fix: default cross-model workflows to frontier models

2026-09-09 22:48:57 +02:00 · 2026-09-09 02:48:34 +00:00
parent 0530392821
commit 939da0c203
69 changed files with 603 additions and 255 deletions
@@ -24,6 +24,7 @@ export const ALL_MODEL_NAMES = [
  'gpt',
  'gpt-5.4',
  'gpt-5.6-sol',
+  'gpt-6-astra',
  'gemini',
  'o-series',
 ] as const;
@@ -62,6 +63,7 @@ export function resolveModel(input: string): Model | null {
  // not add a Sol family pattern: Terra, Luna, future 5.6 variants, and
  // suffixed model IDs must NOT inherit Sol's behavioral profile; they fall
  // through to the generic `gpt` family below.
+  if (/^gpt-6-astra(-|$)/.test(s)) return 'gpt-6-astra';
  if (/^gpt-5\.4(-|$)/.test(s)) return 'gpt-5.4';
  if (/^gpt(-|$)/.test(s)) return 'gpt';
  if (/^o[0-9]+(-|$)/.test(s)) return 'o-series';
@@ -11,7 +11,7 @@ export interface CodexGenerationModelResolution {
  warnings: string[];
 }

-const CODEX_DEFAULT_MODEL: Model = 'gpt';
+const CODEX_DEFAULT_MODEL: Model = 'gpt-6-astra';
 const DEFAULT_SOURCE = `default (${CODEX_DEFAULT_MODEL})`;

 /**
@@ -64,6 +64,19 @@ export const OPENAI_LITMUS_CHECKS = [
 */
 export const CODEX_WEB_SEARCH_FLAG = `-c 'web_search="cached"'`;

+/**
+ * Default model for gstack-owned Codex invocations.
+ *
+ * Conductor's current Codex CLI default may lag the frontier model exposed to
+ * agents, so gstack pins its own default and lets users override it per shell
+ * with GSTACK_CODEX_MODEL or per invocation with an explicit `-c model=...`.
+ * The -c form is accepted by both `codex exec` and `codex review`.
+ */
+export const CODEX_FRONTIER_MODEL = 'gpt-6-astra';
+export const CODEX_MODEL_CONFIG_FLAG = `-c "model=\\"\${GSTACK_CODEX_MODEL:-${CODEX_FRONTIER_MODEL}}\\""`;
+// Native review prefers review_model over model when the user has pinned it.
+export const CODEX_REVIEW_MODEL_CONFIG_FLAG = `${CODEX_MODEL_CONFIG_FLAG} -c "review_model=\\"\${GSTACK_CODEX_MODEL:-${CODEX_FRONTIER_MODEL}}\\""`;
+
 /**
 * Shared Codex error handling block for resolver output.
 * Used by ADVERSARIAL_STEP, CODEX_PLAN_REVIEW, CODEX_SECOND_OPINION,
@@ -151,7 +164,7 @@ Branch on the echoed \`CODEX_MODE\`:
 - **\`under_codex\`** — this session is already running INSIDE a Codex host, so spawning codex again is the same model reviewing itself at multiplied token cost (#2519). Print exactly one line: "[running under Codex — nested codex passes skipped; set GSTACK_FORCE_CODEX_REVIEW=1 to force]" and skip the codex invocations below; run the section's free in-host pass instead if it defines one.
 - **\`not_authed\`** — installed but no credentials. Print: "Codex installed but not authenticated — falling back to a Claude subagent (same model family, not an outside model). Run \`codex login\` or set \`$CODEX_API_KEY\`." Fall back to the Claude subagent path.
 - **\`broken_install\`** — the CLI is on PATH but cannot execute (spawn ENOENT, non-executable binary, missing vendor payload). Print: "Codex is installed but its binary cannot run — Codex passes skipped. Reinstall: \`npm install -g @openai/codex\`." Relay the probe's HINT lines and fall back to the Claude subagent path. This state exists because a missing binary used to land in the model probe's fail-open bucket and report \`ready\`, so every Codex pass was skipped silently (#2742).
- **\`model_unusable\`** — authed but the account cannot use its configured model (#2477: HTTP 400 on every call, usually a stale \`model =\` pin in \`~/.codex/config.toml\`). Relay the probe's HINT lines, tell the user the one-line fix (update the pin; \`[notice.model_migrations]\` names the replacement), and fall back to the Claude subagent path. The ~10s round trip is cached for 1h; timeouts fail open to \`ready\`.
+- **\`model_unusable\`** — authed but the account cannot use gstack's selected Codex model (#2477: HTTP 400 on every call). Relay the probe's HINT lines, tell the user the one-line fix (set \`GSTACK_CODEX_MODEL=<supported-model>\` or pass an explicit \`-c model=...\` override), and fall back to the Claude subagent path. The ~10s round trip is cached for 1h; timeouts fail open to \`ready\`.
 - **\`ready\`** — run the Codex pass below.`;
 }

