chore: remove internal team-docs from main - #42
Merged
Merged
Conversation
Session: 2026-02-13-v040-merge-cleanup Requested by: Brady (bradygaster) Changes: - logged session to .ai-team/log/2026-02-13-v040-merge-cleanup.md - merged 3 decisions from inbox into decisions.md (MCP integration, context optimization, plugin marketplace) - deleted inbox files after merging - propagated team updates to fenster and keaton agent history files
16 tasks
This was referenced Mar 16, 2026
This was referenced Mar 22, 2026
joniba
pushed a commit
to joniba/squad
that referenced
this pull request
Mar 26, 2026
…ct, format) Files cherry-picked from branches squad/2-filter-messages, squad/3-extract-decisions, and squad/4-format-summary. Original PRs bradygaster#31, bradygaster#32, bradygaster#42 had scope pollution from the worktree clobbering problem. Closes bradygaster#2, bradygaster#3, bradygaster#4 Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This was referenced Apr 3, 2026
17 tasks
bradygaster
added a commit
that referenced
this pull request
Sep 1, 2026
Both activation paths could report labels that were never applied, and the
`Activation bindings:` block specified JSON the agent could not produce.
Over-claim by attribution. `squad-plan-activate` Label Pre-flight Step 8 let a
summary name a `squad:{agent}` label once "that issue's `create-issue` call
returned successfully carrying it". `create-issue`'s `labels:` field cannot land
a label the repository lacks — the failure #1959 fixed — so that sentence
licensed reporting labels that never existed. Both paths now condition a
reported label on an accepted `add_labels` call carrying it for that same
issue, targeted by the item's own temporary ID or, for a reused item, its
verified real number. A successful `create-issue` is stated to be no evidence.
Invalid bindings JSON. The block required bare `{created task issue number}`.
The agent never learns a created issue's real number during its turn, and
gh-aw's temporary-ID substitution is a plain text replacement over the whole
comment body that does not skip fenced code blocks and keeps the `#`. A bare
`"issue":#aw_task1` becomes `"issue":#42` — invalid JSON that fails the entire
block. Verified against the pinned runtime (github/gh-aw-actions@v0.87.2,
setup/js/temporary_id.cjs). Quoting is the narrowest correct fix:
`"issue":"#aw_task1"` becomes `"issue":"#42"`, which parses. No new safe job,
no temporary_id_map plumbing, and no inferred numbers.
Runtime limitation, stated rather than worked around: safe outputs are applied
in a post-agent job, so a run has evidence only that a call was accepted for a
specific target, never the GitHub API result. "Accepted" is the strongest
honest claim; the prose forbids saying a label was verified, confirmed, or
checked. Under-claiming is rejected too — an accepted operation may not be
reported as an omission — and the required `Non-roster agent values` handling
from the base stack is preserved and made two-directional.
The post-activation checker resolves `"#42"` and bare integers, and fails
closed on an unresolved `#aw_...` rather than skipping or repairing it.
Tests: new focused suite covering both paths; 20 of its 28 assertions fail
against the pre-fix prose. Two existing assertions that pinned the old
create-issue attribution are updated to the strictly stronger condition, with
their original intent (#1860, #1959) preserved.
Source growth guard raised 170 -> 173 KB. Measured against dev with #1966
already squash-merged, so this counts only #1963's bytes: 175 485 B = 171.4 KB.
172 KB would leave 643 B, reproducing the near-zero-margin failure the guard's
own comment warns about; 173 KB leaves 1 667 B. Not set higher, because #1964
is unmerged and pre-raising for it would hide growth that has not happened. The
ambient prompt budget is unaffected at 32 795 B = 32.0 KB against 40 KB, which
is the condition that guard names as making a raise legitimate.
Closes #1963
Parent #1957
Previously stacked on #1959 (PR #1966); that merged to dev as 9e3f6b3, so this
now targets dev directly and contains #1963's changes only.
