opencode-zen-freex 0.2.7 → 0.2.9

package/limits-audit.mjs

@@ -1,262 +0,0 @@
-// Asks the route which free models it still offers, groups them by the upstream
-// model serving them, and says which look under-declared.
-//
-//   bun run limits:audit
-//
-// Why this exists. Zen's catalogue is where this plugin declares limits from,
-// and two of the ids it publishes were declared far below what the model does:
-// `deepseek-v4.1-flash-free` at 200000/32000 against 1048576/384000, and
-// `mimo-v2.6-flash-free` at 200000/32000 against 1048576/131072. Both were found
-// by hand, one id at a time. What makes them findable without reading every id
-// by eye is that the route answers `x-opencode-upstream-model-id` on every
-// request: two ids naming one upstream model are one capability, so a
-// declaration that differs inside such a group is the question worth asking.
-//
-// What this does not do: measure a window, or write anything. A window costs a
-// prompt of about a million tokens — minutes and megabytes — and belongs to the
-// one id a signal has already pointed at; the numbers live in limits.mjs and are
-// put there by a measurement, never by a script. What this does ask is cheap:
-// one request of `max_tokens: 1000000` per offered id that speaks the chat
-// shape, stopped as soon as it starts writing. An upstream that validates the
-// ceiling refuses and names its own; one that does not just begins to answer and
-// is cut off after the first chunk. Either way the cost is a handful of tokens,
-// and a 410 or a 400 for a model that is gone is visible in the same request.
-// An id the snapshot places on another protocol is listed and not asked.
-//
-// The offered set is the listing's, not the catalogue's: Zen's /v1/models
-// carries 10 of the 40 free ids the catalogue still describes, and a plugin
-// only ever offers what the listing has. Auditing the other 30 reports a page
-// of `Model is unavailable` about models nobody can pick.
-//
-// What is reported, per offered id: the upstream model and the ids sharing it,
-// the ceiling a refusal named, the window a refusal named, and the status. The
-// candidates at the end are the reason to run it.
-//
-// Exit code is 0 when at least one offered id answered, 1 when none did: being
-// unable to ask is not a finding about limits.
-
-import { PROFILES } from "./core-tools.mjs";
-import { LIMITS, limitOverrides, namedContextWindow, namedOutputCap } from "./limits.mjs";
-import { SDK, bootstrapProtocols } from "./models.mjs";
-import { CATALOG, DEFAULT_BASE } from "./provider.mjs";
-import { chatRequest } from "./tools-smoke.mjs";
-
-const BASE = process.env.ZEN_BASE_URL ?? DEFAULT_BASE;
-const CATALOG_URL = process.env.ZEN_CATALOG_URL ?? CATALOG;
-const GENERATION = process.env.ZEN_GENERATION ?? "1.x";
-const READ_BUDGET = 4096;
-const ASKED_CEILING = 1_000_000;
-
-// The ids the plugin would offer: the listing's, kept where the catalogue calls
-// them free — or, for an id neither the catalogue nor the docs describe, where
-// the id names itself free and nothing else names its protocol, which is what
-// models.mjs offers on its own say-so. An id the snapshot already calls
-// something this plugin has no SDK for is not offered by anyone: `jev-1.13-free`
-// is SystemOne, and stays out here for the same reason buildModels leaves it out.
-// Exported for the tests.
-export function offeredIds(listing, catalog, snapshot = bootstrapProtocols) {
-  return listing.filter((id) => {
-    const protocol = snapshot?.[id];
-    if (protocol !== undefined && !Object.hasOwn(SDK, protocol)) return false;
-    const model = catalog?.[id];
-    if (!model) return /-free$/.test(id);
-    return /free/i.test(id) || (model.cost?.input === 0 && model.cost?.output === 0);
-  });
-}
-
-// Offered ids by the upstream model serving them, which is the route's own
-// answer and not a guess from the id's shape.
