4dde5ac077
## Description
...
This PR addresses systemic visibility gaps and backlog growth by uncapping metric reporting and accelerating the issue lifecycle.
### Key Changes
1. **Metric Uncapping**: Refactored `bottlenecks.ts` and `priority_distribution.ts` to use GraphQL Search `totalCount`. This bypasses the previous 1000-issue cap, providing accurate visibility into the true scale of the 2062-issue backlog and 540+ zombie issues.
2. **Lifecycle Acceleration**: Lowered `STALE_DAYS` to 30 and `CLOSE_DAYS`/`NO_RESPONSE_DAYS` to 7 in `gemini-lifecycle-manager.cjs`. This move is necessary to clear the aging backlog and address the spike in zombie issues (issues inactive for >30d).
3. **CI Cost Optimization**: Restricted the Mac CI matrix to Node 20.x for all events. Since Linux runners already provide coverage for Node 22.x and 24.x, this change significantly reduces spend on expensive Mac runners without compromising quality.
### Impact
- **Accuracy**: Metrics now reflect the full repository state rather than a 1000-item sample.
- **Productivity**: Faster issue rotation will help maintainers focus on active community needs.
- **Efficiency**: Estimated ~30% reduction in Actions spend by optimizing the Mac test matrix.
2026-05-06 21:37:44 +00:00
0c4ac593eb
fix(bot): break pigeonholing by syncing lessons-learned and optimizing CI
...
This update resolves the bot's persistent focus on already-completed tasks:
- Moves and syncs lessons-learned.md to tools/gemini-cli-bot/ to ensure persistent memory.
- Marks metrics fixes, prompt hardenings, and user rejection signals as DONE in the ledger.
- Implements the CI matrix optimization (Node 20.x for PRs) the bot was re-attempting.
- This forces the bot to rotate to a new domain in the next run by satisfying its current goals.
2026-05-05 09:01:14 -07:00
76c97bfcc0
Merge branch 'main' into bot-prompt-improvements
2026-05-04 19:31:49 -07:00
128bba380a
fix(bot): dynamically checkout github.ref in publish job instead of hardcoded main
2026-05-04 19:27:08 -07:00
a79da4f3a9
Robust Scale-Safe Lifecycle Consolidation ( #26355 )
...
Co-authored-by: gemini-cli[bot] <gemini-cli[bot]@users.noreply.github.com>
Co-authored-by: Christian Gunderman <gundermanc@google.com >
2026-05-04 22:07:47 +00:00
39de9586a0
feat(bot): increase loop iterations and enforce memory of failures
2026-05-01 14:37:19 -07:00
b266912e61
fix(bot): prevent publish job from creating PRs for rejected changes
2026-05-01 10:22:32 -07:00
c6121d5113
feat(bot): enforce evaluation role and multi-iteration feedback loop
2026-04-30 20:51:27 -07:00
892c8a720d
fix(ci): checkout PR branch instead of main in bot workflow ( #26289 )
2026-04-30 21:59:06 +00:00
0af13141b2
Fix posting invalid response to a comment ( #26266 )
2026-04-30 18:22:59 +00:00
0f1077076e
Skip binary CLI relaunch ( #26261 )
2026-04-30 17:48:23 +00:00
1834ad0298
fix(bot): productivity and backlog optimizations ( #26236 )
2026-04-29 23:18:22 +00:00
dce13019b9
ci(github-actions): switch to github app token and fix bot self-trigger ( #26223 )
2026-04-29 20:45:16 +00:00
6dec6720de
Add the ability to @ mention the gemini robot. ( #26207 )
...
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-04-29 18:46:33 +00:00
c7d5fcff95
Update documentation workflows with workspace trust ( #26150 )
2026-04-29 01:00:57 +00:00
58a57b72ae
Implement bot that performs time-series metric analysis and suggests repo management improvements ( #25945 )
2026-04-28 16:49:53 +00:00
42587de733
feat(memory): persist auto-memory scratchpad for skill extraction ( #25873 )
2026-04-24 17:21:12 -07:00
c4b38a5aef
feat(repo): add gemini-cli-bot metrics and workflows ( #25888 )
2026-04-24 17:16:20 +00:00
dba9b9a0ff
feat(cli): secure .env loading and enforce workspace trust in headless mode ( #25814 )
...