Working as Procedures (Prompt Engineer)
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
bradygaster
added a commit
that referenced
this pull request
Sep 1, 2026
#1963) (#1967) * fix(workflows): report accepted label outcomes in activation summaries Both activation paths could report labels that were never applied, and the `Activation bindings:` block specified JSON the agent could not produce. Over-claim by attribution. `squad-plan-activate` Label Pre-flight Step 8 let a summary name a `squad:{agent}` label once "that issue's `create-issue` call returned successfully carrying it". `create-issue`'s `labels:` field cannot land a label the repository lacks — the failure #1959 fixed — so that sentence licensed reporting labels that never existed. Both paths now condition a reported label on an accepted `add_labels` call carrying it for that same issue, targeted by the item's own temporary ID or, for a reused item, its verified real number. A successful `create-issue` is stated to be no evidence. Invalid bindings JSON. The block required bare `{created task issue number}`. The agent never learns a created issue's real number during its turn, and gh-aw's temporary-ID substitution is a plain text replacement over the whole comment body that does not skip fenced code blocks and keeps the `#`. A bare `"issue":#aw_task1` becomes `"issue":#42` — invalid JSON that fails the entire block. Verified against the pinned runtime (github/gh-aw-actions@v0.87.2, setup/js/temporary_id.cjs). Quoting is the narrowest correct fix: `"issue":"#aw_task1"` becomes `"issue":"#42"`, which parses. No new safe job, no temporary_id_map plumbing, and no inferred numbers. Runtime limitation, stated rather than worked around: safe outputs are applied in a post-agent job, so a run has evidence only that a call was accepted for a specific target, never the GitHub API result. "Accepted" is the strongest honest claim; the prose forbids saying a label was verified, confirmed, or checked. Under-claiming is rejected too — an accepted operation may not be reported as an omission — and the required `Non-roster agent values` handling from the base stack is preserved and made two-directional. The post-activation checker resolves `"#42"` and bare integers, and fails closed on an unresolved `#aw_...` rather than skipping or repairing it. Tests: new focused suite covering both paths; 20 of its 28 assertions fail against the pre-fix prose. Two existing assertions that pinned the old create-issue attribution are updated to the strictly stronger condition, with their original intent (#1860, #1959) preserved. Source growth guard raised 170 -> 173 KB. Measured against dev with #1966 already squash-merged, so this counts only #1963's bytes: 175 485 B = 171.4 KB. 172 KB would leave 643 B, reproducing the near-zero-margin failure the guard's own comment warns about; 173 KB leaves 1 667 B. Not set higher, because #1964 is unmerged and pre-raising for it would hide growth that has not happened. The ambient prompt budget is unaffected at 32 795 B = 32.0 KB against 40 KB, which is the condition that guard names as making a raise legitimate. Closes #1963 Parent #1957 Previously stacked on #1959 (PR #1966); that merged to dev as 9e3f6b3, so this now targets dev directly and contains #1963's changes only. Working as Procedures (Prompt Engineer) Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> * fix(workflows): remove applied-label over-claim from the shared ontology Review on #1967 caught the exact defect this PR exists to remove, in a file the PR already touches. The `Activation bindings:` paragraph in the shared ontology said bindings record "epic labels reported as applied", while the paragraph directly below it correctly defines a reported label as an accepted `add_labels` operation that the agent never observes landing. squad.md stated the accurate contract and the ontology stated the strong one. That split matters because the ontology is the artifact contract the deterministic checker consumes and the file most likely to be read standalone: a consumer reading only that paragraph gets the claim the runtime cannot justify. Left as prose-only drift it would have turned one consistently-wrong place into two inconsistently-wrong ones. Reworded to the accepted-operation semantics used everywhere else, pointing a standalone reader at the definition below it. Guarded against re-drift with a negative assertion over the ontology, mirroring the guard the suite already applies to squad.md. The match is shape-targeted rather than a ban on the word "applied": the same file legitimately says safe outputs "are applied after the agent turn", which is the justification for the weaker claim, so a blanket match would forbid the correct prose too. Verified by mutation — restoring the old wording fails the new test, and only that test. Also pins the local `gh aw` install hint to v0.87.10, matching the pin in .github/workflows/squad-ci.yml, so local strict-compile and lock output match CI. The separate `gh-aw-actions@v0.87.2` citation is left as-is: that is the pinned runtime action whose temporary_id.cjs this change was verified against, which is a different artifact from the CLI extension, and v0.87.2 is still what .github/workflows references. Source growth re-measured after the edit: 175 519 B = 171.4 KB, 1 633 B under the 173 KB guard, so the guard is unchanged. Ambient prompt unaffected. Closes #1963 Parent #1957 Working as Procedures (Prompt Engineer) Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