-export function groupByUpstream(rows) {
-  const groups = new Map();
-  for (const row of rows) {
-    if (!row.upstream) continue;
-    groups.set(row.upstream, [...(groups.get(row.upstream) ?? []), row]);
-  }
-  return groups;
-}
-
-// What is worth a measurement, in the order it should be read. `covered` are the
-// ids limits.mjs already carries evidence for, which are said once and not
-// raised again. Exported for the tests.
-export function findings(rows, covered = new Set()) {
-  const out = [];
-  for (const row of rows) {
-    const declared = row.declared ?? {};
-    // An id limits.mjs already carries evidence for is not asked for again: its
-    // numbers are in the table and repeating them here would bury what is new.
-    // Its status is still printed in the table above, so a model that dies is
-    // not hidden by this — only its numbers stop being a question.
-    if (covered.has(row.id)) continue;
-    if (row.ceiling !== undefined && row.ceiling !== declared.output)
-      out.push(
-        `${row.id}: the route names a ceiling of ${row.ceiling} completion tokens, the catalogue declares ${declared.output ?? "none"}`,
-      );
-    if (row.window !== undefined && row.window !== declared.context)
-      out.push(
-        `${row.id}: a refusal named a window of ${row.window}, the catalogue declares ${declared.context ?? "none"}`,
-      );
-    const named = row.ceiling !== undefined || row.window !== undefined;
-    // A model that does not speak the shape this audit asks with is not a limits
-    // finding and must not sit in this list for ever: it is said once, beside the
-    // ids that were not asked at all.
-    if (protocolScoped(row)) continue;
-    if (row.status !== 200 && !named) {
-      // What is left is worth reading: a 410, and a 400 that named nothing.
-      out.push(`${row.id}: HTTP ${row.status}${row.says ? ` — ${row.says}` : ""}`);
-    }
-  }
-  for (const [upstream, list] of groupByUpstream(rows)) {
-    const largest = (axis) => Math.max(...list.map((row) => row.declared?.[axis] ?? 0));
-    if (list.length < 2) continue;
-    if (new Set(list.map((row) => `${row.declared?.context}/${row.declared?.output}`)).size < 2) continue;
-    for (const row of list) {
-      if (covered.has(row.id)) continue;
-      if ((row.declared?.context ?? 0) >= largest("context") && (row.declared?.output ?? 0) >= largest("output"))
-        continue;
-      const siblings = list
-        .filter((other) => other.id !== row.id)
-        .map((other) => `${other.id} (${other.declared?.context}/${other.declared?.output})`)
-        .join(", ");
-      out.push(
-        `${row.id}: declared ${row.declared?.context}/${row.declared?.output}, and ${upstream} is also served as ${siblings}`,
-      );
-    }
-  }
-  return out;
-}
-
-function says(text) {
-  const match = text.match(/"(?:message|param)"\s*:\s*"([^"]{0,160})"/);
-  if (match) return match[1];
-  // Some upstreams refuse in words that are not under a `message` key at all,
-  // and a refusal nobody can read is not a finding.
-  const flat = text.replace(/\s+/g, " ").trim();
-  return flat ? flat.slice(0, 160) : "";
-}
-
-// A refusal that names the protocol rather than a limit. This audit asks the
-// chat shape, so a model that speaks Responses or Messages answers by saying so;
-// that is the host's business, not a limit to measure.
-export function protocolScoped(row) {
-  return /protocol|format/i.test(row?.says ?? "");
-}
-
-async function getJSON(url) {
-  const response = await fetch(url, { signal: AbortSignal.timeout(30000) });
-  if (!response.ok) throw new Error(`${url} answered HTTP ${response.status}`);
-  return response.json();
-}
-
-// One cheap question per id. The ceiling asked for is past anything this route
-// serves, so an upstream that validates it says what it allows, and the stream
-// is dropped as soon as it starts rather than paying for an answer nobody reads.
