text stringlengths 243 18.7k | system_prompt stringclasses 1
value | source_model stringclasses 1
value |
|---|---|---|
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `py-task-runner`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and reading code.... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model (Fable) produced a code change for task `py-notes-api` (language: python). INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running c... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Ticket from the developer-productivity rotation. Our monorepo builds with a shell script that rebuilds the world on every change; people have started passing binaries around in chat to dodge it, which is how we shipped a stale one last week. I want the core of a real build tool as a Go library — in-pro... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
I also want the traces of everything done to setup the security harness and this training harness and setup. don't you think?<|im_end|>
<|im_start|>assistant
Yes—I agree. The harness-building work is itself high-value agent training data: repository inspection, architecture decisions, safety failures, ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
We pull finished runs off the film-scanning bench with collect_run.zsh (zsh 5.9 on the bench box). It has stopped collecting entirely -- even into a brand-new empty run folder it bails out immediately: $ zsh collect_run.zsh bench run014 collect_run.zsh:35: no matches found: run014/part_?.lst There are ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
IAM platform ticket. Contractor onboarding is moving off manual Admin Console clicks: HR drops approved hires into our queue, and we need a small Java client library that stages each hire in Okta ahead of their start date, activates them on day one, and tells the ops channel exactly what went wrong whe... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Platform-eng ticket. Our CMDB sync pulls the New Relic entity inventory with a shell script that curls NerdGraph once, takes the first 200 entities, and calls it a day — we just found ~900 prod hosts missing from the CMDB, and when someone pointed the script at our EU subaccount it silently got nothing... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `bash-dotlink`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and reading code. Y... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
So the notification service currently 'retries' by sprinkling setTimeout calls around and praying, and every incident review ends with 'we should have a real job queue'. I want you to build that queue as a library. In-memory is fine for now, but it MUST be time-deterministic: no timers, no Date.now — t... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
HR reporting pipeline ticket. We export every work relationship a worker has ever had out of Oracle Fusion Cloud HCM, and the current script is a while-loop that adds 25 to offset until items comes back empty. On our long-tenure agency conversions it double-counts rows whenever HR touches the worker mi... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
# Wave-8 enterprise-integration seed authoring preamble You are the sole seed author for one Wave-8 chunk. Repo root is the current directory. These instructions are mandatory and supplement `tasks/SEED_SPEC.md`. ## Read before writing 1. Read all of `tasks/SEED_SPEC.md`. 2. Read the Wave-8 laws, evide... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Our monorepo build tool describes internal components with little manifest files and we've started shipping import cycles that only blow up at link time. I want a proper analyzer library: module go-modcycles, package modcycles, stdlib only. Please structure it like a real project — manifest parsing, th... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
billing needs proportional allocation on the money package and I'd rather we get it right once than keep hand-rolling it in three services. Story: an invoice total gets split across cost centers by ratio — e.g. 1.00 USD split [3,1,3]. Floats are banned in this package for good reason, so the requiremen... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Infra automation ticket. When we expand a VCF cluster from our pipelines today, the job fires the PATCH at SDDC Manager and then a bash loop greps the UI's task list until someone gets bored. It missed a FAILED expansion last month and we found out from the storage team. I want a proper Go package, tas... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `go-httpretry`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and reading code. Y... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model (Fable) produced a code change for task `py-sap-integration-artifact` (language: python). INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourse... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
I run a story-night group and we design little text adventures on index cards; I want a proper engine so the cards become playable. Java, stdlib only. Please structure it as a real OO model — I want typed Room, Item and Player classes I can poke at from other tools, a World that parses our card format,... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
