You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
symptom/trigger: a user who wants to change render-tag mode (or tag-echo behavior) for ONE model has no per-model knob — diagnostics.renderNone is global, and the only per-model escape is x-bili-passthrough: 1, which bypasses billion-context entirely for that model (no compression). So the user must choose between (a) disabling render tags for every model or (b) disabling compression for the one model that misbehaves.
This is a config-surface change (owner-design territory per AGENTS.md), so it is filed for a decision rather than built.
decision options:
Option A — per-model render-tags override. A config mapping model → renderTags ("text-only" | "none"), resolved per-request in the prepare-* lanes (where renderStrategy is already computed from the global knobRenderNone()). Cost: one new config field (a model→mode map) + per-request lookup; the existing global diagnostics.renderNone stays as the default. Maps directly onto the existing renderTags concept, so no new mechanism — just a per-model key.
Option B — per-route render-tags override. Same idea keyed by upstream route instead of model. Cost: similar, but route keys are less stable than model names and the user's mental model is "this model", not "this route".
Option C — do nothing. The [PR] fix(plugin): tag-echo degenerate retry now forbids the render tags (#7440) #7441 nudge fix breaks the degenerate loop, so the workaround is less necessary; a heavily-conditioned model may still occasionally echo tags but the retry now recovers. Cost: the user still cannot prevent the conditioning at the source (the model keeps seeing tags in history) and may still see occasional tag-echo retries.
recommendation: Option A (per-model render-tags override). It is the narrowest change, maps onto the existing renderTags concept, and lets the user set renderTags: "none" for the one model that gets conditioned on the tags — preventing the echo at the source instead of only recovering from it. Blocks on: owner sign-off on the new config field (name, shape, default) before implementation.
查重: 无 (no existing issue/PR proposes a per-model render-tags or tag-echo knob; the closest are the global diagnostics.renderNone and the per-model x-bili-passthrough bypass, neither of which is a render-tag knob).
Background (one line):#7440's degenerate tag-echo loop is broken by PR #7441's nudge fix, but a user who wants to change render-tag mode for ONE model still has no per-model knob — diagnostics.renderNone is global, and the only per-model escape (x-bili-passthrough: 1) bypasses compression entirely.
Verified (live code check — the analysis holds):
renderNone() (src/knobs.ts:877) reads the global diagnostics.renderNone (or ACP_RENDER_NONE env) — a single boolean, no per-model key.
renderStrategy is computed per-lane from that global knob in all four prepare lanes: prepare-openai.ts:106, prepare-google.ts:119, prepare-responses.ts:177, prepare-anthropic.ts:185 — all knobRenderNone() ? "none" : "text-only".
x-bili-passthrough: 1 (src/server/handle.ts:399) is a per-request passthrough that skips compression entirely — a bypass, not a render-tag knob.
So the issue's analysis is correct: there is no per-model render-tag knob today.
Open question: Should we add a per-model render-tags override?
Options (each with cost):
A — per-model render-tags override. A config mapping model → renderTags ("text-only" | "none"), resolved per-request in the prepare-* lanes. Cost: one new config field (model→mode map) + per-request lookup; the global diagnostics.renderNone stays as the default. Maps onto the existing renderTags concept — no new mechanism.
B — per-route render-tags override. Same idea keyed by upstream route. Cost: similar, but route keys are less stable than model names; the user's mental model is "this model", not "this route".
My recommendation: Option A. It is the narrowest change, maps onto the existing renderTags concept, and prevents the echo at the source instead of only recovering from it.
Default if no decision: Option C (do nothing) — the #7441 nudge fix already breaks the degenerate loop, so the status quo is safe; this is a convenience/robustness improvement, not a blocker.
Label: I attempted to apply the needs-decision label, but the mirror's labels API is not implemented ("endpoint not implemented in ework shim") and tools/add-label.sh does not exist in this workdir — so the label could not be applied. Flagging this so it is not mistaken for an oversight.
Activity
ranxianglei commentedon Nov 21, 2026
🔶 需要决策
Background (one line): #7440's degenerate tag-echo loop is broken by PR #7441's nudge fix, but a user who wants to change render-tag mode for ONE model still has no per-model knob —
diagnostics.renderNoneis global, and the only per-model escape (x-bili-passthrough: 1) bypasses compression entirely.Verified (live code check — the analysis holds):
renderNone()(src/knobs.ts:877) reads the globaldiagnostics.renderNone(orACP_RENDER_NONEenv) — a single boolean, no per-model key.renderStrategyis computed per-lane from that global knob in all four prepare lanes: prepare-openai.ts:106, prepare-google.ts:119, prepare-responses.ts:177, prepare-anthropic.ts:185 — allknobRenderNone() ? "none" : "text-only".x-bili-passthrough: 1(src/server/handle.ts:399) is a per-request passthrough that skips compression entirely — a bypass, not a render-tag knob.So the issue's analysis is correct: there is no per-model render-tag knob today.
Open question: Should we add a per-model render-tags override?
Options (each with cost):
model → renderTags("text-only"|"none"), resolved per-request in the prepare-* lanes. Cost: one new config field (model→mode map) + per-request lookup; the globaldiagnostics.renderNonestays as the default. Maps onto the existingrenderTagsconcept — no new mechanism.My recommendation: Option A. It is the narrowest change, maps onto the existing
renderTagsconcept, and prevents the echo at the source instead of only recovering from it.Default if no decision: Option C (do nothing) — the #7441 nudge fix already breaks the degenerate loop, so the status quo is safe; this is a convenience/robustness improvement, not a blocker.
Label: I attempted to apply the
needs-decisionlabel, but the mirror's labels API is not implemented ("endpoint not implemented in ework shim") andtools/add-label.shdoes not exist in this workdir — so the label could not be applied. Flagging this so it is not mistaken for an oversight.结构化八问(决策请求):
diagnostics.renderNone是全局的,唯一 per-model 出口x-bili-passthrough: 1会绕过整个压缩。renderNone()(src/knobs.ts:877) 读全局diagnostics.renderNone,四条 prepare-* 车道用这个全局布尔算renderStrategy,没有 per-model key;配置面设计时只做了全局开关,没留 per-model 维度。diagnostics.renderTagsByModel: Record<string, "text-only" | "none">),prepare-* 车道算renderStrategy时先查 per-model map,miss 回退全局knobRenderNone()。复用现有renderTags概念,无新机制。renderTags概念上加 per-model 维度,不改架构/边界/数据流;C 不改。diagnostics.renderTagsByModel(model→mode map,默认空);B 引入diagnostics.renderTagsByRoute;C 不引入。选项对比表:
判定: 等 owner 拍板(A/B/C)。不决定的默认行为 = C(不动)。