Fix swarm grok compat with grok CLI 0.2.101

.claude-plugin/marketplace.json

@@ -29,8 +29,8 @@
     {
       "name": "swarm",
       "source": "./plugins/swarm",
-      "description": "Local mixture-of-agents code review for Claude Code. Fans a diff across Claude lenses plus the codex and grok CLIs (grok-build + composer models), merges by mechanism with cross-family consensus, verifies solo findings, and presents one ranked report. Optional --fix / --loop applies the findings you agreed with; --pr reviews a GitHub PR diff and posts the result. Skills: /swarm:review, /swarm:agents.",
-      "version": "0.4.1"
+      "description": "Local mixture-of-agents code review for Claude Code. Fans a diff across Claude lenses plus the codex and grok CLIs (grok-4.5 + composer models), merges by mechanism with cross-family consensus, verifies solo findings, and presents one ranked report. Optional --fix / --loop applies the findings you agreed with; --pr reviews a GitHub PR diff and posts the result. Skills: /swarm:review, /swarm:agents.",
+      "version": "0.4.2"
     }
   ]
 }

.claude/knowledge/features/swarm-backend-adapter.md

@@ -1,9 +1,9 @@
 ---
 title: "Swarm Backend Adapter Layer"
 createdAt: 2026-07-03
-updatedAt: 2026-07-12
+updatedAt: 2026-07-15
 createdFrom: "PR #21"
-updatedFrom: "session: 2026-07-12"
+updatedFrom: "session: 2026-07-15"
 pluginVersion: 1.8.2
 prime: false
 reindexedAt: 2026-07-12
@@ -19,7 +19,7 @@ The script header documents the per-backend mechanics; this entry captures the
 *verified* CLI behavior the adapter is built on and the gotchas that cost a
 debugging round.
 
-## Verified CLI facts (codex 0.128 / grok 0.2.77, 2026-07)
+## Verified CLI facts (codex 0.128 / grok 0.2.101, 2026-07)
 
 - **Uniform findings JSON** is achievable from both CLIs: `codex exec
   --output-schema <file>` and `grok --json-schema '<inline>'` both enforce a
@@ -32,10 +32,15 @@ debugging round.
   `--output-last-message <file>` (stdout carries the agent transcript,
   stderr the progress log); grok prints a response **envelope** on stdout —
   the validated object is its `.structuredOutput` field.
-- **grok's default model rejects `--effort`** (`grok-composer-2.5-fast` errors
-  with "does not support parameter reasoningEffort"). The adapter must pin
-  `-m grok-build`. grok's effort ladder (low…max) matches code-review's;
-  codex has no `max` tier → map `max`→`xhigh` (`-c model_reasoning_effort=…`).
+- **The adapter pins `-m grok-4.5`** — the schema-capable model. grok 0.2.101
+  renamed it from `grok-build` (same upstream pin-rename class as codex's
+  `gpt-5.6-terra`; verified drop-in: identical envelope/`structuredOutput`
+  shape, `--single` unchanged). `grok-composer-2.5-fast` still rejects
+  `--effort` ("does not support parameter reasoningEffort").
+- **Effort ladders**: grok is `low|medium|high` since 0.2.101 (the `max` tier
+  is gone) → the adapter maps `xhigh`/`max`→`high`; codex has no `max` tier →
+  map `max`→`xhigh` (`-c model_reasoning_effort=…`). Both mappings degrade a
+  stale caller instead of erroring.
 - **codex model is pinned** to `CODEX_DEFAULT_MODEL` (`gpt-5.6-terra`, the adapter
   passes `-m` on every call), overridable per call via `--model` — so a review is
   reproducible instead of tracking the user's ambient `~/.codex/config` default.
@@ -46,18 +51,18 @@ debugging round.
   still usable as a second grok voice. Given a strict-JSON *prompt* (the adapter
   appends the schema text and drops `--json-schema`/`--effort`), it emits **pure
   `{"findings":[...]}` directly on stdout — no response envelope, no
-  `structuredOutput`** (verified P2, grok 0.2.82; simpler than grok-build's
+  `structuredOutput`** (verified P2, grok 0.2.82; simpler than grok-4.5's
   envelope). The adapter routes `--model grok-composer-2.5-fast` to a separate
   `run_grok_composer` path that parses the answer **defensively**: collect ALL
   balanced `{...}` objects (whole string, fenced blocks, every `{` run), pick the
   first **non-empty** `findings` object (a leading `{"note":…}`/`{"findings":[]}`
   would otherwise mask the real one), and **validate every item against
-  `finding.schema.json`** (composer, unlike codex/grok-build, is not CLI-schema-
+  `finding.schema.json`** (composer, unlike codex/grok-4.5, is not CLI-schema-
   enforced — a malformed item must ERROR, not reach merge/verify). Both the
   first-object bug and the missing per-item validation were caught by swarm
   reviewing its own diff. composer is
-  ~2× faster than grok-build. It is same-family-correlated, so consumers must
-  count consensus by **model family**, not backend (composer + grok-build
+  ~2× faster than grok-4.5. It is same-family-correlated, so consumers must
+  count consensus by **model family**, not backend (composer + grok-4.5
   agreeing is one grok vote — see [swarm-review-pipeline](swarm-review-pipeline.md)).
 - **Headless tool execution**: both CLIs run read-only commands (e.g.
   `git diff`) without extra approval flags — codex inside `-s read-only`