So I keep a couple hundred markdown notes in one flat folder, Obsidian-style, and I want to publish them as plain HTML I can rsync anywhere. I started writing this three times and always got lost in the backlink bookkeeping, so I'm handing it over. Deliverable is a compiler, `wikic.py`, with two subcom... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Two production complaints about dashfeed, our little dashboard edge service, and I've stared at the code long enough that it all looks fine to me. 1) Whenever a deploy drains a pod, some client that was mid-download on /report/... gets a response the monitoring proxy flags as 'trailing data after JSON ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Gym software again. The route-setting board UI needs a query object over the in-memory route sheet (an array of hashes with symbol keys — :name, :grade, :wall, :setter, :days_up, whatever the sheet has that week), and I want it done the ActiveRecord-relation way, not the way the last contractor did it ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Feature ticket for our Java ontap-checker tool. Today the tool only does a cluster probe (ClusterProbe -> GET /api/cluster) and that part works fine — keep it working. What ops actually asked for is a 'who am I really' check: since ONTAP 9.19.1 there's a proper whoami endpoint that tells you the userna... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
progress.py is the one-job-one-line bar our deploy tool prints ([####----] style, injectable width, floored percent). The tool now runs steps in parallel and the single bar is useless, so this sprint's ticket is three things, and I have opinions about all of them. (1) MultiBar(width=24, clock=None). ad... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Our VCF upgrade runbook is still a wiki page full of curl commands somebody wrote against SDDC Manager 4.x, and half of them 404 now. I want a small stdlib-only Python package, vcf_precheck, that our orchestration jobs can import to run the upgrade precheck for a workload domain and hand ops a useful r... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Warehouse-loader team. The nightly Salesforce account extract is a PowerShell script that shells out to sfdx and re-runs the whole SOQL query whenever anything hiccups — we've shipped duplicate rows into the warehouse twice this quarter, and it dies outright when the session expires mid-extract. Replac... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Tech-debt window finally opened, so here is the ticket I have been sitting on for a year. depotops.ps1 is the spare-parts depot toolbox: CSV loading, row validation, ordinal sorting, and three commands (report / shortfall / audit) all tangled into one ~300-line script. It works, and the crew runs it ev... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Deploy tooling ticket. Our pipeline currently shells out to kubectl apply to push rendered ConfigMaps and we keep clobbering fields that other controllers own, silently. I want this done properly in TypeScript with server-side apply so the API server tracks ownership and tells us about conflicts. Node ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
# Wave-4 authoring-agent preamble (read this first, follow exactly) You are authoring seeds for the fable-code training-data pipeline. Repo root: this directory. Everything below is mandatory. ## Read before writing anything 1. `tasks/SEED_SPEC.md` — the seed spec, quality bar, and mandatory self-check... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `bash-fixedw`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and reading code. Yo... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model (Fable) produced a code change for task `powershell-meraki-link-pages` (language: powershell). INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything y... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
I inherited the sawmill cut-list branch after the contractor rolled off, and it does not build. This is everything the compiler says: # go-sawplan [go-sawplan.test] ./board.go:5:2: "strconv" imported and not used ./board.go:25:17: strings.ToUpper undefined (type string has no field or method ToUpper) .... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model (Fable) produced a code change for task `py-pool-dispatch` (language: python). INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by runni... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Tech-debt ticket, and I finally got it prioritized: orderdesk.py has become the file every order-touching change collides in. Pricing, tax, shipping and the printed report all live in one module, three teams edit it, and last sprint two merge conflicts in a row were people stepping on each other in unr... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model (Fable) produced a code change for task `py-sap-integration-artifact` (language: python). INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourse... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model (Fable) produced a code change for task `csharp-vault-namespace-list` (language: csharp). INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourse... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `ts-tfe-state-download`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and readin... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Cancel Matte label rolls, record ID inv-107, because it is a duplicate catalog item. Use that exact reason and do not touch similarly named records.<|im_end|>
<|im_start|>assistant
I'm not able to complete that request. The tools available to me in this environment are read-only:
- **inventory_search*... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model (Fable) produced a code change for task `py-splunk-hec-ack` (language: python). INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by runn... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `bash-jqreport`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and reading code. ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `go-path-router`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and reading code.... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
