the host e2e-live.sh --host codex|opencode (make e2e-live YES=1 HOST=…) installs the plugin into the seeded repo with `aloop install <host>` and drives the host's headless CLI (`codex exec --json --full-auto`, `opencode run --format json`) with the same intent, approval and checks; models come from the host's routes. --dry-run prints the command. run-summary --host records the host, names it in the reproduce command, and records an unmeasured cost as — instead of $0.00 when the transcript has no `result` line. Test: scripts/test/e2e-live-hosts.test.py (5 checks, stub CLIs). Docs: README, OVERVIEW, ROADMAP M8, TRACKING, evidence ledger, CHANGELOG. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015QxyVf3NgwsgRyYpBgDDTC
adeelahmad
pushed a commit
that referenced
this pull request
Oct 18, 2026
…rs to the gate's suppression check (run 22) e2e-live.sh (#38) passed the Claude prompt as an argument after --allowedTools, which takes every following word, so `claude -p` got no prompt and exited in 2s ("Input must be provided"). The prompt goes on stdin again; --dry-run says so (test: e2e-live-hosts). Live run 22 (wordfreq, 361f8d7): 13/13, 16m18s, $1.14, 2 wakes, 0 plugin reads, 3 blocks. The final-gate persona failed the sprint on RED's #![allow(dead_code)] in tests/common/mod.rs by its own open-ended grep, costing a GREEN re-dispatch. The persona now names exactly assert_no_suppression's patterns and defers to `selfcheck final-gate` (test: suppression-contract.test.py; eval final-gate #4). Ledger, ROADMAP M0.8, TRACKING, CHANGELOG. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015QxyVf3NgwsgRyYpBgDDTC
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.
Requested by Adeel · project thread
Before: the north-star run (
make e2e-live YES=1) only ran on Claude Code, so M8's "measured public runs on Codex and OpenCode" had no way to be produced even on a machine with both CLIs.After:
make e2e-live YES=1 HOST=codexorHOST=opencodeseeds the same repo, installs the plugin into it withaloop install <host>, drives the host's headless CLI (codex exec --json --full-auto,opencode run --format json) with the same intent and up-front approval, runs the same checks, and ends with a ledger row whose reproduce command names the host.--dry-runprints the command without spending anything. Models come from the host's routes (Codex's are empty, so it runs the session's model unless--modelis given). A transcript with noresultline records the cost as unmeasured (—), never $0.00.How: test-first in
scripts/test/e2e-live-hosts.test.py(5 checks with stub CLIs: install happens, the right command per host, usage errors, run-summary's host record), wired intomake ci. README, OVERVIEW, ROADMAP M8, TRACKING, the evidence ledger and CHANGELOG updated; README suite count 43 → 44 (derived test).make cigreen locally. The measured Codex/OpenCode rows themselves still need a machine with both CLIs.Generated by Claude Code