Skip to content

Commit 0e13d6b

Browse files
authored
docs(devlog): close the 260914 triage round-lane unit (#4558)
Ten PRs landed on dev across two merge rounds run by four worktree lane threads, each merged only after the check run's head_sha was verified against the PR head, with post-merge dev runs 34778300807 and 34782580496 as the joint proof for each round. #4522, #4530 and #4516 are closed with merge references after an independent audit of every claim against the tree; eleven issues are deliberately left open with their residuals named. #4555 is green and deliberately unmerged: MAINTAINERS.md requires explicit security review for a change that sends the serving provider's API key to an operator-named endpoint, and the dev self-integration exception does not cover that review. An adversarial review found a real silent regression there, which the lane fixed. Records what the unit learned, including that a fresh lane worktree has no node_modules so hosted CI is the only evidence that can exist, that a push already queues CI so the explicit dispatch is a fallback, and that a cancelled dev run is a concurrency artifact of the release train rather than a failure.
1 parent e97ed7a commit 0e13d6b

5 files changed

Lines changed: 657 additions & 0 deletions

File tree

Lines changed: 126 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,126 @@
1+
# 260914 — Triage round lanes: two merge rounds, four worktree lanes
2+
3+
Status: OPEN. Opened 2026-09-14 KST. Owner: main orchestration session
4+
`01a09bc0-bb13-7393-8526-785a3aeacb91`, goalplan slug
5+
`opencodex-2026-09-14-triage-delivery-loop-hotl-o`.
6+
7+
## Objective
8+
9+
Land 9-11 pull requests into `dev` across two merge rounds, then close the issues
10+
and pull requests those merges resolve or supersede. The input is the 2026-09-14
11+
triage of 64 open PRs and 60 open issues; this unit is the delivery half of it.
12+
13+
## Why this shape
14+
15+
The triage queue mixes two kinds of work that cannot be orchestrated the same way.
16+
PRs #4528, #4529, #4511 and #4512 belong to outside contributors: the work there is
17+
verification and merge, and nothing can be stacked on a fork branch. The remaining
18+
items — the #4515 follow-up, #4519, #4530 and #4516 — are ours to author, and only
19+
those can carry a branch chain. Treating the whole queue as one stack is the failure
20+
mode this unit exists to avoid.
21+
22+
Ordering inside a chain follows gate speed, not importance. #4519 is the highest
23+
priority item in the triage and it sits at the TOP of its lane, because it needs an
24+
independent security review that can stall for days. A stalled bottom layer freezes
25+
everything above it; a stalled top layer costs nothing once its parent has landed.
26+
27+
## Verified repository facts (2026-09-14)
28+
29+
These were read live and decide the merge mechanics. Refresh before acting on them.
30+
31+
- `dev` ruleset carries `deletion`, `non_fast_forward` and `pull_request`
32+
(1 approval, code-owner review required). There is **no** required-status-check
33+
rule and **no** strict up-to-date rule, so a `dev` move does not mechanically
34+
invalidate another PR's checks. Batch merging disjoint PRs inside one CI
35+
generation is therefore sound, and the residual risk is semantic, not textual.
36+
- Cross-platform CI runs in 9-11 minutes (runs observed 2026-09-13T16:54-17:03 and
37+
17:12-17:23).
38+
- Contributor fork PRs sit at `action_required`: their workflow runs have never
39+
executed. #4528 and #4529 both show this. Approving those runs is the first
40+
merge-track action, not the last.
41+
- `src/web-search/passthrough-bridge.ts` holds both `resolveOllamaWebSearchEndpoint`
42+
(119-243) and `sidecarSettingsForBridge` (689). The two lane-A layers collide in
43+
one file, which is what makes lane A a real chain rather than two parallel PRs.
44+
45+
## Lane map
46+
47+
Four `environment: worktree` threads. Write-sets are disjoint by construction; that
48+
disjointness is what licenses the batch merge above.
