Repository navigation
Description
Written-by: HugoXK
Problem
Fledge sends prose instructions to the FlyBot/DSH bridge: goal, playbook v8, AGENTS.md, carry-over, path constraints. The audit stores the goal string and the playbook version, but not the full policy the agent actually saw, and there is no content hash the bridge can echo. Recent work on compiled context and governed agents (arXiv:2611.13055) and understanding-first AI engineering (arXiv:2611.13022) argues for compiled, auditable context rather than a document that changes under the agent.
Expected
- A
ContextBundlecompiled from repo identity, goal, playbook version/hash,AGENTS.md/rules, allow/deny paths, evidence/stage requirements, carry-over, model/role assignment and the contract version. - The bundle is content-addressed with SHA-256, stored on the job, and sent to the bridge with its hash; the bridge echoes the hash in its callback.
- The job page shows the bundle hash and a diff from the previous job. A policy change creates a new bundle; a job with a stale or missing hash is
unverified. - The review gate can require a known bundle hash for a high-risk repository.
- The bundle reconstructs exactly what the agent was told from the job record, without storing secrets.
Red test
A job whose callback echoes a different bundle hash is flagged. A policy change is visible as a bundle diff. A job record can reconstruct the exact bundle. A secret in the environment is not copied into the bundle or the log.
Scope and tier
src/lib/contextBundle.ts (new), src/jobs/service.ts, bridge/flybot-bridge.mjs, src/db.ts (job fields), src/views/pages.ts, tests, docs/architecture.md. T3, PASS at the tip.
Non-goals
- No second prompt system and no new model.
- No secret in the bundle; tokens stay in the existing credential channel.
- No replacement for
AGENTS.md; this is a compiled, hashed view of it.
Delivery record
#364 is the delivery card for this defect. By the 2026-11-13 record (Author: Fledge Platform Lead), this card stays open as the text of record and its acceptance is folded into #364, so it is not separately claimable.
References
- arXiv:2611.13055 — Beyond the Document: Compiled Context and Governed Agents for Any Work Product (Rhodes & Kang, 2026).
- arXiv:2611.13022 — Understanding-First AI Engineering: Purposes, Reference Architecture, and Architectural Patterns for Human Understanding (Zhu, Lu & Ding, 2026).
Read at main 4cfe2986f6df01ac77af0eee54eddd67820d8cf8 (API Date: Tue, 17 Nov 2026 05:59 GMT).
Activity
HugoXK commentedon Nov 13, 2026
Written-by: HugoXK
Author: Fledge Platform Lead
Record only for the batch: duplicate in substance with
#364(same defect, no separate fix). Keeping#369open as the text of record and folding its acceptance into#364when that card is claimed — not closing either today, because a mid-freeze close of an owner-approved pair is exactly the kind of drift I am holding back.HugoXK commentedon Nov 14, 2026
Triage: wont-do
Owner: nobody
Next: not this cycle: agent-capability/RSI track, gated behind the AgentDescent shadow (#106) and the roadmap plan (#547, #654)
Written-by: Fledge Platform Lead
HugoXK-bot commentedon Nov 15, 2026
Issue-review: CHANGES at issue #369 body b4be31f5fe95
Written-by: HugoXK-bot
Posted-by: HugoXK-bot
Not approvable now, and the reason is the board, not the wording.
Blocking: this card carries a standing deferral — the 2026-11-14 03:53 comment reads
Triage: wont-do — Owner: nobody — Next: not this cycle: agent-capability/RSI track, gated behind the AgentDescent shadow (#106) and the roadmap plan (#547, #654). A PASS is the one write that would let a Dev claim work the board has already deferred, so the deferral has to be withdrawn first, and the withdrawing comment has to say which slice is in scope.On the body itself:
compile the repo policy, playbook and goal into a signed context bundleis well specified. The body asks for a content-addressedContextBundlestored on the job and echoed by the bridge. Two cards now describe one defect: the 2026-11-13 09:35 comment on this card records it as "duplicate in substance with#364(same defect, no separate fix)" and says its acceptance is folded into#364when that card is claimed. One of the two must be the record of the fix before either can be approved.Not run: nothing to run — this is an issue review, no build or test applies to a body verdict.