@@ -1,5 +1,5 @@
 import { type TemplateContext, toShellPath } from './types';
-import { AI_SLOP_BLACKLIST, OPENAI_HARD_REJECTIONS, OPENAI_LITMUS_CHECKS, CODEX_WEB_SEARCH_FLAG, CC_BACKGROUND_DEFAULT_SINCE } from './constants';
+import { AI_SLOP_BLACKLIST, OPENAI_HARD_REJECTIONS, OPENAI_LITMUS_CHECKS, CODEX_MODEL_CONFIG_FLAG, CODEX_WEB_SEARCH_FLAG, CC_BACKGROUND_DEFAULT_SINCE } from './constants';

 export function generateDesignReviewLite(ctx: TemplateContext): string {
  const litmusList = OPENAI_LITMUS_CHECKS.map((item, i) => `${i + 1}. ${item}`).join(' ');
@@ -18,7 +18,7 @@ If Codex is available, run a lightweight design check on the diff:
 \`\`\`bash
 TMPERR_DRL=$(mktemp /tmp/codex-drl-XXXXXXXX)
 _REPO_ROOT=$(git rev-parse --show-toplevel) || { echo "ERROR: not in a git repo" >&2; exit 1; }
-codex exec "Review the git diff on this branch. Run 7 litmus checks (YES/NO each): ${litmusList} Flag any hard rejections: ${rejectionList} 5 most important design findings only. Reference file:line." -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="high"' ${CODEX_WEB_SEARCH_FLAG} < /dev/null 2>"$TMPERR_DRL"
+codex exec "Review the git diff on this branch. Run 7 litmus checks (YES/NO each): ${litmusList} Flag any hard rejections: ${rejectionList} 5 most important design findings only. Reference file:line." -C "$_REPO_ROOT" -s read-only ${CODEX_MODEL_CONFIG_FLAG} -c 'model_reasoning_effort="high"' ${CODEX_WEB_SEARCH_FLAG} < /dev/null 2>"$TMPERR_DRL"
 \`\`\`

 Use a 5-minute timeout (\`timeout: 300000\`). After the command completes, read stderr:
@@ -587,7 +587,7 @@ If user chooses A, launch both voices simultaneously:
 \`\`\`bash
 TMPERR_SKETCH=$(mktemp /tmp/codex-sketch-XXXXXXXX)
 _REPO_ROOT=$(git rev-parse --show-toplevel) || { echo "ERROR: not in a git repo" >&2; exit 1; }
-codex exec "For this product approach, provide: a visual thesis (one sentence — mood, material, energy), a content plan (hero → support → detail → CTA), and 2 interaction ideas that change page feel. Apply beautiful defaults: composition-first, brand-first, cardless, poster not document. Be opinionated." -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="medium"' ${CODEX_WEB_SEARCH_FLAG} < /dev/null 2>"$TMPERR_SKETCH"
+codex exec "For this product approach, provide: a visual thesis (one sentence — mood, material, energy), a content plan (hero → support → detail → CTA), and 2 interaction ideas that change page feel. Apply beautiful defaults: composition-first, brand-first, cardless, poster not document. Be opinionated." -C "$_REPO_ROOT" -s read-only ${CODEX_MODEL_CONFIG_FLAG} -c 'model_reasoning_effort="medium"' ${CODEX_WEB_SEARCH_FLAG} < /dev/null 2>"$TMPERR_SKETCH"
 \`\`\`
 Use a 5-minute timeout (\`timeout: 300000\`). After completion: \`cat "$TMPERR_SKETCH" && rm -f "$TMPERR_SKETCH"\`

