Skip to content

Commit 7961993

Browse files
seathatflowsinourveinsseathatflowsinourveins
authored
Record upstream evaluation rule and context read-back waiver (#802)
### Scope Record the owner's 2026-10-06 foundation-selection rule: use upstream evidence for component choices, maintain clean installations, and verify our wiring with smoke checks and organic native counters. The decision names all six superseded gate groups, the 13-row #723 cohort, retained checks, re-scoped S4, alternatives and the upstream-change comparison that reopens a choice. Four current policy guides gain a pointer to this rule; instruction-file changes remain a CC handoff. B3's read-back ruling is an appended, dated "Amendment 2026-10-06" section in the October5 context-budget decision:23 lines inserted,0 removed. NativeStack's part is waived until retirement; the recorded NativeStack2604 pass and Skills row remain historical observations, and the co-op owns the remaining bounded SDK read-back. The CC's clarified preservation rule permits this addendum form. No existing historical or DECIDED line is edited. - Base commit: `d9eb68750311d5f888adec140723da174f9fe10c`. - Lane: `lane:foundation` (sole label). - Owned source paths: NEW `docs/decisions/2026-10-06-upstream-evidence-over-local-evaluation.md`, the appended B3 section in `docs/decisions/2026-10-05-harness-context-budget.md`, `docs/acceptance-evidence-policy.md`, `docs/convergence-architecture.md`, `docs/harness-defaults.md`, `docs/token-practice.md`, and `catalogs/foundation/upstream-surface-dispositions.json`. - The October5 record's existing text remains unchanged. Its append-only form is byte-identical to reviewed58dff931's file, SHA256 `dd3df75f9a7c2d736c476f6df07ffdb4e83e960ccfad79ba3f1826810986cbef`. Existing receipts and measured observations retain their history. - `manifests/evidence.json` registrations are in the final registry-only commit. The two active `context_management` disposition citations point to line134 after the current policy pointer. ## SOTA sources - [affaan-m/ECC](https://github.com/affaan-m/ECC/blob/2b6e839771e53096d8451a213d40dc64ec8acac0/skills/search-first/SKILL.md), commit `2b6e839771e53096d8451a213d40dc64ec8acac0`, Workflow and Decision Matrix: source-backed discovery and reuse. - [modelcontextprotocol/modelcontextprotocol](https://github.com/modelcontextprotocol/modelcontextprotocol/blob/38c84e9f93ad191d9eb26d92b945d17bd0efcaf3/docs/specification/2025-11-25/basic/lifecycle.mdx), commit `38c84e9f93ad191d9eb26d92b945d17bd0efcaf3` / protocol tag `2025-11-25`, Initialization and Operation: client/server negotiation and native operation underlying wiring checks. - [promptfoo/promptfoo](https://github.com/promptfoo/promptfoo/blob/0.123.1/README.md), tag `0.123.1`, README: upstream application-evaluation tooling retains its appropriate integration scope. - [anthropics/claude-code](https://github.com/anthropics/claude-code/blob/v2.1.289/CHANGELOG.md), tag `v2.1.289`, changelog, and [Claude memory documentation](https://code.claude.com/docs/en/memory), reviewed2026-10-06: native context surfaces underlying the preserved context-budget record. - Policy authority: CC interpretation `ITEM-ns2604-coop-20261006T190307Z.md`, SHA256 `425a46312a9dae9a2234e2ec64951f802b389bbb0c11cf744ac120dcce2f4734`; B3 item `task-ns2604-coop-20261006T203515Z`, section5; final preservation scope item `task-ns2604-coop-20261006T230116Z`; FormA item `task-ns2604-coop-20261006T230854Z`. The records paraphrase the policy and contain no verbatim owner quotation. ### Evidence-class table | Claim | Evidence class | Command / receipt | | --- | --- | --- | | Five rules, six superseded gate groups, retained checks and S4 match the CC interpretation | source_review | Canonical item190307Z and independent GPT read; named sources are linked in the new decision | | The #723 cohort contains exactly13 named rows | source_review | `foundation-eta-rerun-wf_91416191-566.json#/result/units/0/result/items`; indices6,10,11,13,14,18,46,48,49,50,51,64,70 independently checked | | B3 records its waiver, measured observation and deferred SDK check without a new host run | source_review | `session-d91d55ad-20261006/IMPROVEMENT-MANIFEST.md` B3, SHA256 `38b27a5646c65d6a5afdb1478f5312c411b038a13b12c576e636e138b5d7284d`; item203515Z section5/B3, SHA256 `fd44de4938cc96e9efcb29f8b7a17077275427b746455a275ca9db5a75f64966` | | B3 is an append-only dated amendment; reviewed58dff source content survives a pure main rebase | source_review | Four source commits are patch-equivalent, append-only diff and dd3df75f... hash; independent rebase/registry critic | | Registry, references and active disposition citations pass locally | local_integration | Fresh native validate and upstream_surface_watch module below; returned streams retained privately | ### Local commands run ```text rtk proxy nice -n 19 ionice -c3 python3 scripts/validate.py exit0:69components,10383hashedfiles,4profiles,223receipts rtk proxy nice -n 19 ionice -c3 python3 -m unittest tests.test_upstream_surface_watch exit0:114tests,6skips rtk proxy git diff --check exit0 ``` These are structural and local integration checks. The B3 Skills figure describes its retained `/context` row; it establishes no provider-token saving or comparative benchmark. Native streams and earlier failed/reviewed attempts remain durable. FormA preserves reviewed58dff's content with only a rebase and registry regeneration; the withdrawn separate-record move is retained privately and is absent from this PR. ### Decision record `docs/decisions/2026-10-06-upstream-evidence-over-local-evaluation.md` contains the selection/evidence rule and CC instruction handoff. The dated B3 amendment in `docs/decisions/2026-10-05-harness-context-budget.md` carries its alternative and overturn comparison beside the original gate. The new decision's B3 link targets that amendment. ### Handoff to the CC The decision lists the instruction sentences in `AGENTS.md`, `examples/claude-native/CLAUDE.md`, `adoption/templates/codex.AGENTS.template.md` and `adoption/scaffold/AGENTS.md` whose selection/evaluation scope needs to follow the rule, including AGENTS.md:9's foundation-selection reference. Those files and deployed configuration are outside this PR. FormA retains the earlier content acknowledgement; the co-op checks the pure range-diff and new-head CI before5f lands. ### Host evidence No `evidence/hosts/` files or live client configuration change. B3 reports existing observations; the SDK kit owner performs the deferred bounded-job check. ### Checklist - [x] Third-party action pin requirements retained; no workflow change. - [x] Workflow permission requirements retained; no workflow change. - [x] No secrets printed or committed; no new required secret. - [x] No paid hosting, subscription or billing surface added. - [x] Peer-owned instruction, install-plan, evidence and decision files preserved.
1 parent b593372 commit 7961993