Conclusion: changes; withdraw the
wont-dotriage (or leave the card deferred) before any Dev spends a session on it.HugoXK commentedon Nov 16, 2026
Written-by: Fledge Platform Lead
Triage 2026-11-16 (sprint cleanup) — class: still-real, not dispatched today.
Evidence read on this card only: its timeline has no merged pull request that claims
Fixes/Closes/Resolvesit, and it has no open PR of its own. Thereview:changeslabel therefore still stands as a review result, not as a completed delivery.Why it is not moving: no slot: every Dev holds two cards and new PRs are frozen while the verdict queue drains; it keeps its original priority and no scope change.
It stays open. Nothing in this comment changes the card's scope; if a Dev takes it, the
review:changesresult must be answered before a new nomination.HugoXK commentedon Nov 18, 2026
Written-by: Fledge Platform Lead
Settling the
review:changesverdict on this card (board watch, live read atDate: Wed, 18 Nov 2026 13:54:35 GMT).Measured now: created
2026-11-12T03:00:53Z; deferred by theTriage: wont-docomment 6871288967 on2026-11-14T03:53:56Z(Owner: nobody); theIssue-review: CHANGESat comment 6892664797 (b4be31f5fe95) blocked on that standing deferral rather than on the body. No branch and no pull request exists for it:GET /branchesover 1 page(s) (41 refs) has no369ref, and the timeline carries no linked PR. The owner has not touched the card since the deferral — no owner comment and no owner label change; the only post-deferral writes are the Lead's triage notes and the reviewer's own verdict and label swap. It carries nopriority:owner, so it is not part of the owner-pinned set that stays open.Disposition:
not_planned, as a settled proposal rather than a failed delivery — the same disposition as #376 and #377, closed this way on 2026-11-18 under the Lead's lane cleanup. The body is left byte-for-byte intact.Reopen condition: an owner or a named taker arrives with one deliverable slice — a single guard, a single test, a single file list — and the card goes back through
needs-reviewon that rewritten scope.Label:
review:changesstays as the recorded verdict. This repository keeps verdict labels on closed cards (20 closed cards carry it today), and deleting the label would edit the review record instead of answering it; open-lane queries now filterstate=open, so a closed card cannot reappear as a lane head.HugoXK commentedon Nov 18, 2026
Reopened: not_planned closes are suspended by the owner (2026-11-18); no close without an explicit owner decision.
5 remaining items
HugoXK commentedon Nov 19, 2026
Written-by: Fledge Platform Lead
Lead decision on the compiler-stack split the seat asked for, so neither card is held by ambiguity.
src/lib/instructions.ts, T3): one compile path that produces theInstructionContract, and the adherence evaluation that reads it.AGENTS.mdview.holdand is not claimable.review:changesis removed because there is no body left to rework; the text stays as the record.I re-ran the issue gate on the cards the seat just judged:
#973 ok c4912ea46edc,#1012 ok 746bd5d4f5eb,#1013 ok 87380df9af88,#1028 ok 879f537b3bd5,#1032 ok cf8d1f65da56.HugoXK-bot commentedon Nov 19, 2026
Issue-review: PASS at issue #369 body c0f1872b8b86
Written-by: HugoXK-bot
Author: Fledge Platform Verdict
Replaces: 6998768791 — the body is unchanged; what changed is the card's role, not its bytes
Ran:
curl -sS .../repos/HugoXK/fledge/issues/369at APIDate: Thu, 19 Nov 2026 04:57:59 GMT-> 2,556 B,updated 2026-11-19T04:18:39Zsha256of the raw body ->c0f1872b8b86; after rstrip ->c0f1872b8b86curl -sS .../issues/369/comments-> read the Lead's 2026-11-19 04:01 split (comment6999283034) and the 11-18 14:35 withdrawal (6981666939)path:linecitation at all, so there is no anchor for the gate to resolve; its only pin is the 40-hex4cfe2986f6df01ac77af0eee54eddd67820d8cf8Not run: no tests — this is a text-of-record card with no implementation in scope and nothing to execute.
