Alexey Spiridonov
90d · built 2026-11-22
Performance
What Alexey Spiridonov shipped in the selected window, measured in ETV, and how it compares with the 90 days before it.
Effective capacity
+2.8engineers
delivers like 3.8 (3.8x pre-AI)
Output (ETV)
20.1ETV
+492.9% vs 3.4 prior
Features share
29.8%
−21.2 pp vs prior window
Fixes share
5.5%
−3.1 pp vs prior window
Work mix
29.8% Features3.9% Maintenance31.3% Tests29.5% Docs5.5% Fixes
184 commits over 90 days, ending 2026-11-22.
Daily performance
Daily ETV, stacked by Features, Maintenance, Tests, Docs and Fixes.
Repository spread
Where this developer's commits land. Concentrated work (top1 > 80%) vs polymath spread (top1 < 30%).
Most impactful commits
Top 10 by ETV in the last 90 days.
- 1.1ETVAdd repeatable backtests for rule changes Summary: Reading a rule diff cannot show whether it improves the artifact an agent produces. Add a backtest runner that stages a fixed scenario and explicitly selected rules, then preserves the artifact, trace, errors, and run metadata. The runner refuses local changes to the source files that shape the run and records their checkout revision, so a later comparison can identify and reproduce those inputs. Model, reasoning effort, and executable paths remain explicit metadata. ___ Differential Revision: D119108233 fbshipit-source-id: db92be24e462f47d7c8a92b9bb31b17b8ba80707github.com-facebook-folly · 8883a5d3 · 2026-09-08
- 1.1ETVPreserve critic-iterate drafts and costs in backtests Summary: Backtests currently preserve only the final answer. Rule maintainers cannot tell what the author fixed unaided, what each external review changed, or what another round cost. Preserve the output after each critic-iterate phase and record its added time and tokens. One run can then show the initial draft, the result of self-review, and the change and cost of each later review. # Behavior details - `output.md` remains the final artifact. Scenarios that begin from an existing draft remain uncheckpointed. - Checkpoint instructions name only the next command; they do not enumerate the remaining review rounds. - Failed reviewer attempts remain in the phase record; a completed retry can still finish that phase. - Missing or out-of-order checkpoints and review records invalidate the run. - No-rules scenarios must explicitly select their prompt. ___ Differential Revision: D119374051 fbshipit-source-id: 1b628900b423f9fb9a05b2cd6d592aca10c6555bgithub.com-facebook-folly · f0fb8709 · 2026-09-10
- 0.8ETVAdd a coroutine-metadata backtest Summary: Add a backtest for writing a general-audience API contract from the middle of a real design conversation: - A partial implementation already exists but needs changes, much like a task resumed with truncated history. - Superseded discussion, an intermediate review, later decisions, and a frozen source snapshot must be reconciled. The resulting document must explain which coroutine work inherits metadata and where propagation stops, without exposing that history. ___ Reviewed By: yinglan98 Differential Revision: D119108234 fbshipit-source-id: 8ee2d0edc297074346f0da354c1124fca3838058github.com-facebook-folly · ce8fb3b0 · 2026-09-08
- 0.6ETVbenchmark_ab.py: flag benchmarks with high run-to-run spread Summary: +488/-47 nonblank lines, excluding recorded `testdata/`. Large run-to-run variation can make an otherwise reportable effect unreliable, or deserve attention even when the estimated effect is small. Measure each complete before/after series by its range relative to its median. Calibrate extreme spread against the measured benchmark set: - Require at least 20 eligible series so one benchmark cannot move the cutoff too much. - Use Tukey's outer fence for the relative cutoff. - Keep the low-priority nanosecond and percentage thresholds as practical floors. Report the result without duplicating benchmarks: - Annotate priority rows in place. - Put unclassified outliers in a separate section with TSV class `high-spread`. - Add before/after ranges in ns and as a percentage of median to TSV. Series missing any round or with median at or below 2ns remain available for effect classification but do not influence spread calibration. ___ Differential Revision: D114015996 fbshipit-source-id: dc6f5f97d85da3b32fa6b9df89717501f307f7cbgithub.com-facebook-folly · 60c56027 · 2026-08-27
- 0.6ETVMove the default backtest result to output/main.md Summary: A dedicated output directory separates authored artifacts from run metadata. Existing scenarios write their usual result as `main.md`. ___ landed-with-radar-review Differential Revision: D128009085 fbshipit-source-id: 1992efdd27156fabcb1f06a51e653d6f39a6c82cgithub.com-facebook-folly · cb867002 · 2026-10-28
- 0.6ETVPreserve complete artifacts at backtest checkpoints Summary: A draft can span several files, so saving one file loses part of its state. Checkpoints and named review phases preserve each relative filename and byte sequence, and sample compression tracks each phase's complete file membership. ___ landed-with-radar-review Differential Revision: D127641356 fbshipit-source-id: 25954f227bb0e354348288bdf89699d39b1e1d13github.com-facebook-folly · 4e43b475 · 2026-10-31
- 0.5ETVCentralize Codex launch isolation Summary: Reviewer and backtest launchers need the same protection from ambient user and repository configuration. Introduce one OSS library that creates a private Git root, isolated engine state, and controlled task and working directories before launching Codex. Keep engine-specific startup behind an adapter so callers will not need to change when Claude support is added. ___ Differential Revision: D119918011 fbshipit-source-id: 363cab1f7a6c98a5aab22a01c8c94900a4eb8b3egithub.com-facebook-folly · 7bc0d0d7 · 2026-09-14
- 0.5ETVCompress stored backtest checkpoints Summary: Checkpointed samples can repeat nearly identical long outputs. That wastes repository space and makes each review's change harder to see. Add a deterministic post-processor for saved samples. It always keeps the final `output.md`, deduplicates identical phases, and keeps the earliest file for repeated non-final content. For each other earlier phase, it uses an adjacent reverse diff only when that diff is less than 60% of the full output. Before deleting any full output, the tool reconstructs every phase byte-for-byte through the reader-facing `apply_diffs` helper. It also removes unneeded runtime `artifact` fields from `checkpoints.json` and prints the phase map for the sample README. The next diff records the generated samples. ___ Differential Revision: D119576089 fbshipit-source-id: 2a1016b7518fa7a00f9437d316df766e3cbbd73bgithub.com-facebook-folly · 81353a08 · 2026-09-11
- 0.4ETVStage backtest rules from declared packages Summary: Adding a rule file to an isolated test currently requires updating the runner's support list and its test fixtures. Scenarios now declare the rule packages they need, and the runner stages their tracked operational Markdown. The separate startup list still chooses what the author reads first. The same package files are checked for uncommitted changes, including tracked additions and deletions, so the recorded revision describes the rules available to the author. Differential Revision: D126720876 fbshipit-source-id: 44986dced3395fe59dee8a33ee0931a363e07f2cgithub.com-facebook-folly · 4ac54415 · 2026-10-21
- 0.4ETVAdd a no-rules backtest baseline Summary: Existing backtests compare rule revisions but do not show what the same model produces without those rules. Add `--no-rules` so quality and cost can be compared with that baseline. The mode keeps the task and model settings while omitting injected rules and rule-only helpers. A scenario whose normal prompt mentions the rules can supply a bare prompt that removes only those instructions. Regular runs are unchanged. ___ Differential Revision: D119291040 fbshipit-source-id: f2cf3608e95c7e1ac57a87d9554ffeaa71cd504fgithub.com-facebook-folly · 43f86a10 · 2026-09-10