Files
OmniRoute/open-sse/executors/devin-agentic/serializer.ts
Diego Rodrigues de Sa e Souza 36abd86929 fix(ci): clear the 08-08 base-red layers — dead-code, prod crash in chat.ts, Responses payload regression, born-red stdio test, gate drifts (#9757)
* fix(ci): drop unused RadarReferrals type export — dead-code ratchet back to 227 baseline

The radar referral-links feature (#9697) exported the inferred type
RadarReferrals from feedSchema.ts but nothing imports it (the singular
RadarReferral is the consumed type). knip counts it as a new dead export,
pushing the dead-code ratchet to 228 > 227 and failing Fast Quality Gates
on every PR born after the merge. RadarReferralsSchema itself stays — it
is used by RadarFeedSchema.

Refs #9737

* fix(ci): clear the 08-08 base-red layer — prod crash in chat.ts, Responses API payload regression, born-red stdio test, gate drifts

Six independent base-reds from the 08-07 evening merge batch, each verified
against the pure release/v3.8.50 tip:

- src/sse/handlers/chat.ts: #9467's squash carried a refactor hunk that
  renamed the all-rate-limited breaker guard to an UNDEFINED variable
  (isAllRateLimited) — a production ReferenceError on the all-accounts-429
  path (chat.ts is outside typecheck:core scope, so only tests caught it).
  Restore credentials?.allRateLimited. Guard: chat-rate-limit-body-lock (2/2),
  also un-breaks batch_api and chat-combo-live-test.
- open-sse/utils/stream.ts: #9315 switched providerPayload summaries to the
  accumulated responseBody, but in passthrough paths that body is synthesized
  in chat-completion shape — Responses API lost its `response` object in the
  dashboard payload. Keep the events-derived summary for OPENAI_RESPONSES
  only. Guard: stream-utils + stream-collector-9315 suites (51/51).
- tests/unit/mcp-stdio-json-purity.test.ts: born red — the full CLI chain
  takes ~10s (2x tsx import + DB init) and the test slept a fixed 4s. Poll
  for the first stdout line with a 60s deadline instead.
- tests/unit/plugins-route-error-sanitization.test.ts: register #9445's new
  marketplace/install route in PLUGIN_ROUTES (route already sanitizes) (33/33).
- tests/unit/provider-models-route-codex.test.ts: realign pinned GPT-5.6
  input limit to #9432's deliberate 272000→922000 bump (7/7).
- lint: fix 11 no-explicit-any errors in repro-9630 + specialty-9293 tests,
  prune 1 orphaned suppression, allowlist the opencode-ai devDependency
  (#8869, publisher-verified), and reword a doc line the fabricated-docs
  gate misread as an env var.

Gates re-verified locally: lint:json --max-warnings 0 exit 0, dead-code 227,
typecheck:core clean, check:deps OK, check:fabricated-docs OK.

Refs #9737

* fix(ci): clear the third 08-08 base-red layer — invalid ru rule pack, stale event pin, orphaned UI repro test, pack/mutation/file-size drifts

Follow-up to the previous layer: the serial fast-gates chain unmasked one
more stratum after file-size/dead-code went green, all verified against the
merged release/v3.8.50 tip:

- compression rules ru/ultra.json (#9581): two rules shipped
  minIntensity "notes", which is not a valid CavemanIntensity
  (lite|full|ultra) — loading ANY language pack list threw and killed the
  rtk-loader suite. Mapped both to "ultra" (they are the most aggressive
  punctuation/case rules, matching the en pack tiers). 2/2.
- plugins-welcome-banner-e2e: #9668 added the onStreamComplete builtin
  event (real emission path via runOnStreamCompleteHooks) and missed this
  pinned-list sibling. 35/35.
- tests/unit/free-pool-frontend-repro (#9046): landed as .tsx with
  node:test semantics — no runner collects tests/unit/*.tsx, so it NEVER
  ran (test-discovery NEW-orphan). It contains zero JSX; renamed to .test.ts
  so the unit runner's existing glob collects it. 5/5 (first real run).
- pack-policy: allow + require bin/mcpStdioConsoleGuard.mjs (#9281) — it is
  preloaded via node --import by bin/mcp-server.mjs, so a published artifact
  without it crashes 'omniroute --mcp' at startup.
- stryker.conf.json: add 5 covering unit tests from the batch (#8779/#9204/
  #9330/#9630/openrouter-passthrough) to tap.testFiles (--strict drift).
- file-size-baseline: consolidate the base-drift rebaseline for the 12
  files grown by the 08-06..08-08 batches (#9616's entries never reached the
  base; measured on this branch's tree — this PR's own source edits add zero
  lines to any frozen file).

