Repository navigation
feat(insights): delivery metrics — first-try rate, fix rounds, time to merge - #272
Merged
Merged
Conversation
…o merge Step one of "self-improving": measure whether the AI team gets better. Each task now records its fix rounds (every change sent back to the Coding agent — red checks, conflicts, review, acceptance, Orchestrator retries or a person's "Ask for changes") and when its last change merged (migration AddDeliveryMetrics in the Sessions module). Insights › Delivery shows tasks merged, passed first try (no change sent back), average fix rounds, median time from task start to merge, and what is waiting for a person — tenant-scoped, for the selected range. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018WAdQ7Rm24xss5QDSvXtJB
hoangsnowy
added a commit
that referenced
this pull request
Oct 23, 2026
…ces every agent follows Self-improvement, step two. After a ticket merges (MAF workflow or step by step), the Retrospective agent runs in the background on the member's computer: it reads the project's raw lessons (reviews, failing checks, failed acceptance) next to its current practices and returns the project's practices — at most 15 short, actionable, project-specific sentences — plus the lessons they now cover. - Knowledge graph: MemoryKinds.Practice (content-keyed), IMemoryStore.ListAsync(kind), ProjectMemory.PracticesBlock. - Readers: the Coding agent gets the practices before the closest lessons; the Reviewer checks the change against them (breaking one is a must-fix finding). - Guardrails (RetrospectiveService): once per project every 10 minutes, one at a time; pinned practices and lessons are never removed; only lessons the agent was shown can be cleared; an empty or failed answer changes nothing. The run is recorded in Insights; the Autopilot log says what changed. - Board › Knowledge: a Practices panel (pin to keep word for word, forget) above the lessons. - Insights › Delivery (#272) shows whether first-try passes go up. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018WAdQ7Rm24xss5QDSvXtJB
Merged
2 of 4 tasks
hoangsnowy
added a commit
that referenced
this pull request
Oct 23, 2026
…ces every agent follows (#273) Self-improvement, step two. After a ticket merges (MAF workflow or step by step), the Retrospective agent runs in the background on the member's computer: it reads the project's raw lessons (reviews, failing checks, failed acceptance) next to its current practices and returns the project's practices — at most 15 short, actionable, project-specific sentences — plus the lessons they now cover. - Knowledge graph: MemoryKinds.Practice (content-keyed), IMemoryStore.ListAsync(kind), ProjectMemory.PracticesBlock. - Readers: the Coding agent gets the practices before the closest lessons; the Reviewer checks the change against them (breaking one is a must-fix finding). - Guardrails (RetrospectiveService): once per project every 10 minutes, one at a time; pinned practices and lessons are never removed; only lessons the agent was shown can be cleared; an empty or failed answer changes nothing. The run is recorded in Insights; the Autopilot log says what changed. - Board › Knowledge: a Practices panel (pin to keep word for word, forget) above the lessons. - Insights › Delivery (#272) shows whether first-try passes go up. Claude-Session: https://claude.ai/code/session_018WAdQ7Rm24xss5QDSvXtJB Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
1 task done
hoangsnowy
added a commit
that referenced
this pull request
Oct 23, 2026
The agent-led retry count lived in memory, so every lab update gave a stuck task two more tries (seen on #42). It now comes from the task's persisted FixRounds (#272 — every change sent back to the Coding agent, by anyone): the rules' 3 rounds plus the agent's 2, capped, so a restart grants nothing new. Claude-Session: https://claude.ai/code/session_018WAdQ7Rm24xss5QDSvXtJB Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Self-improvement starts with measurement ("metrics first"): is the AI team getting better?
AddDeliveryMetrics(Sessions module) — two columns.ISessionRepository.GetDeliveryForTenantAsync→DeliverySummary(merged, first-try, avg fix rounds, median hours to merge, stuck now), tenant-explicit.Test plan
DeliveryMetricsTests: summary maths (median, first-try, average), repository counts rounds + stamps merge + excludes other tenants, duration wording./design-sync).🤖 Generated with Claude Code
https://claude.ai/code/session_018WAdQ7Rm24xss5QDSvXtJB