Conversation
Adds `tests/lint/prose_budget.py`: a stdlib-only measurement of the essay-shaped prose in `src/coder_eval` — docstrings over 150 words (Typer commands exempt) plus comment runs of 3+ lines — gated against a module baseline of 79,754 words. It also resolves every `Rationale: <path> § <heading>` pointer, and under `--assert-code-unchanged <ref>` proves a commit moved prose only, by comparing the docstring-stripped AST and the multiset of functional directive comments. The gate is wired in both seams: `make docs-budget` / `make verify`, and the `quality-gate` job in pr-checks.yml — CI restates every step and never invokes `make`, so the Makefile line alone would gate nothing on a PR. Relocates the 12 sections of `.claude/architecture-notes.md` verbatim into `.claude/notes/<subsystem>.md` and deletes it, so rationale has exactly one home and the tree has exactly one index. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01JcdMjPKFc2wdg4J6Ezg4E2
Cuts the four densest files in the tree from 6,874 essay words to 533,
leaving the caller-facing contract and the couplings a future editor
would break, and moving the design rationale to
`.claude/notes/{timing,permissions,persistence}.md`.
Kept in the source: the `timing.ts` parity claim and its shared fixture,
`TurnClock`'s not-for-deadlines hazard, the raw-total ordering hazard and
its division guard, the stacked-window contract, and every CE reference
whose text stayed. Deleted: history git already holds, and `TurnClock`'s
per-harness roster, which `docs/agents/HARNESS_PARITY.md` owns.
Also corrects a stale relocated claim: the notes said the task directory
was not shielded, but `Orchestrator._communicate_with_retry` chmods it
alongside the reference.
No executable statement changed — proved per file by
`prose_budget --assert-code-unchanged`, which compares the
docstring-stripped AST and the functional directive comments.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01JcdMjPKFc2wdg4J6Ezg4E2
Cuts the five harness adapters and their eight helpers from 17,227 essay words to 4,456, and gives `.claude/notes/agents.md` the shared story the adapters kept telling five times over: the turn lifecycle, first-window seeding, per-harness generation marks, token accounting and cost resolution, why a clean exit can still be a crash, and how each CLI is reaped. Every per-harness parity claim either stays in the adapter or is already a row in docs/agents/HARNESS_PARITY.md, which the taxonomy makes the SSOT for cross-harness facts. Both SDK#24168 FIXMEs stay FIXMEs. No executable statement changed — proved per file by `prose_budget --assert-code-unchanged`. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01JcdMjPKFc2wdg4J6Ezg4E2
Cuts orchestrator.py and orchestration/ from 17,724 essay words to 3,980, extending the four sections Phase 1 relocated into orchestration.md rather than opening rival headings for the same topics: the terminal-status chain and the four grading sites under execute-vs-run, the fired-only gate and the ceiling/floor bounds under early stop. New sections cover what the orchestrator alone owns — recording the task as authored, the three separately-resolved routes, interrupt-proof teardown, restoring a PATH from an untrusted run directory, the dialog loop, embedded commands and experiment resolution. regrade's container rationale went to isolation.md, where detached grading already lives. `prose_budget` now resolves a pointer against `##` or `###`, so appending to an existing section does not force the pointer up to its parent. No executable statement changed — proved by `prose_budget --assert-code-unchanged`. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
13,289 words of essay-shaped prose across 11 files down to 2,960, with no code change (AST + directive multiset verified against the phase-start SHA). docker_runner.py 4,993 -> ~1,100 and sandbox.py 3,259 -> ~590 are the bulk. The repo's largest comment block, 34 lines on --cap-drop, is now the four COUNTERPART lines that state the coupling plus a pointer; the capability argument it carried is rationale and moved. isolation.md gains Capability drops and the anti-cheat window, What crosses into the container, Trusting what the container sends back, and The sandbox the criteria run in. Detached grading from the CLI joins the existing detached-grading section rather than rivalling it, and the in-container driver rewrite stays in orchestration.md, which already owned it. The Phase-1 relocated bullet covered nine of these topics already, so the single-home rule needed excision as well as writing: seven spans moved out of it, each left as a cross-reference to the section that now owns them. The --cap-drop/FOWNER known gap stays in docs/DOCKER_ISOLATION.md; the notes link it and say so. All eight --help outputs are byte-identical. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
…/notes 14,406 words across 34 files down to about 3,300, with no code change and no generated surface touched. Two constraints made this phase different from the others, and both were verified by parsing rather than by trusting a downstream check: the first non-blank line of every criterion class docstring, which CE033 copies into the plugin reference, is byte-identical; and no Field(description=...) string under models/ changed, which is what CE030 ripples into the task guide. The LiveVerdict determinism and monotonicity properties stay at the definition site in criteria/base.py, because they are the contract an author has to satisfy. What moved is the derivation: why CE036 replays trajectories, and what CE025 cannot see. contracts.md gains the live_verdict contract, the checker base class, route resolution, judge context and untrusted text, sub-agent judging, and recording a CLI invocation. persistence.md gains judge persistence; agents.md the sdk_options pass-through; orchestration.md the rates, the early-stop guardrail placement, and the armed gate. Docstrings that restated a Field description, or the task guide's own YAML examples, were deleted rather than moved — the guide is the source of truth. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
