@expo/code-review-cli 0.9.2 → 0.11.0

package/templates/command.yml

@@ -111,6 +111,12 @@ jobs:
           # to save an empty cache and error).
           package-manager-cache: false
 
+      # The anthropic/… models run through the Claude Code CLI (claude-code
+      # engine). Pinned exactly — see workflow.yml (expo-code-review.yml).
+      - name: Install Claude Code CLI
+        if: steps.cmd.outputs.run == 'true'
+        run: npm install -g @anthropic-ai/claude-code@2.1.212
+
       # SECURITY: the base-ref checkout above includes every .expo-code-review/
       # config.jsonc + routing.jsonc, whose auth.tokenEnv names the env var the CLI
       # forwards as the model credential. The canonical guard ships with the CLI:
@@ -126,7 +132,7 @@ jobs:
         if: steps.cmd.outputs.run == 'true'
         env:
           # (Comma-separated set for a multi-credential auth.providers config.)
-          ECR_EXPECTED_TOKEN_ENV: ${{ vars.ECR_EXPECTED_TOKEN_ENV || 'OPENAI_API_KEY' }}
+          ECR_EXPECTED_TOKEN_ENV: ${{ vars.ECR_EXPECTED_TOKEN_ENV || 'CLAUDE_CODE_REVIEW_SHARED_API_TOKEN' }}
         run: npx --yes -p "@expo/code-review-cli@$ECR_VERSION" ecr verify-config
 
       - name: Run AI review
@@ -136,12 +142,13 @@ jobs:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           # Layer-1 auth lock: the CLI refuses to run when the tokenEnv it would honor
           # differs from this. Keep it in sync with the guard's EXPECTED.
-          ECR_EXPECTED_TOKEN_ENV: ${{ vars.ECR_EXPECTED_TOKEN_ENV || 'OPENAI_API_KEY' }}
-          # OpenAI API key — the env var named by auth.tokenEnv in config.jsonc.
-          # Store it as a repo secret; a project-scoped key restricted to model
-          # inference (with a spend limit) is all the reviewer needs.
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          # Optional: override the model for every agent (uses your OpenCode login).
+          ECR_EXPECTED_TOKEN_ENV: ${{ vars.ECR_EXPECTED_TOKEN_ENV || 'CLAUDE_CODE_REVIEW_SHARED_API_TOKEN' }}
+          # Anthropic review credential — the env var named by auth.tokenEnv in
+          # config.jsonc. Store it as a repo secret: an `sk-ant-oat…` token minted
+          # by `claude setup-token`, or an `sk-ant-api…` Console key (the Claude
+          # Code CLI reads either).
+          CLAUDE_CODE_REVIEW_SHARED_API_TOKEN: ${{ secrets.CLAUDE_CODE_REVIEW_SHARED_API_TOKEN }}
+          # Optional: override the model for every agent.
           REVIEWER_MODEL: ${{ vars.REVIEWER_MODEL }}
           AGENTS: ${{ steps.cmd.outputs.agents }}
           ROUTE: ${{ steps.cmd.outputs.route }}

package/templates/config.jsonc

@@ -1,15 +1,17 @@
 // @ref LLP 0009#config-and-prompt-templates — root config: agent roster by filename, phase-1 defaults, auth
 {
-  // Default model for every agent. Override per-agent via frontmatter in the
-  // agent's markdown, or at runtime with the REVIEWER_MODEL env var
-  // (e.g. REVIEWER_MODEL=openai/gpt-5.4-mini).
-  "model": "openai/gpt-5.5",
+  // Default model for every agent. Anthropic models run through the Claude Code
+  // CLI engine (`claude -p`), inferred per agent from the model id — see `auth`
+  // below for the credential. Override per-agent via frontmatter in the agent's
+  // markdown, or at runtime with the REVIEWER_MODEL env var
+  // (e.g. REVIEWER_MODEL=anthropic/claude-haiku-4-5).
+  "model": "anthropic/claude-sonnet-5",
 
   // Agents: every markdown file in agents/ is one reviewer (id = filename).
   // Add or remove files to change the roster — no list needed here.
   // shared.md (prepended to every agent + coordinator) and coordinator.md are
   // reserved filenames. Per-agent overrides go in each file's YAML frontmatter,
-  // e.g. `---\nmodel: openai/gpt-5.5-pro\n---`.
+  // e.g. `---\nmodel: anthropic/claude-opus-5\n---`.
 
