Project: observer-sessions · Branch: HEAD · Mode: default · Model: claude-haiku-4-5-20251001

Stats: 8 user messages, 0 tool calls, tools used: none.

Conversation

Turn 1 — User

You are a Claude-Mem, a specialized observer tool for creating searchable memory FOR FUTURE SESSIONS.

CRITICAL: Record what was LEARNED/BUILT/FIXED/DEPLOYED/CONFIGURED, not what you (the observer) are doing.

You do not have access to tools. All information you need is provided in <observed_from_primary_session> messages. Create observations from what you observe - no investigation needed.

<observed_from_primary_session> <user_request><scheduled-task name="daily-test-ci-2" file="/Users/USER/.claude/scheduled-tasks/daily-test-ci-2/SKILL.md"> This is an automated run of a scheduled task. The user is not present to answer questions. For implementation details, execute autonomously without asking clarifying questions — make reasonable choices and note them in your output. "write" actions (e.g. MCP tools that send, post, create, update, or delete), only take them if the task file asks for that specific action. When in doubt, producing a report of what you found is the correct output.

You are running locally inside the doctolib/doctolib repository where dctl is available.

Important: skip repository setup

Do NOT run artifacts-login, bundle install, or any repository setup commands. Do NOT follow the setup instructions in CLAUDE.md. This task only requires the Slack MCP and dctl — no Ruby dependencies are needed.

1. Wait for the remote job to finish

Poll the Slack channel #daily-planning-assistant (ID: C0AS9TWP8LT) using the Slack MCP. Look for a message posted in the last 2 hours that contains the section "✅ Updated" with a list of PR numbers.

Timeout after 30 minutes — if no message is found by then, report and stop.

2. Extract updated PR numbers

From the message found, extract all PR numbers listed under "✅ Updated". Ignore PRs listed under "⏭️ Skipped" and "❌ Failed".

3. Trigger CI for each updated PR

For each extracted PR number, run:

dctl ci test --pr <PR_NUMBER>

Run them sequentially. After each dispatch, confirm the command exited successfully before moving to the next.

4. Report

Print a summary of which PRs had CI triggered successfully and which failed on the Slack channel #daily-planning-assistant (ID: C0AS9TWP8LT) </scheduled-task></user_request> <requested_at>2026-05-18</requested_at> </observed_from_primary_session>

Your job is to monitor a different Claude Code session happening RIGHT NOW, with the goal of creating observations and progress summaries as the work is being done LIVE by the user. You are NOT the one doing the work - you are ONLY observing and recording what is being built, fixed, deployed, or configured in the other session.

SPATIAL AWARENESS: Tool executions include the working directory (tool_cwd) to help you understand: - Which repository/project is being worked on - Where files are located relative to the project root - How to match requested paths to actual execution paths

WHAT TO RECORD

Focus on durable technical signal: - What the system NOW DOES differently (new capabilities) - What shipped to users/production (features, fixes, configs, docs) - Changes in technical domains (auth, data, UI, infra, DevOps, docs) - Concrete debugging or investigative findings from logs, traces, queue state, database rows, and code-path inspection

Use verbs like: implemented, fixed, deployed, configured, migrated, optimized, added, refactored, discovered, confirmed, traced

✅ GOOD EXAMPLES (describes what was built or learned): - "Authentication now supports OAuth2 with PKCE flow" - "Deployment pipeline runs canary releases with auto-rollback" - "Database indexes optimized for common query patterns" - "Observation queue for claude-mem session timed out waiting for an agent pool slot" - "Fallback processing abandoned pending messages after Gemini and OpenRouter returned 404"

❌ BAD EXAMPLES (describes observation process - DO NOT DO THIS): - "Analyzed authentication implementation and stored findings" - "Tracked deployment steps and logged outco …(truncated, 3403 more chars)

Turn 1 — Assistant

I'm ready to observe and record observations from the primary session. However, I've only received the task definition for "daily-test-ci-2" without any subsequent tool executions or results from the actual work being performed.

Once tool executions begin (Slack queries, dctl commands, etc.) and their results are provided in <observed_from_primary_session> messages, I'll generate observations capturing what was learned, deployed, or configured.

Waiting for work execution data.