Local battery: file-size/deps/test-discovery/mutation/pack-policy/dead-code/
duplication/docs-all/secrets/vuln/workflows ratchets all exit 0; full lint
gate --max-warnings 0 exit 0.

Refs #9737

* fix(types): clear the 3 uncovered open-sse-typecheck regressions + realign combo skip-code siblings

Fourth base-red layer unmasked by the serial gates. The other 4 typecheck
regressions (codex.ts, kiro.ts, tierResolver.test.ts, translator/index.ts)
already have dedicated open [TS7] PRs (#9748/#9753/#9742/#9747) — not
duplicated here. This commit covers only what no open PR owns:

- devin-agentic/serializer.ts TS2367: drop the dead 'role === "system"'
  branch — the guard above already narrows role to user|assistant (system
  throws unsupported_role). Devin suites 104/104.
- raycast.ts TS2416: the buildHeaders 'override' never matched the base
  signature (2nd param is the signed payload string, not the stream
  boolean) — renamed to a private buildRaycastRequestHeaders helper so a
  polymorphic buildHeaders(credentials, true) call can never bind here.
- modelMetadataRegistry.ts TS2352: PricingByProvider → nested-record cast
  now goes through unknown (shape is runtime-guarded by findInsensitive).
- combo-routing-engine.test.ts: realign 2 pre-dispatch-skip expectations to
  #9630's deliberate ALL_TARGETS_SKIPPED contract (87/87).

Refs #9737

* fix(ci): clear the fifth 08-08 base-red layer — reasoning-placeholder contract sweep, GPT-5.6 limits sweep, vi key parity

The 08-08 merges (#9610 reasoning replay, #9432 GPT-5.6 limits, #9630 combo
skip codes, #9336 provider key links) each changed a contract and left
sibling tests pinning the old one. Full grep sweep per contract, not just
the shard that happened to go red:

- reasoning placeholder (#9573/#9610): the fix DELIBERATELY removed
  NON_ANTHROPIC_THINKING_PLACEHOLDER injection on cache miss — the model
  echoed the placeholder as its own reasoning (empty stop) and re-poisoned
  cache + client history; DeepSeek's 400 is specific to an EMPTY STRING, not
  an absent field. Realigned reasoning-cache (2 cases, renamed to describe
  omission) + tool-request-sanitization (1 case + dead import). 60/60.
- GPT-5.6 Codex limits (#9432, 272000 -> 1050000 ctx / 922000 input):
  realigned vscode-token-routes-gpt56 (2) + vscode-token-routes (3). 43/43
  together with t23-t24.
- combo skip codes (#9630): t23-t24-fallback-resilience T24 now expects
  ALL_TARGETS_SKIPPED like the combo-routing-engine siblings.
- vi.json key parity: #9336 added providers.getApiKey/getApiKeyDescription
  to en.json without syncing vi (the only locale with a parity gate).
  Translated both; providers block reordered to match en key order. 5/5.
- pack-artifact-policy.test.ts: sibling of this PR's own required-paths
  change (bin/mcpStdioConsoleGuard.mjs). 10/10.
- combo-routing-engine.test.ts: dropped the 6 comment lines added in the
  previous commit so the frozen test file-size stays at its baseline (the
  rationale lives in that commit message, not the test body).

Gates: file-size, test-discovery, mutation-test-coverage, pack-policy,
open-sse-typecheck, dead-code all exit 0.

Refs #9737

* fix(translator): keep the reasoning_content placeholder for Xiaomi MiMo — #9610 traded one live 400 for another

The xiaomi-mimo replay test (9router#1321) went red on the base after #9610
removed the NON_ANTHROPIC_THINKING_PLACEHOLDER injection globally. That test
is NOT stale — it guards a documented upstream 400 ('Param Incorrect: The
reasoning_content in the thinking mode must be passed back to the API'), so
realigning it would have masked a reintroduced production bug.

Two real bugs conflict here:
- #9573: forwarding the placeholder makes the model continue its chain of
  thought FROM that text (echo -> empty stop) and re-poisons cache/history.
- 9router#1321/#1337: omitting reasoning_content on a plain replay turn makes
  Xiaomi MiMo reject the request outright.

#9610's evidence for omitting is provider-specific — it verified that
deepseek-v4-flash accepts an ABSENT field. It does not extend to MiMo. So the
omission stays for every provider #9610 covered, and the placeholder survives
the cache miss only for xiaomi-mimo (new requiresReasoningContentPresence
predicate next to isReasoningOnlyReplayTarget). The echo that comes back is
still stripped on the way in by isInternalReasoningPlaceholder(), so #9573's
cache/history poisoning stays fixed for MiMo too.