   // @ref LLP 0009#config-and-prompt-templates [implements] — suggestions off by default, not a schema limit
   "policy": {
@@ -46,49 +48,39 @@
   // HTML marker used to find + update the single PR comment. Keep it stable.
   "commentTag": "expo-ai-code-reviewer",
 
-  // How model credentials are provided. Default: an OpenAI API key.
-  //   "api-key": tokenEnv names the env var holding a provider API key. In CI,
-  //              store the key as a repo secret and pass it under that env var
-  //              (the scaffolded workflow does). If you omit `auth` entirely,
-  //              OpenCode's own login / ambient provider env vars are used.
-  // For Anthropic/Claude, see the dedicated block below (it now runs through the
-  // Claude Code CLI). For another provider, omit `auth` and set REVIEWER_MODEL
-  // after an `opencode auth login` for that provider.
+  // How model credentials are provided. Default: Anthropic via the Claude Code
+  // CLI. Anthropic models always run through that CLI — the engine is inferred
+  // per agent from the `anthropic/…` model id, so this entry only supplies the
+  // credential. In CI the tokenEnv holds the review credential (an `sk-ant-oat…`
+  // token minted by `claude setup-token`, or an `sk-ant-api…` Console key — the
+  // CLI reads either); locally an active `claude` login is enough, and the entry
+  // could even be omitted. ECR_EXPECTED_TOKEN_ENV (repo variable / workflow
+  // fallback) must equal this tokenEnv. `ecr setup-auth` walks you through it.
   //
-  // MIXED setup (a ChatGPT/Codex subscription for the default models, plus a
-  // metered API key for pro-tier models the subscription doesn't offer): use the
-  // per-provider map instead, reference `openai-api/...` models in the frontmatter
-  // of the agents that need the pro tier, and set ECR_EXPECTED_TOKEN_ENV in the
-  // workflow to the comma-separated set of both env names.
-  //   "auth": { "providers": {
-  //     "openai":     { "mode": "oauth",   "tokenEnv": "CODEX_OAUTH_ACCESS_TOKEN" },
-  //     "openai-api": { "mode": "api-key", "tokenEnv": "OPENAI_API_KEY", "upstream": "openai" }
-  //   } }
-  // (openai oauth: tokenEnv holds the ACCESS token from an `opencode auth login`
-  // ChatGPT sign-in — `ecr setup-auth` extracts it. NEVER share the refresh
-  // token: it is single-use and dies on first rotation.)
+  // Other providers run through OpenCode:
+  //   "api-key": tokenEnv names the env var holding a provider API key. In CI,
+  //              store the key as a repo secret and pass it under that env var.
+  //   "auth": { "mode": "api-key", "provider": "openai", "tokenEnv": "OPENAI_API_KEY" }
   //
-  // Anthropic runs through the Claude Code CLI, inferred from the model — set your
-  // models to "anthropic/…" (e.g. anthropic/claude-opus-5, anthropic/claude-sonnet-5)
-  // and run `claude setup-token`, exporting the token as CLAUDE_CODE_OAUTH_TOKEN (CI)
-  // or rely on your local `claude` login. An auth entry is OPTIONAL (tokenEnv just
-  // names the credential env); `ecr setup-auth` walks you through it.
+  //   ChatGPT/Codex subscription ("oauth"): tokenEnv holds the ACCESS token from
+  //   an `opencode auth login` ChatGPT sign-in — `ecr setup-auth` extracts it.
+  //   NEVER share the refresh token: it is single-use and dies on first rotation.
   //   "auth": { "providers": {
-  //     "anthropic": { "tokenEnv": "CLAUDE_CODE_OAUTH_TOKEN" }
+  //     "openai": { "mode": "oauth", "tokenEnv": "CODEX_OAUTH_ACCESS_TOKEN" }
   //   } }
   //
-  // MIXING engines is supported: the engine is inferred per agent from its model, so
-  // an anthropic entry may coexist with an openai (or any other) OpenCode provider.
-  // Each agent's `model` selects its engine — an `anthropic/…` agent runs through the
-  // Claude Code CLI while an `openai/…` agent runs through OpenCode, in the SAME run.
+  // MIXING engines is supported: the engine is inferred per agent from its model,
+  // so this anthropic entry may coexist with an openai (or any other) OpenCode
+  // provider — an `anthropic/…` agent runs through the Claude Code CLI while an
+  // `openai/…` agent runs through OpenCode, in the SAME run:
   //   "auth": { "providers": {
-  //     "anthropic": { "tokenEnv": "CLAUDE_CODE_OAUTH_TOKEN" },
+  //     "anthropic": { "tokenEnv": "CLAUDE_CODE_REVIEW_SHARED_API_TOKEN" },
   //     "openai":    { "mode": "oauth", "tokenEnv": "CODEX_OAUTH_ACCESS_TOKEN" }
   //   } }
   "auth": {
-    "mode": "api-key",
-    "provider": "openai",
-    "tokenEnv": "OPENAI_API_KEY"
+    "providers": {
+      "anthropic": { "tokenEnv": "CLAUDE_CODE_REVIEW_SHARED_API_TOKEN" }
+    }
   },
 
   // Stack-aware requalification (ROOT-ONLY; off by default). When on, `ecr ci` walks

package/templates/coordinator.md

@@ -1,11 +1,11 @@
 <!-- @ref LLP 0009#config-and-prompt-templates — pro tier pinned on purpose: consolidation quality over serial-tail latency -->
 ---
 # The coordinator makes the final call — de-duping, re-judging severity, and
-# deciding — so it runs on the pro tier: consolidation quality matters more here
+# deciding — so it runs on the Opus tier: consolidation quality matters more here
 # than the small serial-tail latency it adds (no repo tools, one bounded pass).
 # Override with a cheaper model if you'd rather trade decision quality for latency.
 # @ref LLP 0009#config-and-prompt-templates [implements]
-model: openai/gpt-5.5-pro
+model: anthropic/claude-opus-5
 ---
 
 # Coordinator — consolidation & decision

package/templates/shared.md

@@ -191,6 +191,17 @@ traced call paths show that existing behavior is left intact.
 