bradygaster
added a commit
that referenced
this pull request
Sep 2, 2026
…g check FIDO rejected the first revision of #1980 with two reproduced defects in assertAcceptedOnlyLabelWording (scripts/check-agent-binding.mjs): 1. False negative: NEGATION_NEARBY matched a negation anywhere on the whole line, so an unrelated negation earlier in the line (e.g. "No issues were skipped") blanket-suppressed a real, separate certainty claim later in the same line ("Label squad:kint was verified for #42"). 2. False positive: a forbidden word describing an unrelated subject sharing a line with a label token ("its verified real number" describing a reused issue number, not the label operation) was incorrectly flagged. Fix: split each line into clauses on clause/sentence-ending punctuation (., ,, ;, :), protecting squad:{agent} tokens so their embedded colon is never mistaken for a clause boundary. Label-operation context, the forbidden word, and any negation must now all be found within the *same* clause before a claim is flagged. This lets an unrelated negation in a different clause fail to suppress a real claim, and lets a forbidden word in a clause that carries no label-operation context correctly fall out of scope, without weakening the existing quoted-title/table-row/code-fence/substring/negation guards or the six forbidden standalone certainty claims (applied, received, landed, verified, confirmed, checked). Adds two permanent regression tests reproducing FIDO's exact reported strings in test/gh-aw-activation-artifact-integrity.test.ts. Testing: - npx vitest run test/gh-aw-activation-artifact-integrity.test.ts — 90/90 passed (88 previously + 2 new regression tests) - npx vitest run test/check-agent-binding.test.ts test/gh-aw-activation-summary-outcomes.test.ts test/gh-aw-activation-capacity.test.ts test/gh-aw-quality.test.ts test/gh-aw-activate-roster-binding.test.ts test/gh-aw-agent-binding-correspondence.test.ts test/gh-aw-activation-artifact-integrity.test.ts — 377/377 passed - npx vitest run (full suite) — only pre-existing, unrelated failures remain (externalized-state CLI tests), confirmed identical on the pre-revision commit - npx eslint scripts/check-agent-binding.mjs test/gh-aw-activation-artifact-integrity.test.ts test/gh-aw-activation-capacity.test.ts — clean - npm run build — succeeds; build-metadata/version-bump and skill-template CRLF sync side effects reverted before commit, not part of this diff Scope: only scripts/check-agent-binding.mjs and test/gh-aw-activation-artifact-integrity.test.ts touched, per FIDO's required narrow revision. Closes the FIDO REJECT on #1980. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
bradygaster
added a commit
that referenced
this pull request
Sep 2, 2026
main() filtered binding.issue/epic_issue with Number.isInteger, but compliant activation artifacts write these as quoted "#42" strings per the resolveIssueReference() contract. That produced an empty issues list, skipped label fetching entirely, and made validateActivation() fail with "labels could not be resolved" for otherwise-valid bindings. Add extractIssueNumber(), a non-throwing counterpart to resolveIssueReference() that also accepts the "#42" string form, and use it when building the label-prefetch list in main(). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
bradygaster
added a commit
that referenced
this pull request
Sep 2, 2026
…t A) (#1980) * fix(gh-aw): fast-path /squad activate artifact integrity (E4 preflight A) Closes the gap where the recommended /squad activate fast path (squad-plan-accept, artifacts plan-accepted/phases-accepted) created and labeled issues identically to the granular /squad plan activate path but was not covered by the Activation bindings: contract, the deterministic checker, or the CI collector. - workflows/squad.md: fast path Step 4 now requires the same non-empty Activation bindings: JSON block (shape/quoting/omission semantics) as squad-plan-activate. Renamed both paths' label-reporting heading to the identical "Label operations accepted" text. Reworded the "label set it should have received" trap phrase to drop the forbidden certainty word "received" while preserving meaning. - workflows/shared/squad-planning-ontology.md: the bindings mapping is now documented as mandatory for phases-accepted/plan-accepted too, not just phases-activated/activated. - scripts/check-agent-binding.mjs: ACTIVATION_ARTIFACTS now includes plan-accepted/phases-accepted so missing/empty bindings fail closed for fast-path artifacts exactly like granular ones. Added assertAcceptedOnlyLabelWording(), which rejects standalone certainty claims (applied, received, landed, verified, confirmed, checked) in label-operation reporting. It is scoped to lines that actually mention label vocabulary, strips