-async function ask(id, names) {
-  const { headers, body } = chatRequest({
-    model: id,
-    generation: GENERATION,
-    profile: PROFILES[GENERATION],
-    names,
-    maxTokens: ASKED_CEILING,
-  });
-  const controller = new AbortController();
-  const timer = setTimeout(() => controller.abort(), 45000);
-  try {
-    const response = await fetch(`${BASE}/chat/completions`, {
-      method: "POST",
-      headers,
-      body: JSON.stringify(body),
-      signal: controller.signal,
-    });
-    let text = "";
-    if (response.ok) {
-      const reader = response.body?.getReader();
-      if (reader) {
-        const decoder = new TextDecoder();
-        while (text.length < READ_BUDGET) {
-          const { value, done } = await reader.read();
-          if (done) break;
-          text += decoder.decode(value, { stream: true });
-        }
-      }
-    } else {
-      text = (await response.text()).slice(0, READ_BUDGET);
-    }
-    const upstream = response.headers.get("x-opencode-upstream-model-id") ?? undefined;
-    const endpoint = response.headers.get("x-opencode-endpoint-id") ?? undefined;
-    return {
-      status: response.status,
-      upstream,
-      endpoint,
-      window: namedContextWindow(text),
-      ceiling: namedOutputCap(text),
-      says: response.ok ? "" : says(text),
-    };
-  } catch (error) {
-    return { status: 0, says: error.message, upstream: undefined, endpoint: undefined };
-  } finally {
-    clearTimeout(timer);
-    controller.abort();
-  }
-}
-
-// Only a run asks the route. The tests import the helpers above and must not
-// reach the network.
-if (import.meta.main) {
-  const names = [...PROFILES[GENERATION].required];
-  const [listing, catalog] = await Promise.all([getJSON(`${BASE}/models`), getJSON(CATALOG_URL)]);
-  const models = catalog?.opencode?.models ?? {};
-  const ids = offeredIds(
-    (Array.isArray(listing?.data) ? listing.data : []).map((entry) => entry?.id).filter(Boolean),
-    models,
-  );
-  const free = Object.keys(models).filter(
-    (id) => /free/i.test(id) || (models[id].cost?.input === 0 && models[id].cost?.output === 0),
-  );
-  console.log(`limits audit — ${BASE}`);
-  console.log(`${ids.length} free ids are offered; the catalogue still describes ${free.length}\n`);
-
-  const rows = [];
-  // This asks the chat shape only. An id the snapshot places on another protocol
-  // is left to the host that speaks it, and said once rather than reported as a
-  // finding it cannot be.
-  const asked = ids.filter((id) => (bootstrapProtocols[id] ?? "chat") === "chat");
-  const elsewhere = ids.filter((id) => !asked.includes(id));
-  for (const id of asked) {
-    const answer = await ask(id, names);
-    const declared = models[id]?.limit ?? {};
-    rows.push({ id, declared, ...answer });
-    // What the plugin declares is the catalogue's limit with limits.mjs over it,
-    // so that is what is printed; the catalogue's own pair is shown beside it
-    // when the two differ, since that is the under-report being answered.
-    const effective = { ...declared, ...limitOverrides(id, declared) };
-    const moved = effective.context !== declared.context || effective.output !== declared.output;
-    const pair = (limit) => `${limit.context ?? "—"}/${limit.output ?? "—"}`;
-    const mark = answer.status === 200 ? "  " : "! ";
-    console.log(
-      `${mark}${id.padEnd(34)} ${pair(effective).padStart(17)}` +
-        `${moved ? `  (catalogue ${pair(declared)})` : ""}  ${answer.status}` +
-        `${answer.upstream ? `  ${answer.upstream}${answer.endpoint ? ` via ${answer.endpoint}` : ""}` : ""}` +
-        `${answer.ceiling !== undefined ? `  ceiling=${answer.ceiling}` : ""}${answer.window !== undefined ? `  window=${answer.window}` : ""}` +
-        `${answer.says ? `  — ${answer.says}` : ""}`,
-    );
-  }
-
-  const answered = rows.filter((row) => row.status === 200);
-  const candidates = findings(rows, new Set(Object.keys(LIMITS)));
-  const skipped = [...elsewhere, ...rows.filter(protocolScoped).map((row) => row.id)];
-  if (skipped.length)
-    console.log(
-      `\nnot asked, this audit asks the chat shape only: ${skipped.map((id) => `${id}${bootstrapProtocols[id] ? ` (${bootstrapProtocols[id]})` : ""}`).join(", ")}`,
-    );
-  console.log(`\nlimits.mjs already carries evidence for: ${Object.keys(LIMITS).join(", ")}`);
-  console.log(`\n${candidates.length} candidate${candidates.length === 1 ? "" : "s"}:`);
-  for (const line of candidates) console.log(`  ${line}`);
-  if (!candidates.length) console.log("  none — every offered id is either measured or declared at what the route states");
-
-  if (!answered.length) {
-    console.log(
-      "\nNothing answered, so this says nothing about limits. Check the network or ZEN_BASE_URL and ask again.",
-    );
-    process.exitCode = 1;
-  }
-}

package/tools-smoke.mjs

@@ -1,175 +0,0 @@
-// Asks Zen which of the client generations this package still speaks.