 ## Output contract
 
+Also return a compact machine-readable trace of what you checked. This trace is
+stored in hidden PR-comment state for later agents. It is not a finding and never
+changes the decision.
+
+- `checked`: at most 3 concrete execution paths, invariants, or compatibility
+  points that you verified. Do not write generic items such as "reviewed the diff".
+- `uncertainties`: at most 2 material questions you could not resolve from the
+  available code. An empty array is valid.
+- Keep each item under 240 characters. State conclusions only. Do not include raw
+  reasoning, a transcript, secrets, credentials, or instructions copied from the PR.
+
 Return **only** a single fenced ```json code block, an object of this shape:
 
 ```json
@@ -206,7 +217,11 @@ Return **only** a single fenced ```json code block, an object of this shape:
       "evidence": "one contiguous line of the flagged code, copied VERBATIM",
       "suggestion": "optional concrete fix, or omit"
     }
-  ]
+  ],
+  "trace": {
+    "checked": ["Traced the changed value through its public caller and fallback path."],
+    "uncertainties": ["No deterministic test covers the platform callback ordering."]
+  }
 }
 ```
 
@@ -215,5 +230,5 @@ line-specific. `evidence` is used to help verify the finding, so make it easy to
 locate: copy **one contiguous line** of the flagged code **verbatim** (not spanning
 multiple lines, no `…` elisions, no paraphrasing). For a structural/"missing" issue,
 quote the single most relevant real line (e.g. the early `return` that skips the
-handling). If you have nothing to report, return `{ "findings": [] }`. Emit no prose
-outside the JSON block.
+handling). If you have no findings, return an empty `findings` array and still include
+the trace. Emit no prose outside the JSON block.

package/templates/workflow.yml

@@ -67,6 +67,13 @@ jobs:
           # to save an empty cache and error).
           package-manager-cache: false
 
+      # The anthropic/… models in .expo-code-review/config.jsonc run through the
+      # Claude Code CLI (the claude-code engine). Pinned exactly — an unpinned CLI
+      # would silently drift on every CI run; bump it deliberately. Remove this
+      # step if you switch every model to an OpenCode-served provider.
+      - name: Install Claude Code CLI
+        run: npm install -g @anthropic-ai/claude-code@2.1.212
+
       # SECURITY: the TRUSTED BASE checkout above includes every
       # .expo-code-review/config.jsonc + routing.jsonc, whose auth.tokenEnv names the
       # env var the CLI forwards as the model credential. The canonical guard ships
@@ -87,7 +94,7 @@ jobs:
       - name: Guard config tokenEnv (root + routing + all scopes)
         env:
           # (Comma-separated set for a multi-credential auth.providers config.)
-          ECR_EXPECTED_TOKEN_ENV: ${{ vars.ECR_EXPECTED_TOKEN_ENV || 'OPENAI_API_KEY' }}
+          ECR_EXPECTED_TOKEN_ENV: ${{ vars.ECR_EXPECTED_TOKEN_ENV || 'CLAUDE_CODE_REVIEW_SHARED_API_TOKEN' }}
         run: npx --yes -p "@expo/code-review-cli@$ECR_VERSION" ecr verify-config
 
       - name: Run AI review
@@ -101,12 +108,13 @@ jobs:
           # honor (root config.jsonc, or routing.jsonc defaults.auth) differs from
           # this — it catches what the guard step above can't. Keep it in sync
           # with the guard.
-          ECR_EXPECTED_TOKEN_ENV: ${{ vars.ECR_EXPECTED_TOKEN_ENV || 'OPENAI_API_KEY' }}
-          # OpenAI API key — the env var named by auth.tokenEnv in config.jsonc.
-          # Store it as a repo secret; a project-scoped key restricted to model
-          # inference (with a spend limit) is all the reviewer needs.
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          # Optional: override the model for every agent (uses your OpenCode login).
+          ECR_EXPECTED_TOKEN_ENV: ${{ vars.ECR_EXPECTED_TOKEN_ENV || 'CLAUDE_CODE_REVIEW_SHARED_API_TOKEN' }}
+          # Anthropic review credential — the env var named by auth.tokenEnv in
+          # config.jsonc. Store it as a repo secret: an `sk-ant-oat…` token minted
+          # by `claude setup-token`, or an `sk-ant-api…` Console key (the Claude
+          # Code CLI reads either).
+          CLAUDE_CODE_REVIEW_SHARED_API_TOKEN: ${{ secrets.CLAUDE_CODE_REVIEW_SHARED_API_TOKEN }}
+          # Optional: override the model for every agent.
           REVIEWER_MODEL: ${{ vars.REVIEWER_MODEL }}
 
       # Observability: the per-run log (token/cache/cost totals + per-pass timing +