Repository navigation
feat(cli): plan headroom check and one-key artifact note - #1148
Merged
Merged
Conversation
Collaborator
|
Review (Birfy) Tip SHA: 724d647
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #1113.
What changed
plancatches two avoidable spends before they are paid for; a plainplanstill sends nothing.
--baseline-sample N(opt-in) scores the seed artifact on the first N tasksbefore the run is quoted, and prints the sample's own cost first (
baseline sample: scoring the seed on up to N task(s) costs N agent call(s) (~$X)). Aseed at or above
--saturation(default 0.90) printsno headroom,withholds the paid quote — the
plan: ... up to N agent callsline and thenext:step — printsrefused: no headroom ...and exits 1.--forcequotes the run anyway but keeps
ready: falseplus the reason in thepayload: force buys the estimate, not a different verdict, so a host
following
readycannot auto-start a run the plan says has nothing tolearn.
--jsoncarries the sample asbaseline(sample, score, saturation,headroom) and
ready: falseon a refusal.(
SingleSlot, a one-categoryKeyedRules, a one-fileFileTree): everyworker proposal targets that key, contradicting pairs collapse to one
candidate, so
n_workersis best-of-N selection, not merging, and the notenames the fix (several keys, several files,
AppendRules). Content-addressedstrategies stay quiet, and so does a bundle that installs the reflective
merge pair or an
aggregator_factory(plan: the best-of-N selection warning fires for gepa, whose Pareto pool does not collapse proposals #1039). The pilot report card printsthe same sentence once (
notes, including--dry-run), from the one sharedhelper.
Quiet pins, so the note cannot over-fire:
test_plain_plan_still_samples_nothing,test_a_multi_key_artifact_says_nothing_about_merging,test_the_pilot_card_is_quiet_on_a_multi_key_artifact, plus the existingtest_plan_says_when_workers_buy_selection_rather_than_mergingandtest_plan_selection_warning_quiet_for_an_aggregator_factory(tests/test_integrations.py), unchanged.
evolveis unchanged; no model or network call without the flag.Verification at the tip
Tip SHA: 724d647
Ran:
e42d400e(live main at open), clean tree plus only the newtest file ->
10 failed, 3 passed in 7.98s(failing set byte-identical at00b46e1e,10 failed, 3 passed in 16.24s); every flag-dependent rowdies at argv level (
agentdescent: error: unrecognized arguments: --baseline-sample 4->SystemExit: 2), the one-key note row on theshared helper's sentence, the pilot row on
assert 0 == 1(no note atmain); the 3 passing rows are the pins that must not move.
pytest -q tests/test_plan_headroom_shape.py-> pass (13 passed)pytest -q tests/test_plan_headroom_shape.py tests/test_plan_text_output.py tests/test_plan_probe.py-> pass (37 passed)pytest -q tests/test_integrations.py tests/test_pilot.py tests/test_plan_error_output.py tests/test_strategy.py tests/test_tree_strategy.py-> pass (160 passed, 2 skipped, 1 failed:test_the_launcher_install_writes_ignores_a_shadowing_cwd— stale shared-venv launcher on this host, reproduced on pristined4b66cfa)python -m tools.gen_api_docs --check-> pass (docs/api.md is up to date)python -m tools.changelog_fragments check-> pass (65 changelog fragment(s) OK)Not run:
pytest -q(full) -> 22 failed, 7673 passed, 61 skipped, 10 errors on this host (no Docker, HOME/TMPDIR not redirected, stale shared-venv launcher); the 11 apply/backup files re-run under a redirected HOME -> 69 passed,test_wheel_smoke-> 7 passed; CI at this tip is authoritative.mkdocs build --strict-> mkdocs not installed on this host;docs/start.mdis prose only; thebuildcheck covers it.Review fixes at this tip
--saturationis validated only when--baseline-sampleis present, so aplain
plan --saturation 0is inert instead of exit 2, and an out-of-rangevalue with a sample is an input error. Rows:
test_a_saturation_without_a_sample_changes_nothing,test_an_out_of_range_saturation_is_an_input_error.ready: falsein--json. Row:test_a_forced_json_plan_still_says_not_ready.Written-by: AgentDescent Dev-1
Bot: AgentDescent Dev-1