@@ -757,7 +757,7 @@ command -v codex >/dev/null 2>&1 && echo "CODEX_AVAILABLE" || echo "CODEX_NOT_AV
 \`\`\`bash
 TMPERR_DESIGN=$(mktemp /tmp/codex-design-XXXXXXXX)
 _REPO_ROOT=$(git rev-parse --show-toplevel) || { echo "ERROR: not in a git repo" >&2; exit 1; }
-codex exec "${escapedCodexPrompt}" -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="${reasoningEffort}"' ${CODEX_WEB_SEARCH_FLAG} < /dev/null 2>"$TMPERR_DESIGN"
+codex exec "${escapedCodexPrompt}" -C "$_REPO_ROOT" -s read-only ${CODEX_MODEL_CONFIG_FLAG} -c 'model_reasoning_effort="${reasoningEffort}"' ${CODEX_WEB_SEARCH_FLAG} < /dev/null 2>"$TMPERR_DESIGN"
 \`\`\`
 Use a 5-minute timeout (\`timeout: 300000\`). After the command completes, read stderr:
 \`\`\`bash
@@ -1206,4 +1206,3 @@ Flat design can strip away useful visual information that signals interactivity.
 Prioritize ruthlessly: things needed in a hurry go close at hand, everything
 else a few taps away with an obvious path to get there.`;
 }
-
@@ -22,7 +22,7 @@ import { generateTestFailureTriage } from './preamble';
 import { generateDesignMethodology, generateDesignHardRules, generateDesignOutsideVoices, generateDesignReviewLite, generateDesignSketch, generateDesignSetup, generateDesignMockup, generateDesignShotgunLoop, generateTasteProfile, generateUXPrinciples } from './design';
 import { generateTestBootstrap, generateTestCoverageAuditPlan, generateTestCoverageAuditShip } from './testing';
 import { generateReviewDashboard, generatePlanFileReviewReport, generateExitPlanModeGate, generateAntiShortcutClause, generateSpecReviewLoop, generateBenefitsFrom, generateCodexSecondOpinion, generateAdversarialStep, generateCodexPlanReview, generateCodexDocReview, generatePlanCompletionAuditShip, generatePlanCompletionAuditReview, generatePlanVerificationExec, generateScopeDrift, generateCrossReviewDedup } from './review';
-import { generateSlugEval, generateSlugSetup, generateBaseBranchDetect, generateDeployBootstrap, generateQAMethodology, generateCoAuthorTrailer, generateChangelogWorkflow, generateCodexWebSearchFlag, generateSetupCommand } from './utility';
+import { generateSlugEval, generateSlugSetup, generateBaseBranchDetect, generateDeployBootstrap, generateQAMethodology, generateCoAuthorTrailer, generateChangelogWorkflow, generateCodexWebSearchFlag, generateCodexModelConfigFlag, generateCodexReviewModelConfigFlag, generateClaudeModelFlag, generateSetupCommand } from './utility';
 import { generateLearningsSearch, generateLearningsLog } from './learnings';
 import { generateConfidenceCalibration } from './confidence';
 import { generateInvokeSkill } from './composition';
@@ -42,6 +42,9 @@ export const RESOLVERS: Record<string, ResolverFn> = {
  SLUG_EVAL: generateSlugEval,
  SLUG_SETUP: generateSlugSetup,
  CODEX_WEB_SEARCH_FLAG: generateCodexWebSearchFlag,
+  CODEX_MODEL_CONFIG_FLAG: generateCodexModelConfigFlag,
+  CODEX_REVIEW_MODEL_CONFIG_FLAG: generateCodexReviewModelConfigFlag,
+  CLAUDE_MODEL_FLAG: generateClaudeModelFlag,
  REDACT_INVOCATION_BLOCK: generateRedactInvocationBlock,
  THIRD_PARTY_ACTIONS: generateThirdPartyActions,
  DESIGN_DOC_DISCOVERY: generateDesignDocDiscovery,
@@ -14,7 +14,7 @@
 */
 import type { TemplateContext } from './types';
 import { generateInvokeSkill } from './composition';
-import { codexPreflight, codexErrorHandling, CODEX_WEB_SEARCH_FLAG, CC_BACKGROUND_DEFAULT_SINCE } from './constants';
+import { codexPreflight, codexErrorHandling, CODEX_MODEL_CONFIG_FLAG, CODEX_REVIEW_MODEL_CONFIG_FLAG, CODEX_WEB_SEARCH_FLAG, CC_BACKGROUND_DEFAULT_SINCE } from './constants';
 import { DESIGN_DOC_DISCOVERY_BLOCK } from './design-doc-discovery';
 import { getHostConfig } from '../../hosts/index';