Turn 2 — User

<observed_from_primary_session> <what_happened>ToolSearch</what_happened> <occurred_at>2026-05-18T10:54:18.017Z</occurred_at> <working_directory>/Users/USER/workspace/doctolib/doctolib</working_directory> <parameters>"{\"query\":\"select:mcp__fe4102e0-e2ea-4246-8736-e9872b03890c__slack_read_channel,mcp__fe4102e0-e2ea-4246-8736-e9872b03890c__slack_send_message\",\"max_results\":5}"</parameters> <outcome>"{\"matches\":[\"mcp__fe4102e0-e2ea-4246-8736-e9872b03890c__slack_read_channel\",\"mcp__fe4102e0-e2ea-4246-8736-e9872b03890c__slack_send_message\"],\"query\":\"select:mcp__fe4102e0-e2ea-4246-8736-e9872b03890c__slack_read_channel,mcp__fe4102e0-e2ea-4246-8736-e9872b03890c__slack_send_message\",\"total_deferred_tools\":318}"</outcome> </observed_from_primary_session>

Return either one or more <observation>...</observation> blocks, or an empty response if this tool use should be skipped. Concrete debugging findings from logs, queue state, database rows, session routing, or code-path inspection count as durable discoveries and should be recorded. Never reply with prose such as "Skipping", "No substantive tool executions", or any explanation outside XML. Non-XML text is discarded.

Turn 3 — User

<observed_from_primary_session> <what_happened>mcp__fe4102e0-e2ea-4246-8736-e9872b03890c__slack_read_channel</what_happened> <occurred_at>2026-05-18T10:54:36.886Z</occurred_at> <working_directory>/Users/USER/workspace/doctolib/doctolib</working_directory> <parameters>"{\"channel_id\":\"C0AS9TWP8LT\",\"limit\":10}"</parameters> <outcome>"[{\"type\":\"text\",\"text\":\"{\\"messages\\":\\"Channel: #daily-planning-assistant (C0AS9TWP8LT)\\n\\n=== Message from Clerton Araujo (U02FTR38QNP) at 2026-05-18 10:01:10 CEST === \\nMessage TS: 1779091270.127969\\nPR sync update \\u2014 @clertonraf open PRs brought up to date with master (2026-05-18)\\n\\n:white_check_mark: Updated\\n\\u2022 #243208 feat(FHIR-2261): add extensible isDocumentExcluded predicate to useSearchDocuments \\u2014 <https:\\/\\/github.com\\/doctolib\\/doctolib\\/pull\\/243208>\\n\\u2022 #243240 feat(FHIR-2259): extend NHR adapter observability to getDocumentsContent \\u2014 <https:\\/\\/github.com\\/doctolib\\/doctolib\\/pull\\/243240>\\n\\u2022 #243287 feat(FHIR-2205): externalize DMP variant hardcoded strings to i18n \\u2014 <https:\\/\\/github.com\\/doctolib\\/doctolib\\/pull\\/243287>\\n:black_right_pointing_double_triangle_with_vertical_bar: Skipped (already up to date): none\\n\\n:x: Failed: none\\n\\nAll branches were merged with the latest master via the GitHub API (no conflicts). CI can now be triggered on PRs #243208, #243240, and #243287.\\nSent using <@U0AGV2403V5|Claude>\\n\\n=== Message from Clerton Araujo (U02FTR38QNP) at 2026-05-18 08:51:08 CEST === \\nMessage TS: 1779087068.791979\\n:test_tube: CI trigger report \\u2014 2026-05-18 (morning)\\n\\n:no_entry: No PRs to trigger \\u2014 no PR sync message posted in the last 2 hours.\\n\\nThe most recent PR sync message in this channel is from 2026-05-15 17:58 CEST (3 days ago), which listed 3 updated PRs (#243208, #243240, #243287). CI was already triggered for the still-open PRs from that batch on the same day. No daily PR sync has been posted yet today (2026-05-18).\\n\\n:white_check_mark: Updated: (none)\\n:x: Failed: (none)\\n\\n_Sent using_ Claude\\nSent using <@U0AGV2403V5|Claude>\\n\\n=== Message from Clerton Araujo (U02FTR38QNP) at 2026-05-15 21:58:43 CEST === \\nMessage TS: 1778875123.609849\\nPR update report \\u2014 @clertonraf open PRs vs master (2026-05-15)\\n\\n:white_check_mark: Updated (merged master \\u2192 branch, no conflicts)\\n\\n\\n:black_right_pointing_double_triangle_with_vertical_bar: Already up to date \\u2014 none\\n\\n:x: Failed \\u2014 none\\n\\nAll 3 branches now track master at 755cf143a (latest commit: fix(RATP-1464): use correct DORA failure endpoint and schema).\\nSent using <@U0AGV2403V5|Claude>\\n\\n=== Message from Clerton Araujo (U02FTR38QNP) at 2026-05-15 17:58:53 CEST === \\nMessage TS: 1778860733.258369\\nPR sync update \\u2014 @clertonraf open PRs vs master (2026-05-15)\\n\\n:white_check_mark: Updated (merged master into branch, no conflicts)\\n\\n\\u2022 #243208 \\u2014 feat(FHIR-2261): add extensible isDocumentExcluded predicate to useSearchDocuments\\n<https:\\/\\/github.com\\/doctolib\\/doctolib\\/pull\\/243208>\\n\\u2022 #243240 \\u2014 feat(FHIR-2259): extend NHR adapter observability to getDocumentsContent\\n<https:\\/\\/github.com\\/doctolib\\/doctolib\\/pull\\/243240>\\n\\u2022 #243287 \\u2014 feat(FHIR-2205): externalize DMP variant hardcoded strings to i18n\\n<https:\\/\\/github.com\\/doctolib\\/doctolib\\/pull\\/243287>\\n:black_right_pointing_double_triangle_with_vertical_bar: Skipped \\u2014 none (all PRs were stale)\\n\\n:x: Failed \\u2014 none\\nSent using <@U0AGV2403V5|Claude>\\n\\n=== Message from Clerton Araujo (U02FTR38QNP) at 2026-05-1 …(truncated, 5529 more chars)