-//
-// The gate moved more than once in a day, and nothing short of asking it says
-// so: a stale fingerprint does not look different from a working one until a
-// user is refused. This is the check to run before a release, and whenever a
-// report comes in that the free tier answers 403.
-//
-//   bun run check:gate
-//
-// Each profile is asked twice, because the plugin sends two shapes and Zen
-// does not answer them alike:
-//
-//   floor  the names in `required`, which is what the plugin stands in for a
-//          host that is not OpenCode and has none of these tools by name. This
-//          is the shape the plugin exists to send, so it is the one that
-//          decides the answer.
-//   full   every tool the profile carries, which is what a host that is
-//          OpenCode itself sends. It is reported for what it says about a
-//          wording that has gone stale, and does not decide the exit code.
-//
-// Asking only the full shape hid a real gap: `read` alone is served and
-// everything but `read` is refused, so a Zen that started insisting on another
-// name would leave the full shape passing while the shape the plugin actually
-// sends was refused.
-//
-// Every request here is built by the plugin itself: the header names come from
-// provider.mjs's outboundHeaders and the tools from the same `required` the
-// plugin stands in, so this cannot report on a shape the plugin does not send.
-// A copy of the headers is what it used to ask with, and that copy had drifted -
-// it was missing `accept` - with nothing failing on it.
-//
-// Each request is reported as:
-//
-//   answered   Zen served the request; this shape is current
-//   refused    Zen did not recognise this generation (403)
-//   superseded Zen wants a newer OpenCode than the one this profile claims (426)
-//   unreachable the free tier could not be asked at all
-//
-// Exit code is 0 when at least one generation's floor is answered. A generation
-// being refused is not a failure while another still works.
-
-import { randomBytes } from "node:crypto";
-import { PROFILES, agentFor } from "./core-tools.mjs";
-import { outboundHeaders } from "./provider.mjs";
-
-const BASE = process.env.ZEN_BASE_URL ?? "https://opencode.ai/inference/v1";
-const MODEL = process.env.ZEN_CHECK_MODEL ?? "space-bunny-free";
-const ALPHABET = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz";
-
-// A session id of the shape OpenCode makes, since that is part of what is asked.
-let stamp = 0;
-let counter = 0;
-function sessionID() {
-  const now = Date.now();
-  if (now !== stamp) {
-    stamp = now;
-    counter = 0;
-  }
-  counter++;
-  const value = (~(BigInt(now) * 0x1000n + BigInt(counter))) & 0xffffffffffffn;
-  let tail = "";
-  for (const byte of randomBytes(14)) tail += ALPHABET[byte % 62];
-  return `ses_${value.toString(16).padStart(12, "0")}${tail}`;
-}
-
-// Zen gives the same sentence whichever part of a request failed to look like
-// OpenCode, so it is worth printing: a refusal that arrives with no message at
-// all reads as something other than a stale fingerprint.
-function says(text) {
-  const match = text.match(/"message"\s*:\s*"([^"]{0,120})"/);
-  return match ? `: ${match[1]}` : "";
-}
-
-// The request a shape is asked with. It is its own function so index.test.mjs
-// can hold it against the request the plugin was observed to send, offline, and
-// so limits-audit.mjs asks with the same shape this gate does instead of a copy
-// of it — a copy is what drifted before (it was missing `accept`).