.claude/knowledge/features/swarm-review-pipeline.md

@@ -1,9 +1,9 @@
 ---
 title: "Swarm Review Pipeline (/swarm:review)"
 createdAt: 2026-07-08
-updatedAt: 2026-07-14
+updatedAt: 2026-07-15
 createdFrom: "PR #24"
-updatedFrom: "session: 2026-07-14"
+updatedFrom: "session: 2026-07-15"
 pluginVersion: 1.8.2
 prime: false
 reindexedAt: 2026-07-12
@@ -15,7 +15,7 @@ P2 turns the blueprint into a working review: a **Workflow-tool script**
 (`plugins/swarm/workflows/swarm-review.js`) launched by the `/swarm:review`
 skill. Shape: `scope+gate → fan-out (4 voices) → merge (file,mechanism) →
 verify solos → output-gated synthesis`. Four voices: Claude lenses ∥ codex ∥
-grok-build ∥ composer (see [swarm-backend-adapter](swarm-backend-adapter.md)).
+grok-4.5 ∥ composer (see [swarm-backend-adapter](swarm-backend-adapter.md)).
 
 ## The skill ↔ workflow wiring (the non-obvious parts)
 
@@ -41,7 +41,7 @@ grok-build ∥ composer (see [swarm-backend-adapter](swarm-backend-adapter.md)).
 - **Consensus counts model *families*, not backends.** A cross-family cluster
   (≥2 of claude / openai / grok) is CONFIRMED without extra verify; everything
   else is solo and goes through the adversarial 3-state verifier. composer +
-  grok-build agreeing is one grok vote — they cannot alone mint consensus.
+  grok-4.5 agreeing is one grok vote — they cannot alone mint consensus.
 - **Security is intentionally minimal** (user directive: no cannons-at-sparrows).
   The P1 adapter floor stays (sandbox, tool-less grok, secret scrub, env filter,
   caps); P2 adds only three cheap things — **fencing** the diff as data
@@ -60,7 +60,7 @@ grok-build ∥ composer (see [swarm-backend-adapter](swarm-backend-adapter.md)).
   the delimiter); the workflow only collision-checks it against the returned
   findings and extends it deterministically (`nonce-1`, `-2`…) on collision.
 
-- **`args.claude: false`** runs an **external-only control** (codex + grok-build
+- **`args.claude: false`** runs an **external-only control** (codex + grok-4.5
   + composer, no Claude finder lenses, no gate; merge/verify still in-session).
   Proven useful: a control run found real bugs the with-Claude run missed (an
   `aws_secret_access_key` scrub-list drift, `git diff` omitting untracked files)
@@ -95,11 +95,12 @@ the diff out of the script, above). Claude applies edits between rounds.
   the report table contract this entry defines above (P2 reserved them).
 - **`--max` profile** (`INPUT.max` in the workflow): lifts every voice to its
   ceiling — codex `gpt-5.6-sol`@`xhigh` (codex has NO `max` tier, xhigh is its
-  top), grok-build `max`, Claude finder lenses + verifier `xhigh`; gate/merge
-  and composer (no effort control) unchanged. Orthogonal to `--fix`/`--loop`,
-  composes with both. Both max-tier settings were verified live before wiring
-  (`gpt-5.6-sol`@xhigh + grok `--effort max` end-to-end) — the "no silent fail
-  on a non-existent model/effort" rule.
+  top), Claude finder lenses + verifier `xhigh`; gate/merge, grok (`high` is
+  its ceiling since grok 0.2.101 dropped `max` — it runs there on both
+  profiles) and composer (no effort control) unchanged. Orthogonal to `--fix`/`--loop`,
+  composes with both. The profile's live settings are verified end-to-end
+  (`gpt-5.6-sol`@`xhigh` at wiring time; grok re-verified at `--effort high` on
+  0.2.101) — the "no silent fail on a non-existent model/effort" rule.
 
 ## `--pr`: review a PR diff and post the result (swarm 0.4.0)
 

CHANGELOG.md

@@ -173,6 +173,9 @@ entries are grouped per plugin, newest first.
 