Co-authored-by: galz10 <galzahavi@google.com >
Co-authored-by: davidapierce <davidapierce@google.com >
2026-04-23 16:09:14 +00:00
fafe3e35d2
fix(evals): add typecheck coverage for evals, integration-tests, and memory-tests ( #25480 )
2026-04-16 18:20:27 +00:00
d613dd05db
use macos-latest-large runner where applicable. ( #25413 )
2026-04-14 14:05:25 -07:00
a6d43cba2d
ci: add agent session drift check workflow ( #25389 )
2026-04-14 19:31:48 +00:00
58901207bd
docs: Update docs-audit to include changes in PR body ( #25153 )
2026-04-10 22:29:04 +00:00
f387e456be
Automated documentation audit ( #24567 )
2026-04-09 18:45:24 +00:00
f1bb2af6de
Generalize evals infra to support more types of evals, organization and queuing of named suites ( #24941 )
2026-04-08 23:57:26 +00:00
c7b920717f
feat(test-utils): add CPU performance integration test harness ( #24951 )
2026-04-08 21:50:29 +00:00
4ebc43bc66
feat(test-utils): add memory usage integration test harness ( #24876 )
2026-04-08 17:42:18 +00:00
846051f716
Alisa/approve button ( #24645 )
2026-04-07 16:44:07 +00:00
e74efc5c0b
Do not run pr-eval workflow when no steering changes detected ( #24621 )
2026-04-03 22:54:05 +00:00
ca0e6f9bd9
test: fix Windows CI execution and resolve exposed platform failures ( #24476 )
2026-04-03 15:50:29 +00:00
973092df50
feat: implement high-signal PR regression check for evaluations ( #23937 )
2026-04-02 05:14:43 +00:00
2e03e3aed5
feat(evals): add reliability harvester and 500/503 retry support ( #23626 )
2026-03-26 01:48:45 +00:00
7b710a2790
new linting check: github-actions-pinning ( #23808 )
2026-03-25 21:43:12 +00:00
109a7dc531
test(core): install bubblewrap on Linux CI for sandbox integration tests ( #23583 )
2026-03-25 14:29:46 +00:00
99e5164c82
Evals: PR Guidance adding workflow ( #23164 )
2026-03-23 15:07:40 +00:00
28935d1e6b
Retry evals on API error. ( #23322 )
2026-03-21 02:52:19 +00:00
17b37144a9
fix(automation): evaluate staleness before checking protected labels ( #22561 )
2026-03-15 15:50:19 -04:00
5ddb517593
fix(automation): harden stale PR closer permissions and maintainer detection ( #22558 )
2026-03-15 14:58:56 -04:00
35bf746e62
Add issue for automated changelogs ( #21912 )
2026-03-12 01:43:28 +00:00
80cf2fe444
fix(release): Improve Patch Release Workflow Comments: Clearer Approval Guidance ( #21894 )
2026-03-10 17:15:04 +00:00
237864eb63
feat(cli): Invert quota language to 'percent used' ( #20100 )
...
Co-authored-by: jacob314 <jacob314@gmail.com >
2026-03-07 23:17:10 +00:00
93d9adc03c
feat(triage): add area/documentation to issue triage ( #21222 )
2026-03-05 18:14:47 +00:00
09259a8ec4
test: add browser agent integration tests ( #21151 )
2026-03-05 13:29:35 +00:00
ac4e65d669
feat: add issue assignee workflow ( #21003 )
...
Signed-off-by: Kartik Angiras <angiraskartik@gmail.com >
2026-03-04 19:28:24 +00:00
208291f391
fix(ci): handle empty APP_ID in stale PR closer ( #20919 )
2026-03-03 00:14:36 -05:00
0d69f9f7fa
Build binary ( #18933 )
...
Co-authored-by: Gal Zahavi <38544478+galz10@users.noreply.github.com >
2026-03-03 01:02:19 +00:00
46231a1755
ci(evals): only run evals in CI if prompts or tools changed ( #20898 )
...
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-03-03 00:29:31 +00:00
b034dcd412
Do not block CI on evals ( #20870 )
2026-03-02 20:31:02 +00:00
48412a068e
Add /unassign support ( #20864 )
...
Co-authored-by: Jacob Richman <jacob314@gmail.com >
2026-03-02 19:54:26 +00:00
2e1efaebe4
fix(plan): deflake plan mode integration tests ( #20477 )
2026-03-02 19:51:44 +00:00
gemini-cli[bot]