Files
archy/Release & Testing/Detailed Plans/15-Timing-and-Estimate-Contract.md

5.7 KiB

Sanitized detailed source transcription S15, captured 2026-10-24. Original planning steps, acceptance criteria and historical evidence are retained rather than condensed. Read current context and precedence first: dated holds, approvals, test counts and “latest” labels below belong to their original checkpoint and do not grant current execution/publication authority. Privacy replacements preserve roles and test semantics. See section coverage.

Mandatory AI execution timing rule

Operator instruction recorded 2026-10-22. Consult this file EVERY time estimating remaining work, duration, cost-related execution time, or a delivery date. Applies across this operator's development work, not only this release.

Rule

Estimate from measured AI-agent execution on comparable work with the same acceptance exit. NEVER use human developer hours, working days, story points, generic engineering schedules, or a human-to-AI speed multiplier. Never convert execution hours into calendar days using an eight-hour working day. A model allowance (including B1) is not measured throughput or a delivery promise.

Keep the original requirement IDs and exit criteria fixed. Defects and retries belong underneath their existing requirement. Do not claim a complete requirement from a source/test sub-exit. Scope changes require an explicit ledger change, not an expanding denominator hidden in a new forecast.

Formula

For each comparable work class k:

unit_time[k] = observed_execution_elapsed[k] / qualified_exits[k]
remaining_execution = SUM(remaining_units[k] * unit_time[k]) + unestimated_work
  • observed_execution_elapsed includes agent investigation, coding, debugging, failed attempts, repeated builds, tests, integration and qualification attributable to those units, not just successful commands. Use timestamped session/tool evidence, not file mtimes or invented start times.
  • Include actual attributable execution spent on unfinished/failed units in the observation cohort and disclose that unfinished work; do not select only cheap successes. If there are zero qualified comparable exits, unit_time is UNKNOWN, not zero.
  • Exclude separately recorded operator pauses, resource queues and external authority/device/review waits from execution elapsed. Unclassified gaps remain unknown; do not silently classify them as execution or waiting.
  • Use elapsed interval unions within a lane: overlapping agent/build/test time counts once. Do not add compiler time already included in an end-to-end measured cycle. Do not add a second arbitrary retry percentage when observed retries are already included.
  • remaining_units are actual outstanding exits at the SAME granularity and complexity as measured exits. Do not extrapolate from test counts, lines of code, commits, or a small fixture to an entire installed app. Do not apply measured compile speed to implementation/integration work. Do not assume partially complete work has zero remaining cost or an invented completion percentage.
  • unestimated_work is an explicitly listed unknown term, NOT zero. When any material term is unknown, give the measured subtotal and state that a full total/date is not established. A sample of zero whole-app completions cannot support a whole-app delivery estimate.

For multiple real execution lanes:

execution_makespan = resource_constrained_schedule(remaining tasks, dependencies, measured durations)
conditional_finish = current_time + schedule(remaining tasks AND explicit waits/availability)

For one continuously available serial lane, execution_makespan equals remaining_execution. Count concurrency only where workers/resources actually exist and concurrent work is authorized. Critical path alone is merely a lower bound when resources contend. External waits may overlap work: place them at their dependent gates rather than blindly summing every wait. No assumed unattended or 24/7 operation. Unknown availability/waits mean no unconditional calendar date.

Required timing response

  1. Fixed scope and qualified exits completed since the previous checkpoint.
  2. Remaining measured units by class and any unestimated classes.
  3. Observed timestamp window, sample size, comparable acceptance boundary, failed/retry work and evidence location.
  4. Calculated remaining execution subtotal/range in AI elapsed minutes/hours; distinguish a measured estimate from a model allowance.
  5. External waits, resource/availability assumptions and conditional calendar implications, separately.
  6. Reconcile against the previous forecast: exits completed, newly discovered work under existing IDs, changed measurements, explicit scope changes and forecast error. Never restart a rolling countdown.

With sparse observations, report observed ranges and uncertainty; do not label them confidence intervals or p50/p95 without sufficient data. Never manufacture a finite total merely because the operator requests one. A rough scenario may be supplied only with explicit assumptions and unknown terms. Cost needs actual usage and pricing evidence; elapsed time alone is not a billing estimate.

Correction of earlier reporting

The prior 'further weeks' statement was not derived from a measured end-to-end completion rate. It is withdrawn as a quantitative forecast. Existing compile/browser timings remain valid for those bounded activities only. They do not establish the remaining duration of all 35 platform requirements and eight apps. This rule supersedes human-hour estimates; it does not erase recorded failures, remaining work or authority gates.