 ## swarm
 
+### 0.4.2 — 2026-07-15
+- Fix grok CLI 0.2.101 compat: pin `grok-4.5` (upstream renamed `grok-build`), cap grok effort at `high` (the `max` tier is gone; the adapter maps `xhigh`/`max` → `high` so stale callers degrade instead of erroring).
+
 ### 0.4.1 — 2026-07-15
 - Extract the `/swarm:review --pr` publish path into a deterministic, unit-tested `scripts/pr-post.py` (per-cell sanitizer, stale-head gate, `gh` post); shrink `SKILL.md` step 5 to orchestration + the human confirm gate.
 

CLAUDE.md

@@ -21,7 +21,7 @@ This is a **Claude Code plugin marketplace** (monorepo) containing plugins that
 - **knowledge-system** (v1.5.x) — Knowledge management with three layers: Rules, Knowledge, Memory. Skills: `/init`, `/query`, `/curate`, `/reindex`, `/backfill-knowledge`, `/migrate`, `/statusline`
 - **work-system** (v1.2.x) — Task and worktree workflow. Skills: `/define`, `/kickoff`, `/adopt`, `/continue`, `/status`, `/close`, `/list`
 - **pr-flow** (v1.1.x) — PR review feedback loop. Skills: `/open`, `/cycle`, `/check`, `/fix`, `/rebase`, `/merge`
-- **swarm** (v0.3.x) — Local mixture-of-agents code review (external `codex`/`grok` CLIs — grok-build + composer — plus Claude lenses). P2: `/swarm:review` pipeline (scope→fan-out→merge→verify); P5: `--fix`/`--loop` apply the findings you agreed with. Skills: `/swarm:review`, `/swarm:agents`
+- **swarm** (v0.4.x) — Local mixture-of-agents code review (external `codex`/`grok` CLIs — grok-4.5 + composer — plus Claude lenses). P2: `/swarm:review` pipeline (scope→fan-out→merge→verify); P5: `--fix`/`--loop` apply the findings you agreed with. Skills: `/swarm:review`, `/swarm:agents`
 
 ## Plugin Anatomy
 

README.md

@@ -30,7 +30,7 @@ PR review feedback loop. Create PRs with readiness checks, commit + push + trigg
 
 ### Swarm
 
-Local mixture-of-agents code review. Fans out one review across Claude lens subagents plus the `codex` and `grok` CLIs (grok in `grok-build` + `composer` modes), merges and verifies their findings, and presents a single ranked report — before anything is pushed. With `--fix` / `--loop` it also applies the findings you agreed with (only Claude edits; the external agents stay review-only). `--pr [<number>]` runs the same ensemble against a GitHub PR's diff and posts the gated result as a PR comment (via your own `gh` auth, after one confirmation) — no CI or API-token setup. Complementary to PR Flow's GitHub-side loop. *(Phase 5: `/swarm:review` pipeline + fix loop + PR posting.)*
+Local mixture-of-agents code review. Fans out one review across Claude lens subagents plus the `codex` and `grok` CLIs (grok in `grok-4.5` + `composer` modes), merges and verifies their findings, and presents a single ranked report — before anything is pushed. With `--fix` / `--loop` it also applies the findings you agreed with (only Claude edits; the external agents stay review-only). `--pr [<number>]` runs the same ensemble against a GitHub PR's diff and posts the gated result as a PR comment (via your own `gh` auth, after one confirmation) — no CI or API-token setup. Complementary to PR Flow's GitHub-side loop. *(Phase 5: `/swarm:review` pipeline + fix loop + PR posting.)*
 
 **Commands:** `/swarm:review [--fix | --loop[=N]] [--max]`, `/swarm:review --pr [<number>]`, `/swarm:agents` *(more to come: `/swarm:adversarial`, `/swarm:style`, `/swarm:security`)*
 

plugins/swarm/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "swarm",
-  "description": "Local mixture-of-agents code review for Claude Code. Fans a diff across Claude lenses plus the codex and grok CLIs (grok-build + composer models), merges by mechanism with cross-family consensus, verifies solo findings, and presents one ranked report. Optional --fix / --loop applies the findings you agreed with; --pr reviews a GitHub PR diff and posts the result. Skills: /swarm:review, /swarm:agents.",
-  "version": "0.4.1",
+  "description": "Local mixture-of-agents code review for Claude Code. Fans a diff across Claude lenses plus the codex and grok CLIs (grok-4.5 + composer models), merges by mechanism with cross-family consensus, verifies solo findings, and presents one ranked report. Optional --fix / --loop applies the findings you agreed with; --pr reviews a GitHub PR diff and posts the result. Skills: /swarm:review, /swarm:agents.",
+  "version": "0.4.2",
   "author": {
     "name": "gering"
   },

plugins/swarm/README.md

@@ -14,7 +14,7 @@ Complementary to [pr-flow](../pr-flow/): pr-flow drives the GitHub-PR
 
 **Phase 5 of 6** — the pipeline can now **act** (P3/P4 lens presets still to
 come). `/swarm:review` fans a diff
-across four voices (Claude lenses + `codex` + `grok-build` + `composer`),
+across four voices (Claude lenses + `codex` + `grok-4.5` + `composer`),
 merges by mechanism, verifies solo findings, presents one ranked report, and —
 with `--fix` / `--loop` — applies the findings you agreed with.
 