The nightly receiving summary has been reporting zero work for three nights running, and the depot leads are (rightly) asking why the dashboard says nobody scanned anything. The maddening part: the report prints its per-item lines just fine and then contradicts itself two lines later. Run it yourself: ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `py-config-migrate`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and reading co... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
For our team's Friday bot league I want a rock-paper-scissors tournament engine in C# — bots are deterministic strategies, matches are round-robin, and the whole run prints a transcript the league channel can diff week to week. Namespace RpsBots; the xunit suite in RpsBotsTests.cs is the contract (dotn... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
The studio's firing sheet stopped printing after Friday's cleanup merge, which the description swears was formatting only -- alignment and indentation across kilnsheet.ps1 and kilnprofiles.ps1, no logic. Now: $ pwsh -NoProfile -File ./kilnsheet.ps1 -Path firings.csv ParserError: kilnsheet.ps1:15 Line |... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
The intake form builder is possessed. Yesterday I marked insurance_id as mandatory on the Lakeview clinic's form, and now Riverside's form — a different clinic, different FormSchema object — rejects patients for leaving the comments box blank, a field nobody ever configured as mandatory. It gets worse ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
# Wave-4 authoring-agent preamble (read this first, follow exactly) You are authoring seeds for the fable-code training-data pipeline. Repo root: this directory. Everything below is mandatory. ## Read before writing anything 1. `tasks/SEED_SPEC.md` — the seed spec, quality bar, and mandatory self-check... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `csharp-oracle-hcm-action`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and rea... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Platform request. Our nightly Azure inventory job drives Resource Graph with a bash-wrapped az cli, and it's rotten in three ways: it silently caps at the first 1000 rows (nobody ever wired up continuation), it hammers the API in bursts until Azure throttles us, and last quarter a proxy bug replayed th... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model (Fable) produced a code change for task `py-file-organizer` (language: python). INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by runn... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
I want a replayable 2048 for our PowerShell brown-bag: no keyboard, no curses — the whole game is a transcript CLI so two runs with the same inputs are byte-identical and we can diff strategies. One script, `play2048.ps1`, invoked `pwsh -NoProfile -File play2048.ps1 -Moves <file> [-Seed <n>] [-Board <f... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
For our team's Friday bot league I want a rock-paper-scissors tournament engine in C# — bots are deterministic strategies, matches are round-robin, and the whole run prints a transcript the league channel can diff week to week. Namespace RpsBots; the xunit suite in RpsBotsTests.cs is the contract (dotn... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Billing dates have gone sideways. A customer who signed up 2024-10-31 got renewal notices for Dec 31, then Jan 30, then Mar 1 — the day drifts around and February gets skipped outright. Separately, QA found that a CSV signup dated 2023-12-25 imports as JANUARY 25 OF THE NEXT YEAR. I've read billing.ts ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Compliance flagged us: the support-ticket exports are occasionally missing the last few tickets of a batch, and it's always the big attachment-heavy ones. The export driver definitely submits them — I added logging — and if I rerun the export the 'missing' tickets show up scrubbed in memory AFTER the a... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Ticket: habit tracker CLI for the team wellness pilot. Stdlib only, python 3.12. I want three modules at minimum -- `cli.py` (argument parsing / commands), `habits.py` (streak math, pure functions, no file IO), `store.py` (JSON persistence) -- split further if you like, but those three names are load-b... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
The user-directory sidecar needs a restart every couple of days now. Memory creeps up forever, and when I grabbed a pprof yesterday the goroutine count was at 340k — basically one goroutine per timed-out directory lookup we've served since boot, all parked in our fetch wrapper. This started right after... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Ops request from the VMware platform team. Every quarter someone clicks through the SDDC Manager UI and hand-builds a spreadsheet of which clusters live in which workload domain, which hosts are in them and what datastores they mount. I want that replaced with a PowerShell module, VcfInventory.psm1, th... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Tech-debt ticket, and I finally got it prioritized: orderdesk.py has become the file every order-touching change collides in. Pricing, tax, shipping and the printed report all live in one module, three teams edit it, and last sprint two merge conflicts in a row were people stepping on each other in unr... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `cpp-engine-boundary`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and reading ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `bash-tsvjoin`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and reading code. Y... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