8 files changed

Lines changed: 257 additions & 13 deletions

‎catalogs/foundation/upstream-surface-dispositions.json‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -2614,8 +2614,8 @@
26142614
{
26152615
"key": "codex:feature:context_management",
26162616
"disposition": "declined",
2617-
"reason": "off on both hosts (read 2026-10-04)); the repository record at docs/convergence-architecture.md:132 names it",
2618-
"source": "docs/convergence-architecture.md:132",
2617+
"reason": "off on both hosts (read 2026-10-04)); the repository record at docs/convergence-architecture.md:134 names it",
2618+
"source": "docs/convergence-architecture.md:134",
26192619
"carrier": null,
26202620
"value": null,
26212621
"scope": null,

‎docs/acceptance-evidence-policy.md‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,7 @@
11
# Upstream practice and acceptance evidence
22

3+
Foundation-component selection and readiness follow the [2026-10-06 upstream-evidence rule](decisions/2026-10-06-upstream-evidence-over-local-evaluation.md); the evidence classes, returned-result requirements and discriminating controls below continue to govern claims about our own wiring.
4+
35
The foundation uses research to select a supported upstream solution, then
46
qualifies its actual behavior. Repository popularity, local test totals and a
57
well-formed receipt are discovery or validation signals; none establishes native