-export function requestFor(generation, profile, names) {
-  return chatRequest({ model: MODEL, generation, profile, names, maxTokens: 40 });
-}
-
-export function chatRequest({ model, generation, profile, names, maxTokens = 40, messages }) {
-  return {
-    headers: outboundHeaders({
-      session: sessionID(),
-      agent: agentFor(generation),
-      project: "global",
-      protocol: "chat",
-    }),
-    body: {
-      model,
-      messages: messages ?? [{ role: "user", content: "hi" }],
-      tools: names.map((name) => ({ type: "function", function: profile.tools[name] })),
-      stream: true,
-      stream_options: { include_usage: true },
-      max_tokens: maxTokens,
-    },
-  };
-}
-
-async function check(generation, profile, shape, names) {
-  const { headers, body } = requestFor(generation, profile, names);
-  try {
-    const response = await fetch(`${BASE}/chat/completions`, {
-      method: "POST",
-      headers,
-      body: JSON.stringify(body),
-      signal: AbortSignal.timeout(30000),
-    });
-    const text = await response.text();
-    if (response.ok)
-      return { generation, shape, verdict: "answered", detail: `as ${headers.get("user-agent")}` };
-    if (response.status === 426)
-      return {
-        generation,
-        shape,
-        verdict: "superseded",
-        detail: "Zen wants a newer OpenCode than this profile claims",
-      };
-    return { generation, shape, verdict: "refused", detail: `HTTP ${response.status}${says(text)}` };
-  } catch (error) {
-    return { generation, shape, verdict: "unreachable", detail: error.message };
-  }
-}
-
-// Only a run asks Zen. index.test.mjs imports this module to hold its request
-// against the plugin's, and an import must not reach the network.
-if (import.meta.main) {
-  const results = [];
-  for (const [generation, profile] of Object.entries(PROFILES)) {
-    results.push(await check(generation, profile, "floor", [...profile.required]));
-    results.push(await check(generation, profile, "full", Object.keys(profile.tools)));
-  }
-
-  const width = Math.max(...results.map((result) => result.generation.length));
-  for (const result of results)
-    console.log(
-      `${result.shape.padEnd(6)}${result.verdict.padEnd(12)} ${result.generation.padEnd(width)}  ${result.detail}`,
-    );
-
-  const floor = results.filter((result) => result.shape === "floor");
-  const served = floor.filter((result) => result.verdict === "answered");
-  console.log(`\n${served.length}/${floor.length} generations serve a host that is not OpenCode at ${BASE}`);
-
-  // A generation whose full shape is served while its floor is not is the case
-  // this gate was widened to see: the plugin would work for a host bringing its
-  // own OpenCode tools and be refused for the host it was written for.
-  for (const result of floor) {
-    if (result.verdict === "answered") continue;
-    const full = results.find(
-      (other) => other.generation === result.generation && other.shape === "full",
-    );
-    if (full?.verdict === "answered")
-      console.log(
-        `${result.generation} answers the full OpenCode shape but not the tools the plugin stands in: a host that has none of them by name will be refused.`,
-      );
-  }
-
-  if (!served.length) {
-    // Being unable to ask is not an answer. Saying the fingerprint has gone stale
-    // when nothing was reached sends the reader to `capture` over a dead network.
-    if (results.every((result) => result.verdict === "unreachable")) {
-      console.log(
-        "The free tier could not be reached at all, so this says nothing about the fingerprint. Check the network or ZEN_BASE_URL and ask again.",
-      );
-    } else {
-      console.log(
-        "None of them. Zen has moved past every generation this plugin knows; the tool wording in core-tools.mjs needs capturing again from a current OpenCode.",
-      );
-    }
-    process.exitCode = 1;
-  } else if (served.length < floor.length) {
-    console.log("Some are refused but at least one works, so the plugin still has a generation Zen will serve.");
-  }
-}