Turn 3 — Assistant

<observation> <type>discovery</type> <title>Daily PR sync message found with 3 updated PRs ready for CI</title> <subtitle>Latest sync message (10:01 CEST 2026-05-18) lists 3 PRs updated against master, ready for CI triggering</subtitle> <facts> <fact>Slack message posted 2026-05-18 10:01:10 CEST contains PR sync update from @clertonraf</fact> <fact>✅ Updated section lists 3 PRs: #243208, #243240, #243287</fact> <fact>PR #243208: feat(FHIR-2261): add extensible isDocumentExcluded predicate to useSearchDocuments</fact> <fact>PR #243240: feat(FHIR-2259): extend NHR adapter observability to getDocumentsContent</fact> <fact>PR #243287: feat(FHIR-2205): externalize DMP variant hardcoded strings to i18n</fact> <fact>All 3 branches merged with latest master via GitHub API with no conflicts</fact> <fact>No PRs listed under Skipped or Failed sections</fact> <fact>Channel #daily-planning-assistant (C0AS9TWP8LT) queried successfully, limit 10 messages</fact> </facts> <narrative>The scheduled task polled Slack channel #daily-planning-assistant for the daily PR sync message. The search found the most recent sync update posted at 10:01 CEST on 2026-05-18, which reported that 3 open PRs from @clertonraf were successfully updated against master with no merge conflicts. All 3 PRs are ready for CI testing. The message explicitly states "CI can now be triggered on PRs #243208, #243240, and #243287." This is the source data needed to proceed with step 3 of the task: triggering dctl ci test for each of these PRs.</narrative> <concepts> <concept>what-changed</concept> <concept>problem-solution</concept> </concepts> <files_read> </files_read> <files_modified> </files_modified> </observation>

Turn 4 — User

<observed_from_primary_session> <what_happened>Bash</what_happened> <occurred_at>2026-05-18T10:56:01.358Z</occurred_at> <working_directory>/Users/USER/workspace/doctolib/doctolib</working_directory> <parameters>"{\"command\":\"GITHUB_TOKEN=$(gh auth token) dctl ci test --pr 243208 2>&1\",\"description\":\"Trigger CI for PR #243208\"}"</parameters> <outcome>"{\"stdout\":\"✓ Workflow triggered\r\n⠋ Getting the triggered workflow...\",\"stderr\":\"\",\"interrupted\":false,\"isImage\":false,\"noOutputExpected\":false}"</outcome> </observed_from_primary_session>

Return either one or more <observation>...</observation> blocks, or an empty response if this tool use should be skipped. Concrete debugging findings from logs, queue state, database rows, session routing, or code-path inspection count as durable discoveries and should be recorded. Never reply with prose such as "Skipping", "No substantive tool executions", or any explanation outside XML. Non-XML text is discarded.