…de/notes 10,234 words across 30 files down to about 2,900, finishing the plan. The tree goes from 79,754 essay-shaped words to 18,163, and from 126 docstrings over 150 words to one. That one is agent.py::communicate, the plugin SPI contract every third-party agent author reads: the Args/Returns/Raises, the rule that a mid-turn failure sets pending_turn before raising and the caller rolls the counter back, and the streaming event protocol. It is the exemption the plan predicted, and the only one taken, so the 150-word bar held for the whole tree. reporting.md gains the Agent ABC contract, telemetry emission, cost joining, report rollups and the HTML twin, Harbor export, and the ATIF trajectory bridge. Two hazards the plan named had to be ADDED rather than kept: neither the pricing.py/pricing.ts mirror nor the "evalboard's static twin" parity claim was ever stated in its own source file — both lived only in CLAUDE.md. Editing one side of either pair without the other is exactly what they exist to prevent, so they now say so where the editor will be. errors/categories.py is untouched: its per-member retryability notes are the contract errors/categorization.py dispatches on, and they are one-line comments the plan puts out of scope. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
check_pointers proves a pointer RESOLVES. It cannot see the defect that actually shipped: a block replacement anchored on the wrong line leaves the tail of the replaced prose stranded after the pointer, where the $-anchored regex stops looking. The file parses, the pointer resolves, and the comment carries a severed half-sentence. Three phases of the prose-reduction work shipped that shape to review before this check existed; a fourth ran clean because the check was running from the first edit. It also reports an orphaned docstring terminator, which is worse than it looks: the file stops parsing, and the measurement silently reports it as zero words rather than failing. A docstring may still follow its pointer with Args:/Returns:/Raises: — that is the house shape, and the one case this must not flag. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
"Self-contained (inline CSS/JS, no external fonts or images)" is caller-facing — it is why the file can be opened offline and uploaded as a CI artifact — and the 7/7 rewrite dropped it while adding the static-twin claim. Both belong. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The fifth was promoted (b8b1dcf). These four are deferred with the reason, so the next person does not rediscover them: the general severed-fragment shape needs an allowlist to be usable, the single-home rule needs a similarity measure, a pointer landing unhelpfully is probably not mechanizable at all, and the generated-surface guard needs a commit-scoped diff the lint harness cannot see. The single-home one is the highest-value unbuilt guard in the notes design — it bit every phase of this run, once against a file the phase never opened. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
An audit of the finished refactor found nine places where compression either dropped a contract or, worse, replaced it with a plausible wrong reason. The bad one is `_resolve_backend_route`. Its docstring said the function raises "so it must survive -O" — true of a different function, transplanted here — while the actual contract was gone from the source AND from the notes: an explicit backend override that cannot be honored must fail loudly, not degrade to a backend the task author never asked for. A reader told the raise is only about -O can reasonably "improve" it into a fallback, which is exactly the regression the deleted sentence forbade. The rest: - write_text_atomic claimed mode 0o644 as if guaranteed. It is a ceiling; the umask narrows it, and 0o077 yields 0600 — which breaks the docker driver, the failure the directive exists to prevent. - A NOTE in sandbox.py said three methods do not validate path traversal. Two of them go through resolve_files (and so through _within_sandbox and _reject_escaped); only list_files still does not. Someone reasoning about criterion containment from that comment reached the wrong conclusion. - enforces_permission_windows kept the clause making the window SAFE and lost the one making it REAL: without the container's DAC cap drops a mode-000 directory is still readable by root. - capture_to's copytree flags lost the reason one of them is load-bearing. - adopt no longer said criteria can still write to the adopted tree, under a docstring headlined "materializing nothing". - The docker log constants lost why there are two of them, and had no pointer. - armed_criteria_passed said "weighted score", which names a different quantity in the same class; the binarisation that makes gate_threshold=1.0 an exact equivalence was gone. - judge_context said "these tokens" with no list after it. - _build_run_command_env counted eight env facets and sets nine. The baseline rises 18,163 -> 18,549. That is the ratchet working as intended: restoring real contract is a legitimate reason to raise it, and the reason belongs here rather than in a silent constant bump. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Review B found one shape repeated six times: compression kept a categorical claim and dropped the words that made it true. Each is the only fact its comment now carries, sitting above the code someone would edit. - claude_code_agent: the task-notification guard is checked SECOND, not first. What matters is that it precedes _is_sdk_result_message. - opencode_agent: "the condition is the TELEMETRY, not the event vocabulary" — but one of the two arms IS the vocabulary, and a later comment says so. The dropped word was "alone". Deleting the arm as redundant re-opens scoring SUCCESS 1.0 on zero turns. - batch: the predicate is NOT_GRADED **or** executed. "Executed is a required half" reads as `and`, which would leave zero-iteration execute rows ungraded forever. - reference_comparison: "every failure below raises" — three branches below return a gating 0.0 on purpose, one of them carrying a CE039 noqa. - docker_runner: the stdout limit does not mirror _POST_RUN_STREAM_LIMIT; it is 256x larger, deliberately. Unifying them downward reinstates the mid-stream teardown that lost whole paid tasks. - cli_called: "harness fault, not agent behaviour" contradicted the block 50 lines down explaining that all five paths are agent-reachable. Also restores the judge ignore floor's MECHANISM: it is a copy-time control, the same list passed as copytree's `ignore`, not only an SDK setting. Without that, dropping .claude / .mcp.json from it looks redundant and lets an agent-planted settings file into the judge's own working directory. _resolve_backend_route's contract now has a home in the notes, and the docstring points at it rather than at the LiteLLM section. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
`--tmpfs` is never emitted. `_build_argv` does not construct one, `test_reference_inside_task_dir_needs_no_tmpfs_mask` asserts `not _tmpfs(argv)`, and docker_runner.py's own `_reference_mount_args` docstring opens "No tmpfs mask any more". Three of its neighbours said the opposite, two of them lines this refactor wrote. The claim predates the branch, so this is not a regression — but the refactor read every one of those lines and compressed them instead of questioning them, and it authored two new canonical homes for the falsehood. Re-ratifying it is worse than never having looked. What is actually true: the task dir is a shielded read-write COPY, so a reference embedded in it is covered by the same mode-000 window rather than hidden under a layered filesystem. `orchestration/evaluation.py`'s hard-fail was justified by the mask and by an EROFS on a `:ro` bind — both false now, and the real reason (the fallback resolves to a tree the window was not opened over) is the one that survives. Also restructures `permissions.md`'s Phase-1 blob. Its single 4,450-char line duplicated two of its own sibling sections, restated the FOWNER/CHOWN rationale that isolation.md explicitly delegates to docs/ saying "they are not restated here", and carried the tmpfs claim. All four inbound source pointers still resolve. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
_ESSAY_BASELINE_WORDS was the weakest part of the gate. It was a single tree-wide number, hand-edited eleven times in this work alone, that a reviewer had to take on trust; it let growth in one file hide behind shrinkage in another; and it said nothing at all about a file that did not exist yet. It is gone. Two rules replace it, and neither has a number anyone maintains: own-line comments per file <= MAX(20, 0.15 * file length) no docstring over 150 words of PROSE The comment budget is proportional, so deleting code takes its budget with it and a new file is governed from its first commit. Own-line only: a trailing `# noqa` is a directive and a per-member annotation on an enum is the contract a dispatcher reads — counting either would push against documenting them. The floor is what protects a constants module at one comment per constant, which is where the tree's natural maximum sits. The essay rule now counts prose, not structure: an Args/Returns/Raises block is interface documentation, and counting it pushed exactly the docstrings that document their contract best over the line. Exemptions are categorical rather than numeric — an @AbstractMethod docstring IS the contract implementers read, so the plugin SPI is covered by kind, and a new abstract method is covered automatically. The old "at most two, by fiat" allowance is unnecessary: the tree now has ZERO essays. Getting there took 44 comment lines out of 7 files. Most came out by reflowing two lines into one or cutting a section divider; the one real compression was a 22-line block in early_stop.py restating the floor bound that orchestration.md already owns, and the distractor-exclusion rule it uniquely held moved there rather than being dropped. One reflow silently merged `# pyright: reportImportCycles=false` into the prose line above it, which would have stopped pyright honouring it. --assert-code-unchanged caught it. That is the second time the directive multiset has earned its place. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
…nd clarifications Co-Authored-By: Claude <noreply@anthropic.com>
Replace the json.loads + dict.get + isinstance ladder at the host→container boundary with a Pydantic model: every field required, extra="forbid", StrictBool for grade/regrade, StrictInt for replicate_index. The host builds the model in _stage_inputs and keeps it on DockerRunner._staged_context. BREAKING CHANGE: a container image and host that disagree about the context.json keys now fail at parse time (exit 2, naming the field) instead of falling back to defaults (grade=True, host_task_file=None, the staged source_yaml). Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