‎docs/convergence-architecture.md‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,7 @@
11
# Convergence architecture for native engineering work
22

3+
For foundation-component selection and readiness, apply the [2026-10-06 upstream-evidence rule](decisions/2026-10-06-upstream-evidence-over-local-evaluation.md); the application engineering and research checks below retain their stated scope.
4+
35
Start with one engineering outcome and the evidence needed to accept it. This
46
guide connects research, implementation, native Codex/Claude workers, validation
57
and recovery. It applies to an ordinary software repository before adding a

‎docs/decisions/2026-10-05-harness-context-budget.md‎

Lines changed: 23 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -464,6 +464,29 @@ feeds the next lifecycle-task sweep. Upstream closing a demonstrated glue gap
464464
removes that glue. No new security ceremony, service, model run or custom runner
465465
is added.
466466

467+
#### Amendment 2026-10-06: B3 read-back scope
468+
469+
**Decision.** NativeStack's part of the two-host read-back requirement above is
470+
waived until its retirement. NativeStack2604 has a recorded measured read-back
471+
pass; the owner's `/context` observation supplies the Skills row: **64 skills,
472+
7.8k tokens**. The bounded SDK jobs' `codex-home-full` read-back remains due at
473+
the first bounded SDK job after the night of 2026-10-06, owned by the SDK kit
474+
owner (the co-op). The remaining read-back requirement still governs replacement
475+
of the inline root routing; this amendment changes no client configuration.
476+
477+
**Evidence and authority.** The measured observations are recorded in
478+
`coordination/session-d91d55ad-20261006/IMPROVEMENT-MANIFEST.md`, B3. The waiver
479+
and deferred SDK check follow `task-ns2604-coop-20261006T203515Z`, section 5, B3.
480+
These are retained observations and a dated ruling, rather than a new read-back
481+
performed by this amendment. The Skills figure describes the displayed context
482+
row and establishes no provider-token saving or comparative benchmark.
483+
484+
**Alternative and overturn.** Re-rendering and checking the retiring host was
485+
the alternative to the waiver. A dated decision to retain it as an ongoing
486+
target would reopen its read-back requirement. Compare any continuing target's
487+
actual client blocks with the phrases and settings required above; an SDK
488+
read-back failure remains a wiring issue for the kit owner to resolve.
489+
467490
### PR #726 repair acceptance
468491

469492
| Command | Exit | Actual returned result |

‎docs/decisions/2026-10-06-upstream-evidence-over-local-evaluation.md‎

Lines changed: 208 additions & 0 deletions
Large diffs are not rendered by default.

‎docs/harness-defaults.md‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,7 @@
11
# Native harness defaults
22

3+
Foundation-component selection and readiness follow the [2026-10-06 upstream-evidence rule](decisions/2026-10-06-upstream-evidence-over-local-evaluation.md); local evaluation campaigns no longer select components or gate their readiness, while application checks, paper gates, CI and independent review retain their scope.
4+
35
Use native Codex and Claude as the general engineering harnesses. This policy applies to ordinary projects, research workers and harness maintenance; the trading architecture adds its own domain requirements. The [foundation catalog](../catalogs/foundation/README.md) is the maintained layer map. The [trading catalog](../catalogs/us-equities/README.md) records the separate IBKR, NautilusTrader and Alpaca destination. Neither catalog is a startup prompt or a universal ranking.
46

57
## Core rule

‎docs/token-practice.md‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,7 @@
11
# Token practice and measured native results
22

3+
Foundation-component selection and readiness follow the [2026-10-06 upstream-evidence rule](decisions/2026-10-06-upstream-evidence-over-local-evaluation.md); upstream evidence selects components and native counters record organic use, while accounting boundaries and the evidence needed to claim savings below remain.
4+
35
For a new PC or a separate local ledger, use the [portable upstream counter collector](../tools/token-report/README.md). It produces local JSON/HTML reports, retains failed refreshes and never adds overlapping lifetime snapshots.
46