49+
50+
| Lane | Orchestrator | Bottom layer | Top layer | Write set |
51+
|---|---|---|---|---|
52+
| L1 | `anthropic/claude-opus-5` high | sidecar backend/model agreement | #4519 endpoint destination policy | `src/web-search/`, `src/server/responses/core.ts` (~6290) |
53+
| L2 | `kimi/k3[1m]` high | catalog parser preserves `supportsImages` | capability propagation + override precedence | `src/adapters/devin/`, `src/codex/catalog/provider-fetch.ts` |
54+
| L3 | `anthropic/claude-opus-5` high | #4516 spare-budget argument restoration | budget/ordering regressions | `src/adapters/cursor/` |
55+
| L4 | `kimi/k3[1m]` high | #4529 carry, version-skew refusal plus its unknown-version case | #4512 live-failure regressions | `src/cli/index.ts`, `src/cli/system-restart-client.ts`, `tests/cli/`, `tests/server/audio-dictation.test.ts` |
56+
57+
Lane A's top layer is security-gated. If it stalls past round 2, cut it loose from
58+
the chain and re-base it directly on `dev` rather than holding the lane open.
59+
60+
L4 is not a tests-only lane. The #4529 carry writes `src/cli/index.ts` and
61+
`src/cli/system-restart-client.ts`, so it carries the same structure obligation as
62+
any other source change. Structure owners per lane: L1 `structure/runtime.md`;
63+
L2 `structure/catalog.md` and `structure/adapters/registry.md`; L3
64+
`structure/runtime.md` and `structure/providers/cursor.md`; L4 the owner of
65+
`src/cli/`. Each lane resolves its owner from `structure/INDEX.md` at its own P and
66+
updates the doc in the same PR, because `bun run structure:check` fails on a doc
67+
that no longer matches the tree.
68+
69+
## Worker policy
70+
71+
Two surfaces, each doing what it is for. A **lane** needs its own branch, its own
72+
CI and its own merge, so every lane is a `create_thread` task with
73+
`environment: worktree`. A **worker inside a lane** is a bounded slice of that
74+
lane's own tree, so it is a subagent, spawned by the lane thread into the lane's
75+
worktree. Subagents belonging to different lanes cannot collide because the
76+
worktrees differ.
77+
78+
Four lane threads: `anthropic/claude-opus-5` on L1 and L3, `kimi/k3[1m]` at high
79+
effort on L2 and L4. Each lane loads `$codexclaw:cxc-loop` and runs its own scoped
80+
PABCD cycle with its own goal and FSM, because a thread owns both.
81+
82+
Inside a lane, workers are `devin/swe-2` and `xai/grok-4.6` subagents at roughly
83+
2:3, with no cap on count. Both ids are accepted by `spawn_agent` even though
84+
`devin/swe-2` is absent from the advertised override list in the tool description;
85+
that omission was verified as a documentation gap on 2026-09-14, not a real
86+
restriction. Only one subagent writes at a time, and no subagent runs a
87+
branch-level git operation.
88+
89+
## Proof policy
90+
91+
No local product suite, typecheck, build or install. Every PR body labels them
92+
NOT RUN. The only proof is hosted Cross-platform CI at the exact head SHA,
93+
dispatched explicitly with `gh workflow run ci.yml --ref <branch> -F lane=all`,
94+
because a sync or rebase does not reliably queue it. Non-tip chain commits carry
95+
`[skip ci]`. Pushes are `--no-verify` and fast-forward only; no shared branch is
96+
force-pushed. Each round closes with one post-merge `dev` run as the joint proof
97+
for that batch.
98+
99+
## Work-phase map
100+
101+
| Phase | Outcome | Depends on |
102+
|---|---|---|
103+
| wp1 | This roadmap, at diff level, before any lane dispatch | — |
104+
| wp2 | Round 1: lanes created, bottom-layer PRs, merge-track approvals, batch merge, post-merge dev CI | wp1 |
105+
| wp3 | Round 2: top-layer PRs, retarget after parents land, batch merge, post-merge dev CI | wp2 |
106+
| wp4 | Closure sweep: resolved issues closed with merge references, superseded PRs and issues closed with written reasons | wp3 |
107+
108+
Phase documents: `010_wp2_round1.md`, `020_wp3_round2.md`, `030_wp4_closure.md`.
