docs: gentle deadline example (matz round 16)#6
Open
codenamev wants to merge 24 commits into
Open
Conversation
A time-budgeted plan whose optional tasks decline by name when the clock runs low - essentials always served, garnish as time allows, lateness as a menu decision instead of an outage. Round 16 bench drawn by lottery from all fifty personas. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
A fourteen-line Result monad over TaskResult/TaskFailure: plan steps compose with bind, the first failure switches downstream steps onto the bypass carrying full testimony - failure as composition, not interruption. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
The same plan run at concurrency 1/2/8 with outputs required identical; a smuggler plan fails the proof by encoding a race through a shared array, and the fix is an edge. The prover's own first bug - state leaking across runs - was the lesson in miniature. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
The contract cops grown a config layer: per-cop enable/disable and params, comments as recorded decisions, and RuboCop's pending policy - new cops never fire until the team signs, so upgrades can't redden a build by surprise. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
LLM spend as integer cents in a journal-backed ledger: affordability checked before each spend, budget exhaustion classified retryable (tomorrow has a new budget), and the money trail sharing the work trail's fsynced file. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
Scientist-style rehearsal: v1 serves, v2 shadows the same inputs, mismatches journaled with the request attached, shadow output asserted to feed nothing. The one disagreement is exactly the case a blind cutover would have paged on. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
Outside-in in three acts: fakes for collaborators that don't exist force narrow interfaces into existence, realization leaves the caller untouched, and one discovered seam turns out to fit an entire orchestrated plan behind it - with round 12's papers check keeping the surviving fakes honest. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
Plan progress broadcast to N subscribers, each declaring its backpressure policy: latest_wins drops stale frames for dashboards, every_event buffers to a bound and disconnects loudly for auditors, and publish never blocks the plan. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
Per-capability kill switches checked at use time: instant and deploy-free, per-organ rather than global, non-retryable by decree so retries can't out-vote the human, and every flip audited (who, why) in the same journal as the work. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
Build, manifest+version audit, clean-GEM_HOME install, and boot of the installed package with the repo off the load path. The rehearsal's first run caught its own contaminated stage: RUBYOPT under bundle exec smuggled the repo back onto the child's path. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
The stacked-PR merge commits carry em dashes in their subjects; in a container with no locale set, backtick output arrives tagged US-ASCII and strip/regex raise Encoding::CompatibilityError. Caught by the round-16 smoke run. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
Ten personas drawn at random from all fifty prior casts; catalog at 141 examples. Findings: returning personas attacked new seams, the tools-correct-authors streak reached nine rounds (smuggler ledger, RUBYOPT contamination, plus the smoke run's em-dash encoding catch), and three soft asks are recorded for whoever reopens the shop. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
Mutation testing for workflows: five sabotages, three spec generations, and a fixture audit - a surviving mutant can mean a branch your inputs never visit, not just a missing assertion. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
rails-new for plans: a six-line recipe generates a complete runnable program with journal, retries, and concurrency conventions poured in. The generated output is executed as the acceptance test - which caught the template's own missing require on first run. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
Hostile-HTML ETL as a plan: decode, sanitize, extract, resolve per feed in parallel with a referee grepping the refined product. The first draft ran encoding repair last and the plan itself refused. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
syntax_suggest for plans: unmatched dependencies get a caret and a did-you-mean from Agentic::Suggestions, cycles are shown as the loop itself, and the repaired plan runs as the doctor's own audit. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
Closed-loop scaling on p95 queue time measured around the acquire: Little's law computes the pool size, RateLimit#resize applies it live, and the identical spike re-runs to prove the collapse. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
Zeitwerk's contract for capability packs: path/constant/name as one bijection with lazy, eager-verified, and reloadable gears. Reload generations use the registry's latest-version resolution; the agent's add-time provider snapshot is the cached-reference war, documented. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
OTP restart strategies over plans - one_for_one, rest_for_one, one_for_all as blast-radius policy, bounded restart intensity with escalation, zero rescue clauses in worker agents. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
Confidence-tiered support ladder: playbook auto-resolution, specialist drafts, and a human queue with full dossiers. Thresholds are policy data; the sensitivity check structurally outranks confidence. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
Gemfile.lock for workflows: constraints resolve once into versions plus content digests; frozen runs verify and refuse instead of resolving. Version numbers are claims; digests catch the in-place edit that lockfiles exist for. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
The 99 Bottles arc on a plan: god task pinned as golden master, one responsibility extracted per step, byte-identical output certifying each move, and a botched extraction rejected by the referee. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
Second lottery with a sharpened brief - build products ON the framework, not probes OF it. Ten tools/workflows shipped; catalog at 151 examples; the tools-correct-authors streak reaches ten rounds. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
…examples The 144-example catalog and the persona field notes now live in https://github.com/codenamev/agentic-examples, tagged by compatible Agentic version (agentic-v0.2.0 matches this tree). Kept here: a five-example starter set (ticket screener, latency lab, weekly check-in, did-you-mean, traffic dial) plus the index generator, and the two repo referees relocated to bin/ (doctest.rb, release_rehearsal.rb) since they audit this repo's own docs and package. README points at both. Suite green (610), doctest referee green, release rehearsal green, all five starter examples exit 0. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF
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
2 participants
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.
A time-budgeted plan whose optional tasks decline by name when
the clock runs low - essentials always served, garnish as time
allows, lateness as a menu decision instead of an outage. Round
16 bench drawn by lottery from all fifty personas.
Co-Authored-By: Claude Fable 5 noreply@anthropic.com
Claude-Session: https://claude.ai/code/session_01FeZLdZ3M4q4cho4DZPfSkF