57
Updated September 21, 2026. The [current full-stack convergence](full-stack-convergence.md)

‎manifests/evidence.json‎

Lines changed: 16 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -16528,7 +16528,7 @@
1652816528
},
1652916529
{
1653016530
"path": "catalogs/foundation/upstream-surface-dispositions.json",
16531-
"sha256": "34bfd46db3fb29d0a138f89b4045787a3f67a017c96bdfd001424c5f6de7a55d",
16531+
"sha256": "82fae20369f6c5219cf6111c22c8daea74068ac35cee210cc611e5efa7aa0d88",
1653216532
"bytes": 158923
1653316533
},
1653416534
{
@@ -17003,8 +17003,8 @@
1700317003
},
1700417004
{
1700517005
"path": "docs/acceptance-evidence-policy.md",
17006-
"sha256": "38ddfb80673ae86cad110a65a9cc938bb974d65a34bb9638b7a0f96d3e2ef508",
17007-
"bytes": 5820
17006+
"sha256": "1a7ce4aa3e05986f72d417f76ee7ae4f34dadee922156dc379ea26e3f625cce1",
17007+
"bytes": 6112
1700817008
},
1700917009
{
1701017010
"path": "docs/activation.md",
@@ -17098,8 +17098,8 @@
1709817098
},
1709917099
{
1710017100
"path": "docs/convergence-architecture.md",
17101-
"sha256": "1888656a0c4afcd630cb9fc861b05818de653e438bdb4780eaa91206380b401b",
17102-
"bytes": 15725
17101+
"sha256": "4bd71670734119bae382402efe7ca1180b0812e5c3c32f766e5d2c19fed5d57a",
17102+
"bytes": 15969
1710317103
},
1710417104
{
1710517105
"path": "docs/convergence-audit.md",
@@ -17583,8 +17583,8 @@
1758317583
},
1758417584
{
1758517585
"path": "docs/decisions/2026-10-05-harness-context-budget.md",
17586-
"sha256": "9f1ddd367361a6f9c88b78d18e4f230b80935e966c9d1e3e91aacd578024c38e",
17587-
"bytes": 55486
17586+
"sha256": "b0d7fcee643cd6b29b37dc48025d8006c564c4657c1225e5d9df379265bfaa0f",
17587+
"bytes": 56929
1758817588
},
1758917589
{
1759017590
"path": "docs/decisions/2026-10-05-main-checkout-backup-disposition.md",
@@ -17666,6 +17666,11 @@
1766617666
"sha256": "7fad1a25a8f3b1c151a7c1f125c1635d32d631757c68509588b55d72c1cf6f89",
1766717667
"bytes": 3898
1766817668
},
17669+
{
17670+
"path": "docs/decisions/2026-10-06-upstream-evidence-over-local-evaluation.md",
17671+
"sha256": "396ad0e762f863854c36db4d971730ec21ce26c9462892428898aea8aa8c200a",
17672+
"bytes": 16404
17673+
},
1766917674
{
1767017675
"path": "docs/direct-results.md",
1767117676
"sha256": "12a511fee11f22c90b9b622701d5485be9c8247167102b5768d694244f939a5b",
@@ -17798,8 +17803,8 @@
1779817803
},
1779917804
{
1780017805
"path": "docs/harness-defaults.md",
17801-
"sha256": "822f9ed7114c7017cfebc409e432498b8423c426023eef22dbc4b644c89fc9b4",
17802-
"bytes": 247278
17806+
"sha256": "d956ab78563864e8cc2513d391fe133bc9ef5cc88fb561f94c79adf4bec5abd1",
17807+
"bytes": 247602
1780317808
},
1780417809
{
1780517810
"path": "docs/harness-rules-convergence-20260922.md",
@@ -18043,8 +18048,8 @@
1804318048
},
1804418049
{
1804518050
"path": "docs/token-practice.md",
18046-
"sha256": "9ce6b2d1710076871e97012ca084e29ec0ea919e1755a45733c7c6361638af49",
18047-
"bytes": 40805
18051+
"sha256": "9a70d0c313587f11cfc52a748b5106c521fce8970a34c2543322467f425a3e16",
18052+
"bytes": 41124
1804818053
},
1804918054
{
1805018055
"path": "docs/token-session-handbook.md",

0 commit comments

Comments
 (0)