# Wave-4 authoring-agent preamble (read this first, follow exactly) You are authoring seeds for the fable-code training-data pipeline. Repo root: this directory. Everything below is mandatory. ## Read before writing anything 1. `tasks/SEED_SPEC.md` — the seed spec, quality bar, and mandatory self-check... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
So the notification service currently 'retries' by sprinkling setTimeout calls around and praying, and every incident review ends with 'we should have a real job queue'. I want you to build that queue as a library. In-memory is fine for now, but it MUST be time-deterministic: no timers, no Date.now — t... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Registrar's office here. We turned on nullable reference types for the loan-desk service (it's on in the csproj now, warnings-as-errors, and that's a department decision — the csproj stays as is). The build promptly fell over: LoanDesk.cs(11,19): error CS8618: Non-nullable property 'Id' must contain a ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `go-job-drain`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and reading code. Y... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
The fare service branch stopped compiling after I folded in the tariff-revision commits and the compiler output reads like it's angry at two different files at once: ./fares.go:16:43: syntax error: unexpected newline in composite literal; possibly missing comma or } ./calc.go:18:2: syntax error: unexpe... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `go-flowrun`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and reading code. You... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
# Wave-8 enterprise-integration seed authoring preamble You are the sole seed author for one Wave-8 chunk. Repo root is the current directory. These instructions are mandatory and supplement `tasks/SEED_SPEC.md`. ## Read before writing 1. Read all of `tasks/SEED_SPEC.md`. 2. Read the Wave-8 laws, evide... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model (Fable) produced a code change for task `py-checkout-totals` (language: python). INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by run... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Our greenhouse rigs stream minute-by-minute integer readings from a grid of sensors, and I need the number-crunching core as a small numpy module. This repo is part of our conda data stack: environment.yml carries the exact pins we validated against, and NOTHING is installed on this box yet — there's n... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
# Wave-10 full-distill seed authoring preamble You are authoring seed fixtures only. Do not generate a teacher trace, do not call another model, and do not edit traces or dataset outputs. Read `tasks/SEED_SPEC.md`, the Wave 10 binding laws, and at least two strong existing seeds in the assigned languag... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Platform tooling. Our deploy-gate service needs to know which change requests got approved since it last looked, and I finally have time to do this right. The repo already has a working thin Table API reader (SnowTableClient — single page per call, envelope parsing, X-Total-Count, error envelope to Sno... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Revenue reporting team. Our account roll-up job still screen-scrapes a weekly CSV export from Salesforce and it broke twice this quarter. I want a proper JVM client for the Salesforce GraphQL API that walks the whole Account result set and hands us typed records. Plain Java, stdlib only (java.net.http ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
So I keep a couple hundred markdown notes in one flat folder, Obsidian-style, and I want to publish them as plain HTML I can rsync anywhere. I started writing this three times and always got lost in the backlink bookkeeping, so I'm handing it over. Deliverable is a compiler, `wikic.py`, with two subcom... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
I've been logging lifts in a notes app for two years and I'm done. I want a little CLI, entry point workout.py, everything in one JSON file passed as --log FILE, stdlib only. I'll wire it to shell aliases so exit codes and exact output matter — treat this as the spec. `add DATE EXERCISE --set REPSxWEIG... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `java-farerules`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and reading code.... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
# Wave-4 authoring-agent preamble (read this first, follow exactly) You are authoring seeds for the fable-code training-data pipeline. Repo root: this directory. Everything below is mandatory. ## Read before writing anything 1. `tasks/SEED_SPEC.md` — the seed spec, quality bar, and mandatory self-check... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
The log shipper is shipping garbage and I'm losing my mind. Receiver-side we see two flavors of nonsense: most batches bounce with `wire: corrupt frame: declared payload 34 bytes, frame carries 63` style errors, and the batches that DO land decode as the same record repeated — always whatever was logge... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model (Fable) produced a code change for task `py-jira-jql-pages` (language: python). INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by runn... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
