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 (Fable) produced a code change for task `py-pick-reconcile` (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 `csharp-sap-csrf-batch`. 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
The shard tallier is haunted. Same input, different totals every run — yesterday `error` counted 1597, then 1601, then the right number. Worse, roughly one ingest run in ten the whole process just dies mid-aggregation. Single-shard inputs never misbehave, only multi-shard ones. `go test -race -timeout ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Release engineering ticket. Our deploy pipeline kicks Terraform Enterprise runs by shelling out to curl in a 400-line Jenkins groovy blob, and last month it applied a plan that had failed policy checks because nobody checks the run state properly. I want a real Go package, `tferun`, that drives the doc... | 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
# 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
Corner Pharmacy's refill planner is scheduling pickups for days we are closed. We are closed every Sunday. Holiday closures work — the Christmas-window fills rolled to the next day exactly like they should — but any refill whose ready date lands on a Sunday prints a "ready Sunday" pickup slip, and the ... | 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-setlist`. 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
Need the scheduling core for our team calendar service. Plain TypeScript on bare node (node 24 type stripping, zero deps, tests run with node --test), no UI, no storage. Three public modules — internal helpers are your call. Timestamps everywhere are naive strings 'YYYY-MM-DDTHH:MM' (we normalize to UT... | 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-obsrun`. 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 `c-iniscan`. 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
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
# 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
Ticketing meltdown at the Orpheum. Our reservation book behaves perfectly for studio-theater shows (seats 1-80) and loses its mind for main-hall shows (seats 101-412): the same main-hall seat gets sold to two different patrons, the seating chart shows seats as free that we JUST sold, the refund desk ge... | 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-newrelic-synthetic-monitor`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running command... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Analytics-platform ticket. Our usage-reporting service talks to BigQuery through a pile of copy-pasted fetch calls that string-interpolate values straight into SQL, silently truncate any result past the first response page, and turn 64-bit user IDs into corrupted doubles because someone fed them throug... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Release engineering ticket. Our deploy pipeline kicks Terraform Enterprise runs by shelling out to curl in a 400-line Jenkins groovy blob, and last month it applied a plan that had failed policy checks because nobody checks the run state properly. I want a real Go package, `tferun`, that drives the doc... | 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
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `ts-approval-flow`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and reading cod... | 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 `go-burst-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
Data-platform ticket. Our telemetry archiver pushes nightly rollup blobs to S3 with a single put_object call, and last night a 3.4 GB rollup timed out four times and the job gave up — we resend the whole object every time anything hiccups. I want a proper multipart uploader package, `s3mpu`, built on t... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
The county clerk's office is standing up a scan-room browser over its microfiche archive — decades of property deeds and permits on reels, digitized frame by frame. The scan appliance that serves frames is slow and billed per request, and the collection runs to six figures of frames. The tool the last ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
I'm on call and I keep re-deriving the same numbers from nginx access logs with increasingly unholy awk. Please build me a proper little analyzer, entry point `logreport.py`. Our logs are common log format, one request per line, like: 10.0.0.2 - - [10/Oct/2025:09:01:16 +0000] "GET /api/users HTTP/1.1" ... | 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
Streaming platform team. Every release train we promote event schemas to the shared Schema Registry by hand with curl, and last month someone force-registered an incompatible orders schema and broke three consumers. I want a proper release-gate client in this repo. It talks to the registry's REST API d... | 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 `c-ringbuf`. 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
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `zsh-plugin-option-scope`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and read... | 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-pandas-pivot` (language: py). INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running co... | 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
# 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
Storage platform ticket, Python. Our NAS provisioning runbook is still a human clicking System Manager and we keep getting duplicate volumes when someone re-runs a half-finished request. I want a small stdlib-only Python package `ontapvol` that provisions ONTAP FlexVol volumes over the cluster REST API... | 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
Two field reports against the backup agent's manifest layer (backman.py) and support is done arguing with customers about them. First: nightly incrementals keep skipping files people definitely changed. Classic case from yesterday: someone edits a config right after the nightly run finishes, next night... | 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-shardplan`. 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