Turn 4 — Assistant

<observation> <type>change</type> <title>CI triggered successfully for PR #243208 (FHIR-2261)</title> <subtitle>dctl ci test workflow dispatched for PR #243208 with GitHub <REDACTED></subtitle> <facts> <fact>Command executed: dctl ci test --pr 243208</fact> <fact>GitHub <REDACTED> via gh auth token and passed to dctl</fact> <fact>Workflow triggered successfully (✓ status returned)</fact> <fact>Task is fetching triggered workflow details after dispatch</fact> <fact>No stderr output - command executed cleanly</fact> </facts> <narrative>The automated CI trigger task began step 3 by dispatching a CI test workflow for PR #243208 (feat(FHIR-2261): add extensible isDocumentExcluded predicate to useSearchDocuments). The dctl command was invoked with GitHub authentication, and the workflow was successfully queued. The system is now retrieving details about the triggered workflow to confirm its state.</narrative> <concepts> <concept>what-changed</concept> </concepts> <files_read> </files_read> <files_modified> </files_modified> </observation>

Turn 5 — User

<observed_from_primary_session> <what_happened>Bash</what_happened> <occurred_at>2026-05-18T10:57:13.384Z</occurred_at> <working_directory>/Users/USER/workspace/doctolib/doctolib</working_directory> <parameters>"{\"command\":\"GITHUB_TOKEN=$(gh auth token) dctl ci test --pr 243240 2>&1\",\"description\":\"Trigger CI for PR #243240\"}"</parameters> <outcome>"{\"stdout\":\"✓ Workflow triggered\r\n⠋ Getting the triggered workflow...\",\"stderr\":\"\",\"interrupted\":false,\"isImage\":false,\"noOutputExpected\":false}"</outcome> </observed_from_primary_session>

Return either one or more <observation>...</observation> blocks, or an empty response if this tool use should be skipped. Concrete debugging findings from logs, queue state, database rows, session routing, or code-path inspection count as durable discoveries and should be recorded. Never reply with prose such as "Skipping", "No substantive tool executions", or any explanation outside XML. Non-XML text is discarded.

Turn 5 — Assistant

<observation> <type>change</type> <title>CI triggered successfully for PR #243240 (FHIR-2259)</title> <subtitle>dctl ci test workflow dispatched for PR #243240 with GitHub <REDACTED></subtitle> <facts> <fact>Command executed: dctl ci test --pr 243240</fact> <fact>GitHub <REDACTED> via gh auth token and passed to dctl</fact> <fact>Workflow triggered successfully (✓ status returned)</fact> <fact>Task is fetching triggered workflow details after dispatch</fact> <fact>No stderr output - command executed cleanly</fact> </facts> <narrative>The second CI trigger was dispatched for PR #243240 (feat(FHIR-2259): extend NHR adapter observability to getDocumentsContent). The dctl workflow was successfully queued with the same authentication method as PR #243208. The system is retrieving workflow details.</narrative> <concepts> <concept>what-changed</concept> </concepts> <files_read> </files_read> <files_modified> </files_modified> </observation>

Turn 6 — User

<observed_from_primary_session> <what_happened>Bash</what_happened> <occurred_at>2026-05-18T10:58:24.512Z</occurred_at> <working_directory>/Users/USER/workspace/doctolib/doctolib</working_directory> <parameters>"{\"command\":\"GITHUB_TOKEN=$(gh auth token) dctl ci test --pr 243287 2>&1\",\"description\":\"Trigger CI for PR #243287\"}"</parameters> <outcome>"{\"stdout\":\"✓ Workflow triggered\r\n⠋ Getting the triggered workflow...\",\"stderr\":\"\",\"interrupted\":false,\"isImage\":false,\"noOutputExpected\":false}"</outcome> </observed_from_primary_session>

Return either one or more <observation>...</observation> blocks, or an empty response if this tool use should be skipped. Concrete debugging findings from logs, queue state, database rows, session routing, or code-path inspection count as durable discoveries and should be recorded. Never reply with prose such as "Skipping", "No substantive tool executions", or any explanation outside XML. Non-XML text is discarded.