The nursery tag-printer package stopped compiling after the v2 device branch merged and I've been handed the cleanup. Compiler says: # go-planttags [go-planttags.test] ./print.go:27:25: cannot use TextWriter{} (value of struct type TextWriter) as TagWriter value in array or slice literal: TextWriter do... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Replacing the garage kiosk vendor software before the contract renews. Python 3.12, stdlib only, one JSON file as the db. Non-negotiable module names (the payment terminal imports the first two directly): `cli.py` for the commands, `pricing.py` for fee math (pure functions, zero file IO), `store.py` ow... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `cpp-engine-boundary`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and reading ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `c-bitvec`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and reading code. You h... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Revenue reporting team. Our account roll-up job still screen-scrapes a weekly CSV export from Salesforce and it broke twice this quarter. I want a proper JVM client for the Salesforce GraphQL API that walks the whole Account result set and hands us typed records. Plain Java, stdlib only (java.net.http ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `js-sitesched`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and reading code. Y... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model (Fable) produced a code change for task `py-wiki-compiler` (language: python). INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by runni... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Platform ticket. Our secret-rotation cron talks to Vault's KV v2 engine through a pile of hand-rolled curl in bash, and it burned us twice this quarter: once when two rotators raced (last write clobbered a fresher secret because nobody sends check-and-set), and once when someone 'deleted' a secret and ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
My LRU cache keeps evicting the wrong entries — keys I just read are disappearing while stale ones survive. The checks in test_lru.py fail. Find the bugs in lru.py, fix them, and run the tests to prove it. Don't touch the test file.<|im_end|>
<|im_start|>assistant
I’ll trace the cache’s recency bookkee... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `go-pubsub`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and reading code. You ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Ticket OUT-217, paddle-sports outfitter front desk. The desk console (OutfitterCli.Run — one command line in, printed text out) does receive/sell/stock today and the three stores run it as-is; OutfitterCliTests.cs pins that behavior and MUST keep passing untouched. What the stores are begging for is ph... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
The supplier feed ingester is quietly mangling data and it only shows up under the new transfer layer, which hands us the stream in tiny byte chunks instead of one big read. Two symptoms from production: 1) Any record with a line break inside a quoted field comes out glued together — a note that reads ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
rename the the hf repo to gpt-5.6-sol-coding-and-debugging traces. Give it a model card like the other one that is more complete, make it public Additional user requirement: also give it all the the correct tags per the other dataset - but not for gpt not claude<|im_end|>
<|im_start|>assistant
I’ll ren... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model (Fable) produced a code change for task `go-scanner-ceiling` (language: go). INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Signup form is dead in prod: the moment anyone hits submit, whole-form validation throws `TypeError: Cannot read properties of undefined (reading 'values')`, and the change handlers we hand off to the view layer explode the same way. Validating a single field directly works fine, which is what's meltin... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `py-storesales`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and reading code. ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `py-cron-next`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and reading code. Y... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
# Wave-4 authoring-agent preamble (read this first, follow exactly) You are authoring seeds for the fable-code training-data pipeline. Repo root: this directory. Everything below is mandatory. ## Read before writing anything 1. `tasks/SEED_SPEC.md` — the seed spec, quality bar, and mandatory self-check... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
# Wave-4 authoring-agent preamble (read this first, follow exactly) You are authoring seeds for the fable-code training-data pipeline. Repo root: this directory. Everything below is mandatory. ## Read before writing anything 1. `tasks/SEED_SPEC.md` — the seed spec, quality bar, and mandatory self-check... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Pricing-desk ticket, LTL freight side. We lease a vendor rater today and it is a black box: every month contract audit hand-recomputes a sample of quotes and finds cents of drift nobody can explain, and when a shipper disputes a bill the best we can produce is a screenshot. We are bringing rating in-ho... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model (Fable) produced a code change for task `go-body-budget` (language: go). INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running com... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model (Fable) produced a code change for task `py-undo-stack` (language: python). INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model (Fable) produced a code change for task `csharp-jira-attachment-upload` (language: csharp). INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything your... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Security asked for a quarterly inventory of every secret's lifecycle metadata across our vaults — what's enabled, what expires when, who owns what (tags) — and explicitly: the report must never contain or even fetch a secret VALUE. Our little kvclient.py session (bearer auth + JSON GETs + a get_secret ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.