@@ -370,7 +370,7 @@ Then add the context block and mode-appropriate instructions:
 \`\`\`bash
 TMPERR_OH=$(mktemp /tmp/codex-oh-err-XXXXXXXX)
 _REPO_ROOT=$(git rev-parse --show-toplevel) || { echo "ERROR: not in a git repo" >&2; exit 1; }
-codex exec "$(cat "$CODEX_PROMPT_FILE")" -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="high"' ${CODEX_WEB_SEARCH_FLAG} < /dev/null 2>"$TMPERR_OH"
+codex exec "$(cat "$CODEX_PROMPT_FILE")" -C "$_REPO_ROOT" -s read-only ${CODEX_MODEL_CONFIG_FLAG} -c 'model_reasoning_effort="high"' ${CODEX_WEB_SEARCH_FLAG} < /dev/null 2>"$TMPERR_OH"
 \`\`\`

 Use a 5-minute timeout (\`timeout: 300000\`). After the command completes, read stderr:
@@ -534,7 +534,7 @@ _REPO_ROOT=$(git rev-parse --show-toplevel) || { echo "ERROR: not in a git repo"
 # here. It defines _gstack_codex_timeout_wrapper (gtimeout -> timeout ->
 # unwrapped fallback), added in #1056 but never wired into this call site.
 source ~/.claude/skills/gstack/bin/gstack-codex-probe 2>/dev/null || true
-_gstack_codex_timeout_wrapper 540 codex exec "${CODEX_BOUNDARY}Review the changes on this branch against the base branch. Run DIFF_BASE=$(git merge-base origin/<base> HEAD) && git diff "$DIFF_BASE" to see the diff. Your job is to find ways this code will fail in production. Think like an attacker and a chaos engineer. Find edge cases, race conditions, security holes, resource leaks, failure modes, and silent data corruption paths. Be adversarial. Be thorough. No compliments — just the problems. End your output with ONE line in the canonical format \`Recommendation: <action> because <one-line reason naming the most exploitable finding>\`. Generic reasons like 'because it's safer' do not qualify; the reason must point to a specific finding or no-fix rationale." -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="high"' ${CODEX_WEB_SEARCH_FLAG} < /dev/null 2>"$TMPERR_ADV"
+_gstack_codex_timeout_wrapper 540 codex exec "${CODEX_BOUNDARY}Review the changes on this branch against the base branch. Run DIFF_BASE=$(git merge-base origin/<base> HEAD) && git diff "$DIFF_BASE" to see the diff. Your job is to find ways this code will fail in production. Think like an attacker and a chaos engineer. Find edge cases, race conditions, security holes, resource leaks, failure modes, and silent data corruption paths. Be adversarial. Be thorough. No compliments — just the problems. End your output with ONE line in the canonical format \`Recommendation: <action> because <one-line reason naming the most exploitable finding>\`. Generic reasons like 'because it's safer' do not qualify; the reason must point to a specific finding or no-fix rationale." -C "$_REPO_ROOT" -s read-only ${CODEX_MODEL_CONFIG_FLAG} -c 'model_reasoning_effort="high"' ${CODEX_WEB_SEARCH_FLAG} < /dev/null 2>"$TMPERR_ADV"
 \`\`\`

 Set the Bash tool's \`timeout\` parameter to \`600000\` (10 minutes). It sits ABOVE the 540s wrapper deliberately, so the wrapper fires first and a stall surfaces as a diagnosable exit 124 instead of a harness kill that returns nothing. The wrapper resolves \`gtimeout\`, then \`timeout\`, then runs unwrapped, so it is safe on a macOS without coreutils. After the command completes, read stderr:
@@ -567,7 +567,7 @@ cd "$_REPO_ROOT"
 # here. It defines _gstack_codex_timeout_wrapper (gtimeout -> timeout ->
 # unwrapped fallback), added in #1056 but never wired into this call site.
 source ~/.claude/skills/gstack/bin/gstack-codex-probe 2>/dev/null || true
-_gstack_codex_timeout_wrapper 540 codex review --base <base> -c 'model_reasoning_effort="high"' ${CODEX_WEB_SEARCH_FLAG} < /dev/null 2>"$TMPERR"
+_gstack_codex_timeout_wrapper 540 codex review --base <base> ${CODEX_REVIEW_MODEL_CONFIG_FLAG} -c 'model_reasoning_effort="high"' ${CODEX_WEB_SEARCH_FLAG} < /dev/null 2>"$TMPERR"
 \`\`\`