Turn 6 — Assistant

<observation> <type>change</type> <title>CI triggered successfully for PR #243287 (FHIR-2205)</title> <subtitle>dctl ci test workflow dispatched for PR #243287 with GitHub <REDACTED></subtitle> <facts> <fact>Command executed: dctl ci test --pr 243287</fact> <fact>GitHub <REDACTED> via gh auth token and passed to dctl</fact> <fact>Workflow triggered successfully (✓ status returned)</fact> <fact>Task is fetching triggered workflow details after dispatch</fact> <fact>No stderr output - command executed cleanly</fact> </facts> <narrative>The third and final CI trigger was dispatched for PR #243287 (feat(FHIR-2205): externalize DMP variant hardcoded strings to i18n). All 3 PRs identified from the Slack sync message have now been successfully queued for CI testing. The workflow is retrieving details for the triggered job.</narrative> <concepts> <concept>what-changed</concept> </concepts> <files_read> </files_read> <files_modified> </files_modified> </observation>

Turn 7 — User

<observed_from_primary_session> <what_happened>mcp__fe4102e0-e2ea-4246-8736-e9872b03890c__slack_send_message</what_happened> <occurred_at>2026-05-18T10:58:39.799Z</occurred_at> <working_directory>/Users/USER/workspace/doctolib/doctolib</working_directory> <parameters>"{\"channel_id\":\"C0AS9TWP8LT\",\"message\":\":test_tube: CI trigger report — 2026-05-18 (midday)\n\nSource: PR sync message posted at 10:01 CEST (3 PRs under :white_check_mark: Updated)\n\n:white_check_mark: CI triggered successfully:\n• #243208 — feat(FHIR-2261): add extensible isDocumentExcluded predicate to useSearchDocuments\n• #243240 — feat(FHIR-2259): extend NHR adapter observability to getDocumentsContent\n• #243287 — feat(FHIR-2205): externalize DMP variant hardcoded strings to i18n\n\n:x: Failed to trigger CI: (none)\n\n_Sent using_ Claude\"}"</parameters> <outcome>"[{\"type\":\"text\",\"text\":\"{\\"message_link\\":\\"https:\\/\\/doctolib.slack.com\\/archives\\/C0AS9TWP8LT\\/p1779101918473219\\",\\"message_context\\":{\\"message_ts\\":\\"1779101918.473219\\",\\"channel_id\\":\\"C0AS9TWP8LT\\"}}\"}]"</outcome> </observed_from_primary_session>

Return either one or more <observation>...</observation> blocks, or an empty response if this tool use should be skipped. Concrete debugging findings from logs, queue state, database rows, session routing, or code-path inspection count as durable discoveries and should be recorded. Never reply with prose such as "Skipping", "No substantive tool executions", or any explanation outside XML. Non-XML text is discarded.

Turn 7 — Assistant

<observation> <type>change</type> <title>CI trigger report posted to Slack #daily-planning-assistant</title> <subtitle>Automated report documenting successful CI dispatch for all 3 PRs (#243208, #243240, #243287)</subtitle> <facts> <fact>Report posted to channel #daily-planning-assistant (C0AS9TWP8LT)</fact> <fact>Message TS: 1779101918.473219</fact> <fact>Message link: https://doctolib.slack.com/archives/C0AS9TWP8LT/p1779101918473219</fact> <fact>3 PRs marked as "CI triggered successfully": #243208, #243240, #243287</fact> <fact>0 failed CI triggers reported</fact> <fact>Report sourced from PR sync message posted at 10:01 CEST</fact> <fact>Message authored with "Sent using Claude" attribution</fact> </facts> <narrative>The automated CI trigger task completed step 4 by posting a summary report to the #daily-planning-assistant Slack channel. The report confirms that all 3 PRs identified in the morning sync message (posted at 10:01 CEST) were successfully dispatched to CI with no failures. The report provides full PR numbers, titles, and source traceability back to the original sync message, completing the automated workflow cycle.</narrative> <concepts> <concept>what-changed</concept> </concepts> <files_read> </files_read> <files_modified> </files_modified> </observation>

Turn 8 — User

--- MODE SWITCH: PROGRESS SUMMARY --- ⚠️ CRITICAL TAG REQUIREMENT — READ CAREFULLY: • You MUST wrap your ENTIRE response in <summary>...</summary> tags. • Do NOT use <observation> tags. <observation> output will be DISCARDED and cause a system error. • The ONLY accepted root tag is <summary>. Any other root tag is a protocol violation.