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
# 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-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
I rebased our elevator intake-board branch and now the grading module won't compile, and the errors read like nonsense. A taste, from the middle of two screens of this: In file included from band.h:7, from grade.c:2: silo.h:7:6: error: redeclaration of 'enum grade_label' 7 | enum grade_label { | ^~~~~~... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Our session-token cache goes insane every time the fleet's NTP daemon steps the clock. Saturday it stepped backward ~1h and tokens that should have aged out kept getting served for the rest of the hour — auth saw revoked sessions come back from the dead. When the clock stepped forward, the opposite: fr... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Platform-inventory ticket, Ruby. Compliance wants a monthly inventory of every project on our self-managed GitLab, and the old rake task that hammered page=1..N fell over once we passed a few tens of thousands of projects — GitLab's own docs say big listings should use a different pagination style, so ... | 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-retry-policy` (language: python). INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by runnin... | 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-newrelic-synthetic-monitor`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running command... | 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 `ts-atlas-ip-access-list` (language: ts). INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by ru... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
The lunchroom Connect Four ladder is moving onto our chat bot and I need the engine plus a house bot whose play is exactly reproducible — we archive games as move lists and replay them during disputes, so the bot must be a pure function of (position, depth). Build connect4.ts (stdlib only, no npm); tes... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
CRM integrations pod. Our provisioning service already creates Salesforce record hierarchies through the sObject Tree endpoint (tree_client.ts — it works, leave its behavior alone), but sales ops keeps asking for linked writes a tree can't express: create an Account, then a Contact AND an Opportunity t... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Ticketing meltdown at the Orpheum. Our reservation book behaves perfectly for studio-theater shows (seats 1-80) and loses its mind for main-hall shows (seats 101-412): the same main-hall seat gets sold to two different patrons, the seating chart shows seats as free that we JUST sold, the refund desk ge... | 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-sentinel-shutdown` (language: python). INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by r... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Two field reports against the backup agent's manifest layer (backman.py) and support is done arguing with customers about them. First: nightly incrementals keep skipping files people definitely changed. Classic case from yesterday: someone edits a config right after the nightly run finishes, next night... | 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-supervisor`. 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
We got bitten badly by the units package last month: it's one process-wide table (package-level maps, an init() that preloads the standard units, a global precision setting), and when the importer started calling units.SetPrecision(6) for its own output, every dashboard number rendered by the SAME proc... | 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-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
I run the online side of our Saturday farm market and since we shipped the "reorder last week's basket" button the support inbox is a mess. Two flavors of weird, and I can reproduce both: 1) A customer hits reorder on a saved basket, gets a fresh copy to tweak, adds a couple of jars of honey to the COP... | 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 `ts-cleanup-reject` (language: ts). 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
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
The after-school coding club wants Snakes & Ladders runnable in the terminal, replayable from files so every demo comes out identical. One bash script: `snakes.sh <board-file> <dice-file> <player> <player>...` — at least two players, turn order is the argument order. Fewer arguments than that (or only ... | 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 `zsh-assocrep`. 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
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `go-modcycles`. 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-ttl-jump` (language: python). INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running co... | 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
Code review keeps turning up the same whitespace junk, and we now have four separate one-off fixer scripts in tools/. I want them unified behind a proper plugin pipeline, and I have strong opinions about the shape of it: plugins register themselves through a decorator, and the ORDER plugins run in come... | 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-supervisor`. 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-tfe-run-queue`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and reading cod... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
SRE tooling ticket. Our release gate is supposed to hold a deploy when the checkout SLO is burning, but the current implementation is a PowerShell relic that talks to the OLD Dynatrace SLO endpoint on our live.dynatrace.com URL and treats a slow evaluation as a pass. We've upgraded to the latest SLOs, ... | 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-snowflake-partition-results` (language: go). INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yoursel... | 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 `zsh-plugin-option-scope`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and read... | 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-mdtoc`. 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