Both contracts now hold simultaneously: xiaomi-mimo replay + reasoning-cache +
tool-request-sanitization 61/61; placeholder-strip/responses/translator/combo
regression sweep 168/168. Gates: file-size, open-sse-typecheck, dead-code,
mutation-test-coverage exit 0; typecheck:core clean.

A live check on the VPS (Hard Rule #18 path 2) is the only way to confirm the
DeepSeek half of #9610's empirical claim; flagging it in the PR rather than
widening this fix on speculation.

Refs #9737

* test(translator): pin the reasoning-placeholder provider scope so neither half of the conflict can silently re-break

#9610 removed the placeholder globally on the strength of ONE provider's
observed behavior (deepseek-v4-flash accepting an absent reasoning_content),
which re-opened the MiMo 400 (9router#1321). The previous commit scoped the
placeholder to xiaomi-mimo; this pins BOTH directions in one test so the next
global edit fails loudly instead of trading the bugs again:

- xiaomi-mimo plain replay turn, cache miss -> reasoning_content present
  (narrowing the scope away from MiMo re-opens 9router#1321)
- deepseek plain replay turn, cache miss -> reasoning_content absent
  (widening it back to DeepSeek re-opens the #9573 echo bug)

Guard verified by mutation: forcing requiresReasoningContentPresence() to
return true makes the DeepSeek half fail (1 pass / 1 fail), and the file was
restored from the pre-probe copy before committing.

Also checked kimi-coding/kimi-coding-apikey, the other strict-contract entries
in REASONING_REPLAY_PROVIDERS: their originating PR (#7673) fixes capture and
replay of REAL reasoning and documents no 400 on an absent field, so they stay
out of the placeholder scope — evidence-scoped, not speculatively widened.

Reasoning suites together: 87/87. Gates: file-size, test-discovery,
mutation-test-coverage, dead-code exit 0; eslint clean.

Refs #9737

---------

Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>
2026-08-08 09:08:45 -03:00