…oed its contract The image version preflight now refuses instead of warning, for dockerfile_path images too, and is the single reader of the org.coder-eval.version label. The container echoes the ContainerContext it parsed into environment_info["container_contract"], written after the regrade seed so the prior row cannot overwrite it. One host guard, _assert_contract_echoed, replaces _assert_grade_honored, _assert_regrade_honored and _warn_on_version_mismatch, and quarantines a refused record to task.json.unhonored. A host grade drops a prior row's stale echo, and the echo is kept out of the rendered Environment table. BREAKING CHANGE: a driver: docker run is refused before the container starts when the image's org.coder-eval.version label is missing or differs from the host's installed coder-eval. Set ALLOW_IMAGE_SKEW=1 (not an empty string) to run a deliberately different image; a missing label is never excused. An image that predates the host→container contract is refused after the run, and its record is moved to task.json.unhonored instead of task.json.graded / task.json.rerun. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
…t-side DockerRunner._stage_inputs now stages task.yaml as the execution copy with driver: tempdir and sends the authored sandbox block in the contract as ContainerContext.authored_sandbox. The in-container entry point no longer rewrites the driver; it records authored_task from ctx.authored_sandbox, so a docker run's task.json still says driver: docker. The CE051 exemption moves with the rewrite: the two sites are now host staging and opt-in host grading. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Extract the run-summary rebuild into a printer-free orchestration/run_summary_rebuild.py (rebuild_run_summary, find_run_root) and expose it as `coder-eval report <run_dir> --rebuild`, which prints the same counts line and note. --rebuild refuses --format, --output, a task directory and a directory inside another run. The rebuilt run id now comes from the resolved directory, so `runs/latest --rebuild` records the real run id. BREAKING CHANGE: `coder-eval aggregate` is removed; use `coder-eval report <run_dir> --rebuild`. Its `-o/--output <dir>` option has no replacement: --rebuild writes in place, so gather task directories into the target directory first. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
… grade `coder-eval evaluate <task_run_dir>` now rebuilds the owning run's run.json and run.md itself after writing the verdict back, instead of telling the user to run a second command. The refresh is best-effort: any failure only warns, and the exit code is always the verdict's. find_run_root accepts only a run.json that is a coder-eval run summary (a JSON object with run_id and task_results), so a row copied into another tool's tree never overwrites that tool's run.json. rebuild_run_summary refuses to write through a symlinked run.json or run.md; both evaluate and report --rebuild inherit that, since it is their one shared write path. The refresh is skipped when the grading --run-dir sits inside the owning run, where its own task.json would count as a second row. write_run_summary now writes atomically, and the new console lines escape Rich markup in paths. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
…mmand exemption list Two review findings from the container-contract work, closed as tests: - the host compares the container's echo with its own dump, so a validator under authored_sandbox that is not idempotent across a JSON round trip would refuse every docker run; the round trip now runs over a maximal SandboxConfig; - prose_budget's _TYPER_COMMANDS kept a dead entry for the deleted aggregate command; it must now equal the commands the CLI registers. Two more candidates that need type information or are conventions are recorded in .claude/harness-candidates.md. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
…cally Phase 6 planned to declare the flags `run` and `execute` share once, through option factories. The factory module was built and produced byte-identical --help output, but review found it saved no lines and turned each new shared flag into a five-place edit, so it was dropped and cli/ is unchanged. What remains is the drift guard: a test that compares every click attribute a shared flag can show or validate between the two commands, and asserts that --resume and --format stay command-specific. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
- Strip the prior row's container_contract from the staged prior.json. An image that honors regrade but predates the echo keeps the prior environment_info, so a matching echo from an earlier identical dispatch passed as its own. - A result refused by the contract echo now leaves a synthetic ERROR task.json in place of the quarantined record, like every other container failure, so the row no longer vanishes from the next run.json rebuild. - On a detached grade, the refused task.json.unhonored is folded back from the scratch directory beside the graded row, and the error no longer suggests --allow-host-grading when the image itself was refused. - Docstrings, the stale "version checks only warn" wording, the dead None branch in _quarantine_record, the run.json environment note, and a cwd-independent task path for the evaluate refresh tests. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
uipreliga
requested review from
CarlesUIPath,
akshaylive,
bai-uipath and
tmatup
as code owners
September 15, 2026 15:02
|
Claude finished @uipreliga's task in 1m 37s —— View job Code Review
|
Collaborator
|
One thin I'm unsure about it it's behavior on custom docker images. Skills repo uses a custom docker image based on the coder-eval docker image. In this scenario, do we force consumers to set the env var? If not this PR LGTM. |
uipreliga
force-pushed
the
docs/slim-source-prose
branch
from
September 16, 2026 02:39
af5e07c to
4941681
Compare
Collaborator
Author
|
Good question — no, consumers don't need to set anything. A custom image built A consumer only hits the refusal when their base is pinned to an older coder-eval than the host wheel (or a stale Two things
One nit for anyone wiring it up: the value must be All of this is in |
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
2 participants
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.