I maintain the solitaire corner of our office arcade box and FreeCell is next on the list. I don't need a UI or a solver — I need the ENGINE: load a deal from text, referee every move, and be pedantic about the supermove capacity rule, because that's the one everyone argues about. Implement src/lib.rs ... | 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 `go-healbudget`. 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
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `py-flowplan`. 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
We have a small in-house Java client for SDDC Manager (Json/SddcHttpClient/DomainsClient in this repo) that our inventory jobs use, and today it's driven by an access token somebody pastes into an env var. VCF access tokens are short-lived, so the jobs die mid-run every hour and — worse — when someone ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
The photo-kiosk thumbnail warmer is failing our CI gate (`bash run_verify.sh`) — it gets through gofmt fine but go vet is unhappy about the warmer, and honestly the thing has been flaky on the bench too: after a warm pass the cache sometimes contains just ONE photo (the log shows the same filename rend... | 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 `ts-cleanup-reject` (language: ts). 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
Cancel Municipal grant review, record ID cal-101, because the host withdrew the agenda. Use that exact reason and do not touch similarly named records.<|im_end|>
<|im_start|>assistant
I can't complete this cancellation. The tools available to me are read-only — `calendar_search` (to find meetings) and ... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Scheduler infra. We run two copies of the ingest scheduler and today they "coordinate" via a Redis SETNX hack that split-brained us twice last quarter. I want proper Kubernetes leader leases. The repo already has k8s_client.py — a small working ApiClient (bearer auth, JSON, get/create/replace lease cal... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
You are Fable, the sole seed author responsible for repairing wave 8 chunk 8C. Do not delegate, do not call another model, and do not generate code-teacher traces. The four existing seeds were authored and their reference gates passed, but the fail-closed wave audit rejected at least one user prompt be... | 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
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `go-retry`. 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
You are the PRIMARY code reviewer for a distillation-trace acceptance gate. A teacher model produced a code change for task `ts-reportcard`. 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
Our rollout-gate repo is red on CI and I'm holding the pager. Backstory: a teammate finished the version-range gating in gate.mjs right before going on leave — the feature itself looks done, and I literally watched the suite pass on their laptop. But every CI build since their last push dies in the boo... | 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-ringbuf`. 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
Mentions are haunted. The first @user in a message frequently never gets notified, hasMention literally alternates true/false when you call it twice on the same string, and the handle validator accepts 'no spaces allowed' as a valid username. Three symptoms, one small module. Repro for all of it: `node... | 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-monorepo-command`. 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
The lobby badge printer has been misbehaving ever since I ported the front-desk slip renderer from the old VB app, and reception is annoyed. Three separate complaints, all on every single pass it prints: - The badge number printed on the pass tracks OUR desk-app session counter (restarts at 1 whenever ... | 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-wiredepot`. INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by running commands and reading cod... | 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-wrap-justify`. 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 `java-okta-user-lifecycle` (language: java). INDEPENDENTLY verify it with your own tools and return a strict verdict. Trust no prior review — verify everything yourself by... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Security-engineering ticket. Our SIEM ingestion box tails the Okta System Log today with a cron + curl hack that re-reads whole hours and double-writes events after every hiccup, and the detection team is done with it. Build the replacement: a small C# library (namespace OktaSyslog) that sweeps /api/v1... | 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-wordfreq`. 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
Change windows on the fleet are currently a wiki page and crossed fingers, and the last bad window proved we cannot reconstruct afterwards what was applied where or what to unwind. I want changerun.ps1: a planner that turns our desired-state model plus per-host facts into an ordered change plan, then t... | You are an elite agentic AI coding assistant. You write clean Python code and utilize tools effectively. | Frontier-Distill |
<|im_start|>user
Ticket: inventory service MVP for the warehouse tooling. Small JSON REST server, in-memory storage for now but storage WILL move to Postgres next quarter, so the HTTP layer must be written against a storage interface, not a concrete map. Module go-inventory-api, package inventory. Exports the tests (an... | 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
Ticket from the release-audit crew. After every deploy we run three saved SPL searches by hand in the Splunk UI and paste screenshots into the change record — audit wants that automated from our Java service. Build the client classes for it (stdlib only; a small JSON helper ships in Json.java — use or ... | 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.