109+
110+
## Out of scope
111+
112+
#4022, #4259, #2562, #3283, #3742, #3738, #4020 and #4299; any account-pool
113+
redesign; any Lab import into `src/router.ts`, `src/server/lifecycle.ts` or
114+
`src/server/responses/core.ts`; security write-ups in any tracked directory
115+
(scratch only, per AGENTS.md); rewriting another maintainer's branch; and the
116+
uncommitted `src/codex/inject.ts` and `src/codex/sync.ts` changes observed in the
117+
parent checkout, whose author was never identified.
118+
119+
## Terminal outcomes
120+
121+
DONE needs 9 or more PRs merged, each with a CI run id at its merged SHA or an
122+
explicitly recorded decision to merge without observing CI, both rounds closed with
123+
a post-merge `dev` run, the named issues closed with merge references, and the
124+
superseded set closed with written reasons. NEEDS_HUMAN is reserved for the
125+
security review on #4519 and #4528. A heartbeat firing, a wait timeout or a
126+
compaction is none of these.
Lines changed: 184 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,184 @@
1+
# 010 — wp2: Round 1
2+
3+
Bottom layers plus the clean half of the merge track. Target: five PRs merged into
4+
`dev` in one CI generation, closed by a post-merge `dev` run.
5+
6+
Every source fact below was read live on 2026-09-14 by read-only recon agents.
7+
Re-verify line numbers before editing; `dev` moves.
8+
9+
## Round 1 contents
10+
11+
| # | Branch or PR | Owner | Deliverable |
12+
|---|---|---|---|
13+
| 1 | `codex/260914-l1-bridge-backend-model` | L1 | sidecar model bound to the bridge backend |
14+
| 2 | `codex/260914-l2-devin-catalog-supports-images` | L2 | catalog parser preserves field 5 as true/false/unknown |
15+
| 3 | `codex/260914-l3-cursor-spare-budget` | L3 | spare-budget restoration of recent invocations |
16+
| 4 | #4511 (`maoxin1234:fix/vision-native-model-capabilities`) | main | merge as-is |
17+
| 5 | #4512 (`maoxin1234:fix/audio-outcome-accounting`) | main | merge as-is |
18+
19+
## L1 bottom — bridge backend/model agreement
20+
21+
File: `src/web-search/passthrough-bridge.ts`.
22+
23+
`sidecarSettingsForBridge` (677-705) takes `sidecar.model` from the global
24+
`config.webSearchSidecar` blob without checking that the global backend equals the
25+
bridge backend, and `core.ts:6290-6296` passes that blob whole. A global
26+
`{backend:"openai", model:"gpt-5.6-luna"}` therefore reaches
27+
`runAnthropicWebSearch` when a provider sets `webSearchBridge.backend: "anthropic"`.
28+
Credentials do not leak — `resolvePassthroughWebSearchBridgeAuth` (155-181)
29+
inspects only the named backend — so this is a model and settings defect, not a key
30+
defect, and the PR body must say exactly that.
31+
32+
```diff
33+
- sidecar?: Pick<OcxWebSearchSidecarConfig, "model" | "reasoning" | "xSearch">;
34+
+ sidecar?: Pick<OcxWebSearchSidecarConfig, "backend" | "model" | "reasoning" | "xSearch">;
35+
36+
- const model = backend === "anthropic" ? sidecar.model ?? DEFAULT_ANTHROPIC_BRIDGE_MODEL
37+
- : backend === "xai" ? sidecar.model ?? DEFAULT_XAI_BRIDGE_MODEL
38+
- : backend === "gemini" ? sidecar.model ?? DEFAULT_GEMINI_BRIDGE_MODEL
39+
- : sidecar.model ?? DEFAULT_OPENAI_BRIDGE_MODEL;
40+
+ const model = modelForBridgeBackend(backend, sidecar);
41+
```
42+
43+
`modelForBridgeBackend` applies `sidecar.model` only when
44+
`resolveSidecarBackend(sidecar.backend) === backend`, and otherwise returns the
45+
backend default. Reuse `resolveSidecarBackend` from `src/web-search/index.ts`; do
46+
not invent a second resolver. `planWebSearch` (index.ts:112-208) already pins the
47+
backend first and is the precedent to follow.