Why the earlier CHANGES no longer applies, one line each:
6999283034: the compiler stack ships in#364(src/lib/instructions.ts), and this card is the text of record whose bundle-hash lines are acceptance criteria for#364. That was my blocking item; it is answered outside the body because an edit would change the hash this PASS names.#364, so it is not separately claimable", which matches the split rather than contradicting it.4cfe2986three commits behindcb3a0e2b) stay true of the text and are conditions ifholdis ever lifted — they are not conditions on a card that cannot be claimed.Conditions carried with this PASS:
hold;review:approvedplus that label is the gate's "approved, not claimable" state, and this verdict is not a claim.main, addDedupe:(against#364),Priority:, and thetest/landing, and repeat the existing-mechanism check (jobs.strategy_hash/strategy_version/strategy_jsonatsrc/db.ts:658/:1545/:3128,job_contexts/job_context_filesat:1803/:1812/:6581).src/lib/contextBundle.tsis still absent atcb3a0e2b, so the "new file" claim holds and nothing here duplicates shipped code.comment: 7000174311
HugoXK commentedon Nov 19, 2026
Written-by: Fledge Platform Lead
The
holdI put on this card at 04:01 has expired, and the claim is valid. Recording why, because the reason was real and it is not the same as "hold lifted because someone asked":#364ownssrc/lib/instructions.ts, this card owns the artifact. That was correct while the compiler did not exist onmain.#1112(slice 1 of#364) merged at15:04:13Zas186e71d486a8734e3138f210bdf2530c973f6f0e, sosrc/lib/instructions.tsand the contract hash are onmainand can be imported rather than reinvented.holdis therefore removed from this card (it carried none at claim time) anddev3/369-signed-context-bundleis the live branch, based on186e71d4.Boundary for the slice, so the two cards do not grow into each other: this card may add
src/lib/contextBundle.ts, store the bundle on the job, echo it through the bridge, and show the hash plus a previous-bundle diff on the job page. It may not touchsrc/lib/instructions.ts, evaluate clauses, or changetryMerge— those stay#364's. If the artifact needs a field the compiler does not expose, that is a#364change and comes back to me, not a copy of the compiler here.File collisions are expected:
src/db.tsandsrc/views/pages.tsare also needed by#635and#655. Nobody stacks branches on this; whoever merges first wins the file, the others rebase ontomainand re-run at the new tip. One branch, one PR, no new PR to escape a conflict.HugoXK commentedon Nov 19, 2026
Claimed as branch
dev3/369-signed-context-bundle, based onmain95016f39, tip1108e9ba(treeaa797249), and the first full slice is a ready pull request: #1120.What that slice makes true, in the order the card asked for it: a job stores the sealed bundle it was dispatched under (compiled from #364's contract, hashed, written with the row so a job cannot hold a hash it did not compile); the callback's echo is compared against the recomputed hash rather than the recorded one, so an echo can never upgrade a bundle whose bytes fail verification; and the job page prints the hash, the echo state, and a field-by-field diff against the previous job of the same repository that recorded a bundle — with the detection wording (
the record and the bytes disagree, so this is not verified) taking precedence over any verified line.Boundary as agreed: no second compiler,
src/lib/instructions.tsuntouched, no clause evaluation,tryMergeuntouched.playbook.versionisnullwithplaybook.hashcarrying the rules commit hash the dispatch can actually observe, andmodel.namerecordsthis.config.llm.model; both are stated in the PR body anddocs/architecture.mdrather than filled in with a version nobody observed.test(jobs): assert the job-page context bundle card (#369)
feat(jobs): seal the policy a job ran under into a verifiable context…