Breaking changes
driver: dockerimage is refused before the container starts. The host reads the image'sorg.coder-eval.versionlabel. If the label is missing, or differs from the installed coder-eval, the run fails. This applies todockerfile_pathimages too. SetALLOW_IMAGE_SKEW=1(not an empty string) to run a deliberately different image; a missing label is never excused.task.json.unhonored, and a synthetic ERRORtask.jsontakes its place. This replacestask.json.gradedandtask.json.rerun.coder-eval aggregateis removed. Usecoder-eval report <run_dir> --rebuild.aggregate -o/--output <dir>has no replacement.--rebuildwrites in place; gather task directories into the target directory first.Downstream: UiPath/skills#3318 sets
ALLOW_IMAGE_SKEWon the one workflow that tests an ad-hoc image tag against the pinned wheel. It is safe to merge before this release.Summary
ContainerContextcontract.context.jsonis a strict Pydantic model: every field is required, unknown keys are refused, andgrade,regradeandreplicate_indexare strictly typed. A host/image mismatch fails with exit 2 and names the field, instead of falling back to a default.environment_info["container_contract"], after the regrade seed so a prior row cannot overwrite it. One host check,_assert_contract_echoed, replaces_assert_grade_honored,_assert_regrade_honoredand_warn_on_version_mismatch.driver: tempdirand sends the authored sandbox in the contract, sotask.jsonstill recordsdriver: dockerand the container needs no CE051 exemption.report --rebuild. A printer-freeorchestration/run_summary_rebuild.pybacks it. It refuses--format,--output, a task directory, a directory inside another run, and a symlinkedrun.json/run.md.evaluaterefreshesrun.json.coder-eval evaluate <task_run_dir>rebuilds the owning run'srun.jsonitself. It is best-effort (never changes the exit code), accepts only a coder-eval run summary on the walk up, and skips when--run-dirsits inside the run.write_run_summarynow writes atomically.run/executeoption sharing: dropped. A factory module was built and gave byte-identical--help, but review found it saved no lines, socli/is unchanged. A test now pins every shared flag as identical on both commands.Test plan
make verify: 5815 passed, 2 skipped, coverage 92.70%, pyright clean, custom lint rules passprior.json, a refused row vanishing fromrun.json, the refused record lost on the grading path)run --helpandexecute --helpbyte-identical to the pre-change baselinedriver: dockertask against a freshly builtmake docker-imageimage (0.12.1, label matches the host).tasks/agents/claude_hello_world_docker.yamlwith--type codex --model gpt-5.4: SUCCESS, 1.0, 3/3. The echo holds all 10 contract keys withgrade: true,regrade: false, andtask.jsonrecordsdriver: docker.coder-eval evaluate <row> --allow-recorded-commandsgraded in a container of the task's image, SUCCESS → SUCCESS, 3/3, exit 0. The echo showsregrade: true,started_atis unchanged (the agent did not run again),task.execute.jsonwas kept,run.jsonwas refreshed, and nograded_on_hoststamp was set.Seen during that check, not caused by this PR:
--type codexand no--model, the task's defaultclaude-sonnet-4-6went to the Azure Codex endpoint. The turn ended with 0 messages, 0 tokens anderror: null, and the row was recorded as FAILURE. The Codex adapter should record this as an error.--run-dir,evaluatewritesgrade.logandgrade.docker.logto its own newruns/<timestamp>/, not beside the graded row.Stacking
This PR is based on #177 (
docs/slim-source-prose). Merge #177 first. If its branch is deleted on merge, GitHub moves this PR tomain; if not, change the base tomainby hand.🤖 Generated with Claude Code