48+
49+
Tests go in `tests/web-search/web-search-passthrough-bridge.test.ts`: a global
50+
openai model with an anthropic bridge yields `claude-sonnet-5`; a matching backend
51+
keeps the override; repeat the matrix for xai and gemini. Structure owner is
52+
`structure/runtime.md`, hosted-search bridge contract at L238-247.
53+
54+
Destination policy stays out of this layer. That is L1 top.
55+
56+
## L2 bottom — Devin catalog preserves supportsImages
57+
58+
File: `src/adapters/devin/cloud-direct/catalog.ts`.
59+
60+
`parseCatalogBuffer` (107-141) has arms for fields 1, 4, 18 and 22 and no default,
61+
so `ClientModelConfig` field 5 is dropped by omission. `disabled` defaults to
62+
`false` when absent; image support must not copy that pattern, because an absent
63+
field has to stay unknown. That is the #1796 precedent, and Antigravity already
64+
implements the tri-state at `src/providers/antigravity-models.ts`:587-592.
65+
66+
```diff
67+
export interface ModelCatalogEntry {
68+
modelUid: string; label: string; disabled: boolean; contextWindow?: number;
69+
+ /** ClientModelConfig #5. Present true/false asserts; omitted means unknown. */
70+
+ supportsImages?: boolean;
71+
}
72+
+ let supportsImages: boolean | undefined;
73+
} else if (sf.num === 4 && sf.wire === 0) { disabled = sf.value === 1n;
74+
+ } else if (sf.num === 5 && sf.wire === 0) { supportsImages = sf.value === 1n;
75+
byUid.set(modelUid, { modelUid, label: label || modelUid, disabled,
76+
...(contextWindow > 0 ? { contextWindow } : {}),
77+
+ ...(supportsImages !== undefined ? { supportsImages } : {}),
78+
});
79+
```
80+
81+
Extend the file-header schema comment with `#5 supportsImages bool` in the same
82+
commit; the comment is the only schema documentation this parser has.
83+
84+
Test: extend `"the catalog parser reads the per-account context window"` in
85+
`tests/providers/devin-adapter.test.ts` (300-323) with three cases built from
86+
`encodeVarintField(5, 1)`, `encodeVarintField(5, 0)` and omission, asserting
87+
`true`, `false` and `undefined`. Encoder helpers already exist at
88+
`src/adapters/devin/cloud-direct/wire.ts`:54-63.
89+
90+
PR #4511 touches only `src/vision/eligibility.ts` and its test, so there is no file
91+
overlap. Do not wait on it and do not restack into it.
92+
93+
Corrections returned by L2 after doing the work: `encodeVarintField` is at
94+
`wire.ts`:63-65, not 54-63; `parseCatalogBuffer` spans 107-142; the file-header
95+
schema comment omits field 18 as well as field 5, so the patch documents both and
96+
carries per-field provenance instead of a blanket "verified against extension.js"
97+
claim, because field 5 identity is corroborated from external ClientModelConfig
98+
documentation rather than re-read from the vendor bundle. For this layer the only
99+
structure owner that actually documents the Devin adapter in prose is
100+
`structure/adapters/registry.md`; `structure/catalog.md` has no Devin mention and
101+
owns the round-2 provider-fetch surface instead.
102+
103+
## L3 bottom — Cursor spare-budget restoration
104+
105+
File: `src/adapters/cursor/protobuf-request.ts`. The per-call 2 KiB cap
106+
(`CURSOR_INVOCATION_ARGUMENTS_BYTE_LIMIT`, line 84) is applied at envelope
107+
construction in `toolCallArgumentsText` (937-967) and never revisited, even when
108+
almost all of the 192-root and 512 KiB envelope is unused. A 4,693-byte successful
109+
call loses its tail inside a 6,011-byte replay.
