ci: pi progress streaming, codex gpt-5.5 + danger-full-access sandbox (#9030)

* ci: install bubblewrap for codex sandbox; stream pi progress in logs

- Codex's vendored bwrap fails to set up loopback on some ubicloud
  runners, leaving codex unable to read any local files. Install the
  system bubblewrap package before running codex so its read-only
  sandbox works reliably.
- Switch pi to --mode json and pipe events through jq to surface
  agent/turn boundaries and tool calls live in the GitHub Actions log,
  matching codex's progress visibility. Final assistant text is
  extracted from the saved event log into pi-final-message.md for the
  PR comment.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* ci: drop bubblewrap install, use codex -s danger-full-access

Codex's read-only sandbox uses bwrap which fails to set up loopback on
some ubicloud runners. Rather than apt-installing bubblewrap, switch to
the no-sandbox mode for parity with how Pi and Claude already operate
in the same workflow — runner is ephemeral and we trust the codex
prompt the same way.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* ci: bump codex review model from gpt-5.4 to gpt-5.5

gpt-5.5 is positioned as the agentic successor to gpt-5.4 — same
per-token latency, fewer tokens to complete Codex tasks, and
explicitly stronger at holding context across large systems and
multi-tool reasoning, which matches the PR review workload.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

.github/workflows/codex-pr-review.yml

@@ -237,9 +237,9 @@ jobs:
         run: |
           codex exec \
             -C "$GITHUB_WORKSPACE" \
-            -m gpt-5.4 \
+            -m gpt-5.5 \
             -c 'model_reasoning_effort="xhigh"' \
-            -s read-only \
+            -s danger-full-access \
             -o codex-final-message.md \
             - < .github/codex/pr-review.prompt.md
 

.github/workflows/pi-pr-review.yml

@@ -222,12 +222,42 @@ jobs:
           DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY }}
           PI_SKIP_VERSION_CHECK: '1'
         run: |
+          set -o pipefail
           pi -p \
             --provider deepseek \
             --model deepseek-v4-pro \
             --tools read,grep,find,ls,bash \
+            --mode json \
             < .github/pi/pr-review.prompt.md \
-            > pi-final-message.md
+            | tee pi-events.jsonl \
+            | jq -rc --unbuffered '
+                if .type == "agent_start" then "🤖 pi agent started"
+                elif .type == "turn_start" then "── turn ──"
+                elif .type == "message_end" then
+                  "[\(.message.role)] " + (
+                    (.message.content // [])
+                    | map(
+                        if .type == "text" then "text(\(.text | length)c)"
+                        elif .type == "tool_use" then "🔧 \(.name) \(.input | @json | .[:160])"
+                        elif .type == "tool_result" then "✅ result"
+                        else .type
+                        end
+                      )
+                    | join(" | ")
+                  )
+                elif .type == "turn_end" then "── turn done (\((.toolResults // []) | length) tool result(s)) ──"
+                elif .type == "agent_end" then "🏁 pi agent done"
+                else empty
+                end
+              '
+
+          jq -r '
+            select(.type == "agent_end")
+            | .messages
+            | map(select(.role == "assistant"))
+            | last
+            | (.content[]? | select(.type == "text") | .text)
+          ' pi-events.jsonl > pi-final-message.md
 
       - name: Post Pi review comment
         if: steps.pi_config.outputs.enabled == 'true' && steps.pr.outputs.skip != 'true'