@@ -25,7 +25,8 @@ with `--fix` / `--loop` — applies the findings you agreed with.
   default branch (including uncommitted work). `--fix` applies the agreed
   findings once; `--loop[=N]` re-reviews after each fix round until it converges
   (cap default `10`); `--max` runs the deepest-effort profile (codex
-  `gpt-5.6-sol`/`xhigh`, grok `max`, Claude lenses + verifier `xhigh`) — slower,
+  `gpt-5.6-sol`/`xhigh`, Claude lenses + verifier `xhigh`; grok already runs
+  at `high`, its ceiling) — slower,
   more thorough, composes with `--fix`/`--loop`.
 - `/swarm:review --pr [<number>]` — run the same ensemble against a **GitHub
   PR's diff** (`gh pr diff`; bare `--pr` resolves the current branch's PR) and,
@@ -43,21 +44,21 @@ presets).
 ## The pipeline (`/swarm:review`)
 
 ```
-Scope+gate → Fan-out (Claude lenses ∥ codex ∥ grok-build ∥ composer)
+Scope+gate → Fan-out (Claude lenses ∥ codex ∥ grok-4.5 ∥ composer)
           → Merge (file, mechanism) → Verify solos → Ranked synthesis
 ```
 
 1. **Scope + gate** — a cheap agent classifies the diff and picks which Claude
    lenses are worth running (security is never gated out when code/args/files
    flow to an external process).
 2. **Fan-out** — four voices in parallel: one Claude finder per gated lens plus
-   `codex`, `grok-build` and `composer` as full reviews through the adapter.
+   `codex`, `grok-4.5` and `composer` as full reviews through the adapter.
 3. **Merge** — an LLM step clusters findings by `(file, mechanism)`, not
    `(file, line)` (external CLIs number against the inlined diff).
 4. **Verify** — solo clusters go through an adversarial 3-state verifier
    (`CONFIRMED`/`PLAUSIBLE`/`REFUTED`; only `REFUTED` is dropped).
 
-**Consensus counts model *families*, not backends.** `grok-build` and
+**Consensus counts model *families*, not backends.** `grok-4.5` and
 `composer` are both grok, so their agreement is one vote — a `CONSENSUS` tag
 requires ≥2 of *claude / openai / grok*. Everything else is a solo and earns
 its place through the verifier.
@@ -93,7 +94,7 @@ Backends:
 |---------|------|-----------|
 | `claude` | probe-only | reviews run in-session via the Agent tool |
 | `codex` | external reviewer | `codex exec --output-schema` (model `gpt-5.6-terra`, effort `xhigh`) in a read-only sandbox; auth via `codex login status` |
-| `grok` | external reviewer | headless `-p` with inline `--json-schema` (model `grok-build`); findings extracted from the response envelope. `--model grok-composer-2.5-fast` takes a separate defensive-parse path (a ~2×-faster second grok voice, no schema flag). |
+| `grok` | external reviewer | headless `-p` with inline `--json-schema` (model `grok-4.5`); findings extracted from the response envelope. `--model grok-composer-2.5-fast` takes a separate defensive-parse path (a ~2×-faster second grok voice, no schema flag). |
 
 Unavailable backends drop from the ensemble — `claude` alone still works.
 `/swarm:review` reports a backend that *errored* mid-run distinctly from one

plugins/swarm/docs/pipeline-blueprint.md

@@ -287,11 +287,11 @@ credential mid-review) converged on these non-negotiable mitigations:
 
 - **Registered workflow** (not inline) so per-agent `durationMs` is available
   for the timing balance line.
-- **Model labels** in the balance line (`Opus-4.8`/`GPT-5.5`/`grok-build`),
+- **Model labels** in the balance line (`Opus-4.8`/`GPT-5.5`/`grok-4.5`),
   read from each backend's review output.
 - **Optional composer lens-gate**: `grok-composer-2.5-fast` can't enforce
   `--json-schema`/`--effort`, but a strict-JSON prompt makes it emit valid JSON
-  and reason on demand (tested 2/2). It's ~2× faster than grok-build but its
+  and reason on demand (tested 2/2). It's ~2× faster than grok-4.5 but its
   ~20s CLI cost undercuts a Haiku gate; keep it optional, with a defensive
   parser + fallback-to-all-lenses.
 - **Balance / footer / loop-round box:** render deterministically from the