110+
111+
Insert a second pass after `selected` is assembled (near line 694) and before the
112+
return. It spends only leftover aggregate bytes, newest `toolResult` first, skips
113+
`outputElided` roots, and never evicts a retained root. It does not remove the cap:
114+
admission still uses the 2 KiB prefix.
115+
116+
Two review-surviving details from recon:
117+
118+
- Gate on `echoToolResultInRoot && replayedCalls` rather than
119+
`externalModel && replayedCalls`. Native `composer-2.5` echoes results into roots
120+
but is not an external wire model, so the narrower gate would leave it capped.
121+
- Use the callback form of `String.prototype.replace` so replacement patterns
122+
appearing inside serialized arguments are not expanded by the replace call.
123+
124+
The two existing 600 KiB tests in
125+
`tests/providers/cursor/cursor-tool-result-invocation.test.ts` stay unchanged and
126+
must stay green: `"PROBE a huge argument must not evict the result output from root
127+
replay"` (244) and `"the truncated invocation line stays within the declared
128+
argument budget"` (261). They are the proof that the cap still bites under
129+
pressure.
130+
131+
The PR body states that this claims nothing about #3506 causation. The four
132+
rejected patches there were 1,648, 1,396, 1,670 and 1,900 bytes, all under the cap.
133+
134+
## Merge track in round 1
135+
136+
Every contributor PR has Cross-platform CI queued and stuck at `action_required`;
137+
none has ever executed a job. Approving those runs is the first action of the
138+
round, not the last.
139+
140+
- #4511 at `6d926244101cb6234b66634464007268a06b1d89`: no outstanding reviewer ask,
141+
non-draft, readiness 4/4. Approve CI, wait for green, merge.
142+
- #4512 at `0235ce604cb907185295e42b05754d11d11a0bb2`: non-draft, readiness 4/4,
143+
one open CodeRabbit ask for live `handleExternalLive` regressions. Do not push a
144+
carry commit onto that branch. The readiness gate binds to the exact head, so a
145+
new push resets the checklist and re-drafts the PR. Merge as-is and deliver the
146+
asked coverage as our own follow-up PR in round 2.
147+
- #4528 (2/4) and #4529 (0/4) are drafts. Approve their CI in round 1 so round 2
148+
has real information, but plan them as carries rather than direct merges.
149+
150+
## Merge and proof mechanics
151+
152+
Each lane pushes with `--no-verify`, fast-forward only. Non-tip chain commits carry
153+
`[skip ci]`. For each PR, dispatch CI explicitly, because a sync or rebase does not
154+
reliably queue it:
155+
156+
```sh
157+
gh workflow run ci.yml --ref <branch> -F lane=all
158+
```
159+
160+
One ruleset term the batch argument has to respect:
161+
`require_extra_approval_for_unattributed_changes` is true on `dev`. A carry that
162+
replays another author's commits can therefore need an approval beyond the standard
163+
one. The mitigation is to author each carry as our own commits with a
164+
`Co-authored-by` trailer rather than cherry-picking the contributor's commits; the
165+
trailer is what GitHub reads for credit, and the change stays attributed to the
166+
pushing author for the ruleset.
167+
168+
Wait for that run at the exact head SHA, then merge. Because `dev` carries no
169+
required-status-check rule and no strict up-to-date rule, the five PRs may merge
170+
back to back inside one generation; their write-sets are disjoint, so the residual
171+
risk is semantic rather than textual. Close the round with one post-merge `dev`
172+
Cross-platform CI run and record its id.
173+
174+
Every PR body fills Summary, Verification and Checklist, and states plainly that
175+
the local suite, typecheck, build and install were NOT RUN, naming the hosted run
176+
id and SHA as the only proof.
177+
178+
One thing the lanes discovered that makes this policy stronger than intended: a
179+
fresh lane worktree has no `node_modules`, so a focused `bun test` cannot execute
180+
at all without `bun install`. Local focused runs are therefore impossible in a lane
181+
rather than merely disallowed, and hosted CI is the only evidence that could exist.
182+
The one check that runs without install is `bun run structure:check`, used for
183+
debugging the doc gate and never cited as proof.
184+

0 commit comments

Comments
 (0)