fenced/inline code and quoted strings first, skips markdown table rows, and treats explicit negations as compliant -- never a blanket whole-comment scan -- so quoted titles, unrelated sections, negations, and substrings (unverified) don't false-positive. Wired into main()'s per-comment loop. - .github/workflows/squad-agent-binding-check.yml: the collector filter matched only /activated/i, which a plan-accepted/phases-accepted comment never contains, so fast-path artifacts were silently never passed to the checker. Now matches the squad_artifact field precisely for all four activation artifact types. - test/gh-aw-activation-artifact-integrity.test.ts (new): heading parity, fast-path bindings-contract presence + mutation kills against committed source, checker/runtime parity across all four artifact types (missing and [] bindings), a full parseStructuredData+validateActivation pipeline test against realistic comment strings (including bindings-block deletion/emptying), parameterized forbidden-word rejection (6 words x case/punctuation), negative tests for quoted titles/table rows/unrelated sections/negations/substrings, and collector-regex parity/regression tests. - test/gh-aw-activation-capacity.test.ts: updated the one existing assertion pinned to the reworded trap phrase. Out of scope per the E4 preflight package A brief: workflow discriminators, docs sequencing, draft PR UX, and all other E4 findings. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix(gh-aw): scope negation/claim detection to clauses in label-wording check FIDO rejected the first revision of #1980 with two reproduced defects in assertAcceptedOnlyLabelWording (scripts/check-agent-binding.mjs): 1. False negative: NEGATION_NEARBY matched a negation anywhere on the whole line, so an unrelated negation earlier in the line (e.g. "No issues were skipped") blanket-suppressed a real, separate certainty claim later in the same line ("Label squad:kint was verified for #42"). 2. False positive: a forbidden word describing an unrelated subject sharing a line with a label token ("its verified real number" describing a reused issue number, not the label operation) was incorrectly flagged. Fix: split each line into clauses on clause/sentence-ending punctuation (., ,, ;, :), protecting squad:{agent} tokens so their embedded colon is never mistaken for a clause boundary. Label-operation context, the forbidden word, and any negation must now all be found within the *same* clause before a claim is flagged. This lets an unrelated negation in a different clause fail to suppress a real claim, and lets a forbidden word in a clause that carries no label-operation context correctly fall out of scope, without weakening the existing quoted-title/table-row/code-fence/substring/negation guards or the six forbidden standalone certainty claims (applied, received, landed, verified, confirmed, checked). Adds two permanent regression tests reproducing FIDO's exact reported strings in test/gh-aw-activation-artifact-integrity.test.ts. Testing: - npx vitest run test/gh-aw-activation-artifact-integrity.test.ts — 90/90 passed (88 previously + 2 new regression tests) - npx vitest run test/check-agent-binding.test.ts test/gh-aw-activation-summary-outcomes.test.ts test/gh-aw-activation-capacity.test.ts test/gh-aw-quality.test.ts test/gh-aw-activate-roster-binding.test.ts test/gh-aw-agent-binding-correspondence.test.ts test/gh-aw-activation-artifact-integrity.test.ts — 377/377 passed - npx vitest run (full suite) — only pre-existing, unrelated failures remain (externalized-state CLI tests), confirmed identical on the pre-revision commit - npx eslint scripts/check-agent-binding.mjs test/gh-aw-activation-artifact-integrity.test.ts test/gh-aw-activation-capacity.test.ts — clean - npm run build — succeeds; build-metadata/version-bump and skill-template CRLF sync side effects reverted before commit, not part of this diff Scope: only scripts/check-agent-binding.mjs and test/gh-aw-activation-artifact-integrity.test.ts touched, per FIDO's required narrow revision. Closes the FIDO REJECT on #1980. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> * fix(gh-aw): resolve quoted issue references before prefetching labels main() filtered binding.issue/epic_issue with Number.isInteger, but compliant activation artifacts write these as quoted "#42" strings per the resolveIssueReference() contract. That produced an empty issues list, skipped label fetching entirely, and made validateActivation() fail with "labels could not be resolved" for otherwise-valid bindings. Add extractIssueNumber(), a non-throwing counterpart to resolveIssueReference() that also accepts the "#42" string form, and use it when building the label-prefetch list in main(). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * test(gh-aw): cover quoted activation references Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
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
1 participant
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.
Removes internal team content (proposals, human-evals, demo-script, release-process) from tracked files. Blog posts remain.
Requested by Brady.