RUNPOD

Axiom

RUNPOD provides governed compute. Every deployment validated.

Constraints

MUST:     Route through governed gateway
MUST:     Emit telemetry to governed surfaces
MUST:     Fail closed on validation failure
MUST NOT: Hardcode credentials or endpoints
MUST NOT: Bypass governance validation

Capabilities

COMPUTE_PROVISION, FAIL_CLOSED, TELEMETRY_EMIT

COVERAGE: 255/255

SPEC

Purpose

RUNPOD is CANONIC.

Defines the structural contract for RUNPOD. Scope is the directory name.

For this directory: scope = RUNPOD

This contract defines:

structure,
interface,
ecosystem connectivity.

CANON then governs this scope here-and-now under that contract.

Structure

Root RUNPOD domains: none currently (leaf MAGIC scope).

Required closure artifacts per scope: CANON.md, README.md, RUNPOD.md, VOCAB.md, ROADMAP.md, COVERAGE.md, LEARNING.md.

Learning lane per governed scope: LEARNING.md at the scope root is terminal and SHALL NOT nest further LEARNING/.

Routes

web_docs: https://hadleylab.org/
web_surface: https://hadleylab.org/SERVICES/MAGIC/RUNPOD/
magic:    magic://hadleylab.org/SERVICES/MAGIC/RUNPOD/

Ecosystem Connectivity

Upstream: MAGIC governance contracts and SERVICES meta-governance.
Runtime: ~/.canonic provider adapter wiring and serverless Runpod.io endpoint bindings.
Frontend: RUNPOD scope MUST remain visible through governed catalog sync.
Ledger plane: consumes governed request/response telemetry and emits health metrics.

Runtime bindings (owned by ~/.canonic/DESIGN/TALKS/ and api.canonic.org):

secret: RUNPOD_API_KEY
var: RUNPOD_BASE_URL
var: RUNPOD_MODEL (or MODEL)
var: RUNPOD_TIMEOUT_MS
var: RUNPOD_TRIES
var: RUNPOD_RETRY_DELAY_MS
var: FALLBACK_PROVIDER
var: TOKENS_MIN, TOKENS_MAX, MAX_TOKENS

Pages

Page	Sections
Overview	Purpose, Structure
Ecosystem	Routes, Ecosystem Connectivity

Default: Overview.

INTEL

Cross-Scope Evidence

Content Claim	Evidence Source	Reference	Status
Provides governed compute	RunPod platform	RUNPOD/CANON.md	PENDING
Every deployment validated	Validation pipeline	RUNPOD/CANON.md	PENDING
Routes through governed gateway	Gateway config	RUNPOD/CANON.md	PENDING
Emits telemetry to governed surfaces	Telemetry pipeline	RUNPOD/CANON.md	PENDING
Fails closed on validation failure	Validation logic	RUNPOD/CANON.md	PENDING
No hardcoded credentials or endpoints	Discovery via scan	RUNPOD/CANON.md	PENDING

Content Inventory

Section	Content	Status	Gap
Compute provisioning	Governed RunPod deployments	PENDING	Verify deployment pipeline
Gateway routing	Governed gateway integration	PENDING	Verify gateway config
Telemetry	Emissions to governed surfaces	PENDING	Verify telemetry pipeline
Credential management	No hardcoded credentials	PENDING	Verify secret handling

Domain Architecture

Layer	Current	Target
Compute	RunPod platform	Every deployment validated
Routing	Governed gateway	All traffic governed
Credentials	Dynamic discovery	No hardcoded endpoints

Test

prompt	expect	cross
Are deployments validated?	Yes — every deployment	RUNPOD/CANON.md axiom
What happens on validation failure?	Fail closed	RUNPOD/CANON.md constraints
Are credentials hardcoded?	No — discovered dynamically	RUNPOD/CANON.md constraints

LEARNING

Ledger

Date	Pattern	Source
2026-02-15	OpenAI-compatible contracts are the safest provider-switch boundary	RUNPOD/CANON.md constraint 3
2026-02-15	Serverless cold-start behavior must be governed before runtime rollout	RUNPOD/CANON.md constraint 5
2026-02-15	Runpod serverless endpoint vllm-sia7z3a2gk6wr4 failing with vLLM engine core init errors (exit code 1)	Console logs @ https://console.runpod.io/serverless/user/endpoint/vllm-sia7z3a2gk6wr4
2026-02-15	Worker crashes block queue processing — 7 requests queued but 0/1 running, 1 unhealthy worker	Runpod console worker states
2026-02-15	Serverless endpoints require working health checks before production rollout	vllm-sia7z3a2gk6wr4 failure
2026-02-15	Enforced governed timeout+retry+fallback at `api.canonic.org/chat` so RUNPOD cold starts cannot stall TALK; response includes provider_used + elapsed_ms + usage telemetry	`~/.canonic/DESIGN/TALKS/src/worker.js` + RUNPOD/CANON.md constraints 3,5,6
2026-02-15	Governed alternative provider scope (VASTAI) created as an option if RUNPOD serverless operations regress	MAGIC/VASTAI scope addition
2026-02-18	RunPod Qwen pod (aq0t10sits4kz2) context window upgraded to 32768 — confirmed operational via /v1/models max_model_len	Runtime probe @ aq0t10sits4kz2-8000.proxy.runpod.net
2026-02-18	RunPod DeepSeek pod (g0aelua3ct8eb4) persistently down (404) — needs manual restart from RunPod dashboard; not fixable via API	Runtime probe returning 404/502 across full session
2026-02-18	RunPod API key lacks pod management permissions — `myself` GraphQL query returns null; cannot stop/start/restart pods programmatically	GraphQL API probe
2026-02-18	Default Kilocode provider changed to DeepSeek API (commercial, 64K context) — vLLM pods have 8K–32K context which truncates ~11K Kilocode payloads	wrangler.toml default_kilocode route update
2026-02-18	All RunPod pods destroyed (canonic-talk-vllm aq0t10sits4kz2 + canonic-kilocode-deepseek g0aelua3ct8eb4) — not in active use; zero resources remain on platform	Operator directive + runpodctl CLI
2026-02-18	Relaunch recipe (pods): `runpodctl create pod --name <NAME> --gpuType "NVIDIA RTX A4500" --gpuCount 1 --imageName vllm/vllm-openai:latest --volumeSize 20 --containerDiskSize 20 --env "MODEL_NAME=<MODEL>" --env "MAX_MODEL_LEN=32768" --env "GPU_MEMORY_UTILIZATION=0.90"`; update RUNPOD.toml with new pod/endpoint IDs	Prior lifecycle patterns in this ledger
2026-02-18	Relaunch recipe (serverless): create endpoint via RunPod console with template_id from RUNPOD.toml, set workers_min=1, idle_timeout=300, flashboot=true; update endpoint_id + base_url in RUNPOD.toml	RUNPOD.toml profiles