 **No prompt argument.** \`--base\` is what scopes the review, and the positional \`[PROMPT]\` is mutually exclusive with it — passing both fails at argv parsing. Do NOT "fix" that error by dropping \`--base\` and keeping the prompt: a prompt-only \`codex review\` silently falls back to the **uncommitted working-tree** scope (\`git status --short; git diff\`), so it reviews the wrong changes and reports "no changes" on a clean tree. Prompt text describing the diff range does not change what the CLI feeds the reviewer. Unlike the adversarial pass above, which uses \`codex exec\` and really does run the git command it's told to, this path gets a pre-computed diff from the CLI — which is also why it needs no filesystem boundary.
@@ -668,7 +668,7 @@ THE PLAN:
 \`\`\`bash
 TMPERR_PV=$(mktemp /tmp/codex-planreview-XXXXXXXX)
 _REPO_ROOT=$(git rev-parse --show-toplevel) || { echo "ERROR: not in a git repo" >&2; exit 1; }
-codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="high"' ${CODEX_WEB_SEARCH_FLAG} < /dev/null 2>"$TMPERR_PV"
+codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only ${CODEX_MODEL_CONFIG_FLAG} -c 'model_reasoning_effort="high"' ${CODEX_WEB_SEARCH_FLAG} < /dev/null 2>"$TMPERR_PV"
 \`\`\`

 Use a 5-minute timeout (\`timeout: 300000\`). After the command completes, read stderr:
@@ -808,7 +808,7 @@ THE DOCS AND DIFF: <list the touched doc paths>"
 \`\`\`bash
 TMPERR_DOC=$(mktemp /tmp/codex-docreview-XXXXXXXX)
 _REPO_ROOT=$(git rev-parse --show-toplevel) || { echo "ERROR: not in a git repo" >&2; exit 1; }
-codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="high"' ${CODEX_WEB_SEARCH_FLAG} < /dev/null 2>"$TMPERR_DOC"
+codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only ${CODEX_MODEL_CONFIG_FLAG} -c 'model_reasoning_effort="high"' ${CODEX_WEB_SEARCH_FLAG} < /dev/null 2>"$TMPERR_DOC"
 \`\`\`

 Use a 5-minute timeout (\`timeout: 300000\`). After the command completes, read stderr:
@@ -1,5 +1,6 @@
 import type { TemplateContext } from './types';
-import { CODEX_WEB_SEARCH_FLAG } from './constants';
+import { CODEX_MODEL_CONFIG_FLAG, CODEX_REVIEW_MODEL_CONFIG_FLAG, CODEX_WEB_SEARCH_FLAG } from './constants';
+import { CLAUDE_FRONTIER_EVAL_MODEL } from '../../lib/eval-model';

 /**
 * {{CODEX_WEB_SEARCH_FLAG}} — the non-deprecated codex web-search flag
@@ -10,6 +11,23 @@ export function generateCodexWebSearchFlag(_ctx: TemplateContext): string {
  return CODEX_WEB_SEARCH_FLAG;
 }

+/**
+ * {{CODEX_MODEL_CONFIG_FLAG}} — the default frontier Codex model override.
+ * Users can override it with GSTACK_CODEX_MODEL, or replace it with a
+ * request-specific `-c model="..."` when the skill input names a model.
+ */
+export function generateCodexModelConfigFlag(_ctx: TemplateContext): string {
+  return CODEX_MODEL_CONFIG_FLAG;
+}
+
+export function generateCodexReviewModelConfigFlag(_ctx: TemplateContext): string {
+  return CODEX_REVIEW_MODEL_CONFIG_FLAG;
+}
+
+export function generateClaudeModelFlag(_ctx: TemplateContext): string {
+  return `--model "\${GSTACK_CLAUDE_MODEL:-${CLAUDE_FRONTIER_EVAL_MODEL}}"`;
+}
+
 export function generateSlugEval(ctx: TemplateContext): string {
  return `eval "$(${ctx.paths.binDir}/gstack-slug 2>/dev/null)"`;
 }