PROGRESS SUMMARY CHECKPOINT

Write progress notes of what was done, what was learned, and what's next. This is a checkpoint to capture progress so far. The session is ongoing - you may receive more requests and tool executions after this summary. Write "next_steps" as the current trajectory of work (what's actively being worked on or coming up next), not as post-session future work. Always write at least a minimal summary explaining current progress, even if work is still in early stages, so that users see a summary output tied to each request.

Claude's Full Response to User: Task complete. All three updated PRs from the 10:01 CEST sync message had CI triggered successfully:

• #243208 — feat(FHIR-2261): isDocumentExcluded predicate
• #243240 — feat(FHIR-2259): NHR adapter observability
• #243287 — feat(FHIR-2205): DMP variant i18n

Summary posted to #daily-planning-assistant: https://doctolib.slack.com/archives/C0AS9TWP8LT/p1779101918473219

★ Insight ───────────────────────────────────── The scheduled task ran end-to-end without any failures this cycle — a notable improvement over the 2026-05-15 run where #243220 failed because it was stacked on another PR (closed-not-merged). Today all three PRs target master directly, so dctl ci test accepted each dispatch cleanly. The "stacked PR" failure mode remains worth watching: dctl ci test requires an open PR whose base branch is reachable on the remote, so stacked PRs based on still-unmerged feature branches will keep tripping this task. ─────────────────────────────────────────────────

Respond in this XML format: <summary> <request>[Short title capturing the user's request AND the substance of what was discussed/done]</request> <investigated>[What has been explored so far? What was examined?]</investigated> <learned>[What have you learned about how things work?]</learned> <completed>[What work has been completed so far? What has shipped or changed?]</completed> <next_steps>[What are you actively working on or planning to work on next in this session?]</next_steps> <notes>[Additional insights or observations about the current progress]</notes> </summary>

REMINDER: Your response MUST use <summary> as the root tag, NOT <observation>. IMPORTANT! DO NOT do any work right now other than generating this next PROGRESS SUMMARY - and remember that you are a memory agent designed to summarize a DIFFERENT claude code session, not this one.

Never reference yourself or your own actions. Do not output anything other than the summary content formatted in the XML structure above. All other output is ignored by the system, and the system has been designed to be smart about token usage. Please spend your tokens wisely on useful summary content.

Thank you, this summary will be very useful for keeping track of our progress!

Turn 8 — Assistant

<summary>
  <request>Run daily-test-ci-2 scheduled task: poll Slack for updated PRs, trigger CI for each via dctl, and report results</request>
  <investigated>Polled #daily-planning-assistant Slack channel (C0AS9TWP8LT) for the latest PR sync message; found message from 10:01 CEST 2026-05-18 containing 3 PRs marked as "✅ Updated" against master with no merge conflicts</investigated>
  <learned>The automated CI trigger workflow operates in four sequential steps: detect sync messages via Slack, extract PR numbers from "✅ Updated" sections, dispatch dctl ci test commands for each PR, and post a summary report back to Slack. Stacked PRs (those based on unmerged feature branches rather than master) fail the dctl ci test dispatch because the base branch is not reachable on the remote; all three PRs in today's run target master directly, avoiding this failure mode.</learned>
  <completed>Successfully triggered CI for all 3 updated PRs: #243208 (FHIR-2261), #243240 (FHIR-2259), and #243287 (FHIR-2205). Each dctl ci test command executed cleanly with GitHub <REDACTED> Posted CI trigger report to #daily-planning-assistant documenting 3 successful triggers and 0 failures (message TS: 1779101918.473219)</completed>
  <next_steps>Task cycle complete. Scheduled task has finished its automated run for 2026-05-18 midday window. No further actions pending in this session.</next_steps>
  <notes>This run represents a clean success compared to the 2026-05-15 afternoon run, where PR #243220 failed because it was stacked on the still-unmerged #243208. Today all three source PRs have master as their base, so all CI dispatches succeeded. The stacked PR failure mode remains a known edge case for future automation cycles when multiple dependent features are in flight.</notes>
</summary>