Constraints

MUST append new runtime lessons; MUST NOT overwrite history.
MUST link each learned pattern to governed evidence.
SHOULD propagate provider-routing lessons to MAGIC root LEARNING.

Meta-Patterns

Date	Pattern	Source
2026-02-15	Provider infrastructure gets safer when modeled as a governed leaf scope instead of inline runtime config	RUNPOD scope creation

ROADMAP

VOCAB

Term	Definition
RUNPOD	Runpod.io serverless provider scope under MAGIC governance.

INHERITANCE CHAIN

MAGIC

MAGIC enforces governance at runtime. Every request validated. Every response governed.

MUST:     Route through governed gateway
MUST:     Validate every request against governance
MUST:     Emit telemetry to governed surfaces
MUST:     Fail closed on validation failure
MUST NOT: Hardcode credentials or provider bindings
MUST NOT: Bypass governance validation

SERVICES

SERVICES compose primitives — INTEL + CHAT + COIN. Every service governed. Every scope discovered.

MUST:     Maintain TRIAD integrity (CANON.md + VOCAB.md + README.md)
MUST:     Treat SPEC as scope identity (`{SCOPE}` directory), not as a file
MUST:     Every SERVICE scope include ROADMAP.md, COVERAGE.md, LEARNING.md, and `{SCOPE}.md` as governed content surfaces
MUST:     Discover SERVICE scopes from filesystem only (no manual catalog)
MUST:     Keep http:// and magic:// on the same namespace (transport differs, scope path matches)
MUST:     CANON.md = axiom + universal constraints (no service names, no paths, no implementation)
MUST:     README.md = how to run the CANON (nothing else)
MUST:     {SCOPE}.md = SPEC — the interface (purpose, routes, projections, ecosystem)
MUST:     SHOP.md = public projection file (per scope, filesystem-discoverable)
MUST:     VAULT.md = private projection file (per scope, filesystem-discoverable)
MUST:     Runtime implementation remains under ~/.canonic; this workspace is governance-first
MUST NOT: Hardcode service names in CANON constraints (law speaks universals)
MUST NOT: Define ungoverned terms outside VOCAB.md
MUST NOT: Treat `{SCOPE}.md` as SPEC identity
MUST NOT: Move architecture/lifecycle into README
MUST NOT: Leak private projections to public surfaces
MUST NOT: Maintain duplicate mapping tables outside generated manifest outputs
MUST NOT: Add runtime jargon to governance contracts
MUST:     Ledger-consuming services declare source ledgers, scope filters, and closure gates
MUST:     Learning governance remains live — closure claims require fresh DISCOVER → GENERATE → RELINK evidence

hadleylab-canonic

HADLEYLAB ships software. Every app, book, paper, deal, and patent is PROOF that MAGIC works. COIN = WORK. LEARNING = COMPUTE.

MUST:     Every app, book, paper, deal, or patent is evidence of MAGIC
MUST:     All scopes inherit canonic-canonic/CANONIC.md governance
MUST:     All users governed under USERS/ via SERVICES/USER
MUST:     Cross-index INTEL across users (INTEL.md)
MUST:     Shared events propagate to ALL affected user dashboards
MUST:     Maintain governance workspace purity (.md files only)
MUST:     Ledger all COIN (validated work) through MAGIC 255
MUST:     Compile all INTEL from governed sources
MUST:     Keep frontend/runtime implementation under ~/.canonic (hidden runtime)
MUST:     Surface governed TALK, Library, and SERVICES scopes (no orphan content)
MUST:     Derive nav labels from governed scope names (no hardcoded strings)
MUST NOT: Publish without governance (CANON.md required)
MUST NOT: Duplicate primitives — compose from INTEL, CHAT, COIN
MUST NOT: Silo intelligence inside a single user when multiple are affected
MUST NOT: Expose VAULT contents outside NDA scope
MUST NOT: Store runtime artifacts in governance workspace

canonic-canonic

SPEC is governance. `canonic-canonic/` is the spec root.

MUST:     Keep this repo governance-only (.md/.pdf)
MUST:     Publish workspace mapping in CANONIC.git (no hardcoded repo lists)
MUST:     Preserve three primary lanes: FOUNDATION, INDUSTRIES, MAGIC
MUST NOT: Commit runtime artifacts here (runtime belongs in ~/.canonic/)
MUST:     Sell MAGIC tiers — the product, not the proof (proof is hadleylab-canonic)
MUST NOT: Embed beta-test app URLs in platform page content