219 lines
7.4 KiB
TypeScript

import {
asRecord,
DevinAgenticBridgeError,
estimateTokens,
type AnthropicTool,
type DevinPrompt,
} from "./types.ts";
import { createHash } from "node:crypto";
export const MAX_TOOL_RESULT_CHARS = 65536;
function stringifyContentValue(value: unknown): string {
if (typeof value === "string") return value;
if (value == null) return "";
return JSON.stringify(value);
}
function boundedToolResult(value: unknown): string {
const text = stringifyContentValue(value);
if (text.length <= MAX_TOOL_RESULT_CHARS) return text;
const removed = text.length - MAX_TOOL_RESULT_CHARS;
return `${text.slice(0, MAX_TOOL_RESULT_CHARS)}\n[TRUNCATED ${removed} CHARACTERS BY OMNIROUTE]`;
}
function serializeSystem(system: unknown): string[] {
if (typeof system === "string" && system.trim()) return [`[System]\n${system}`];
if (!Array.isArray(system)) return [];
const parts: string[] = [];
for (const block of system) {
const record = asRecord(block);
if (record.type === "text") {
parts.push(String(record.text || ""));
} else if (Object.keys(record).length > 0) {
throw new DevinAgenticBridgeError(
`Unsupported Anthropic system block type: ${String(record.type || "unknown")}`,
"unsupported_system_block"
);
}
}
return parts.length > 0 ? [`[System]\n${parts.join("\n")}`] : [];
}
function serializeBlock(
block: unknown,
knownToolUses: Set<string>,
tools: AnthropicTool[]
): string {
const record = asRecord(block);
const type = String(record.type || "");
if (type === "text") return String(record.text || "");
if (type === "thinking") return `[Thinking]\n${String(record.thinking || "")}`;
if (type === "redacted_thinking") return "[Redacted Thinking]";
if (type === "tool_use") {
const id = String(record.id || "").trim();
const name = String(record.name || "").trim();
if (!id || knownToolUses.has(id)) {
throw new DevinAgenticBridgeError(
id ? `Duplicate Anthropic tool_use id: ${id}` : "Anthropic tool_use is missing id",
id ? "duplicate_tool_use_id" : "missing_tool_use_id"
);
}
const declared = tools.find((tool) => tool.name === name);
if (!declared) {
throw new DevinAgenticBridgeError(
`Historical tool_use references undeclared tool: ${name || "unknown"}`,
"undeclared_historical_tool"
);
}
knownToolUses.add(id);
return [
"[Assistant Tool Use]",
`id: ${id}`,
`name: ${name}`,
"arguments:",
JSON.stringify(record.input || {}, null, 2),
].join("\n");
}
if (type === "tool_result") {
const toolUseId = String(record.tool_use_id || "").trim();
if (!toolUseId || !knownToolUses.has(toolUseId)) {
throw new DevinAgenticBridgeError(
`Anthropic tool_result references unknown tool_use id: ${toolUseId || "missing"}`,
"orphan_tool_result"
);
}
return [
"[Tool Result]",
`tool_use_id: ${toolUseId}`,
`is_error: ${record.is_error === true ? "true" : "false"}`,
"content:",
boundedToolResult(record.content),
].join("\n");
}
if (type === "image") {
throw new DevinAgenticBridgeError(
"Anthropic image blocks are not supported by devin-cli-agentic",
"unsupported_image_block"
);
}
throw new DevinAgenticBridgeError(
`Unsupported Anthropic content block type: ${type || "unknown"}`,
"unsupported_content_block"
);
}
function serializeMessage(
message: unknown,
knownToolUses: Set<string>,
tools: AnthropicTool[]
): string {
const record = asRecord(message);
const role = String(record.role || "user");
if (role !== "user" && role !== "assistant") {
throw new DevinAgenticBridgeError(
`Unsupported Anthropic message role: ${role}`,
"unsupported_role"
);
}
// role was just narrowed to "user" | "assistant" by the guard above ("system" throws).
const label = role === "assistant" ? "Assistant" : "User";
const content = record.content;
if (typeof content === "string") return `[${label}]\n${content}`;
if (!Array.isArray(content)) return `[${label}]\n${stringifyContentValue(content)}`;
return `[${label}]\n${content
.map((block) => serializeBlock(block, knownToolUses, tools))
.join("\n\n")}`;
}
function normalizeTools(tools: unknown): AnthropicTool[] {
if (tools == null) return [];
if (!Array.isArray(tools)) {
throw new DevinAgenticBridgeError("Anthropic tools must be an array", "invalid_tools");
}
return tools.map((tool) => {
const record = asRecord(tool);
const name = typeof record.name === "string" ? record.name.trim() : "";
if (!name) {
throw new DevinAgenticBridgeError("Anthropic tool is missing name", "invalid_tool_name");
}
return {
name,
description: typeof record.description === "string" ? record.description : undefined,
input_schema: asRecord(record.input_schema),
};
});
}
function serializeToolCatalog(tools: AnthropicTool[]): string[] {
if (tools.length === 0) return [];
return [
[
"[Available Tools]",
"When a tool is required, respond with exactly one XML-wrapped JSON object:",
'<tool>{"name":"ToolName","arguments":{}}</tool>',
"Use only the tools listed below. Do not claim that a tool was executed.",
"Do not execute tools inside Devin or emit ACP tool-call events; request them only with the XML envelope.",
"Never describe a future tool action in plain text; emit the tool envelope instead.",
].join("\n"),
...tools.map((tool) =>
[
`[Tool] ${tool.name}`,
tool.description ? `description: ${tool.description}` : "description:",
"input_schema:",
JSON.stringify(tool.input_schema || { type: "object", properties: {} }, null, 2),
].join("\n")
),
];
}
function serializeToolChoice(value: unknown, tools: AnthropicTool[]): string[] {
if (value == null) return [];
const choice = asRecord(value);
const type = String(choice.type || "");
if (type === "auto") return ["[Tool Choice]\nauto"];
if (type === "any") return ["[Tool Choice]\nA tool call is required."];
if (type === "none") return ["[Tool Choice]\nDo not call a tool."];
if (type === "tool") {
const name = String(choice.name || "").trim();
if (!tools.some((tool) => tool.name === name)) {
throw new DevinAgenticBridgeError(
`tool_choice references unknown tool: ${name}`,
"invalid_tool_choice"
);
}
return [`[Tool Choice]\nCall exactly this tool: ${name}`];
}
throw new DevinAgenticBridgeError(
`Unsupported Anthropic tool_choice type: ${type || "missing"}`,
"invalid_tool_choice"
);
}
export function serializeAnthropicForDevin(body: unknown): DevinPrompt {
const record = asRecord(body);
const messages = Array.isArray(record.messages) ? record.messages : [];
const tools = normalizeTools(record.tools);
const knownToolUses = new Set<string>();
const sections: string[] = [
...serializeSystem(record.system),
...serializeToolCatalog(tools),
...serializeToolChoice(record.tool_choice, tools),
...messages.map((message) => serializeMessage(message, knownToolUses, tools)),
].filter((section) => section.trim().length > 0);
if (sections.length === 0) {
throw new DevinAgenticBridgeError("Anthropic request contains no messages", "empty_messages");
}
const text = sections.join("\n\n---\n\n");
const idSeed = createHash("sha256").update(text).digest("hex").slice(0, 24);
return { text, tools, inputTokensEstimate: estimateTokens(text), idSeed };
}