Post-first-call iteration of the bootstrap. Citation verification of Volva's R07-followon test reply confirmed all six arXiv IDs she cited are real papers — including two 2026 submissions (SWE-PRBench Kumar March 2026, Sansford et al. ICLR-workshop April 2026) that have training-cutoffs newer than Claude's. The load-bearing finding: Volva is the access path to a training surface Claude cannot reach. Updates: - AGENTS.md — third role (general sounding board) added alongside research-partner and code-reviewer. New "Cross-frontier-model cooperation — why you exist" section explicitly names the pattern: Volva and her callers run different model families with different training cutoffs and priors; she should disagree more cheaply, cite recent work confidently, and mark training-cutoff gaps explicitly when load-bearing. - SOUNDING-BOARD-GUIDE.md (new) — discipline for general design- talk-through calls. Steelman first then critique; surface specific concerns not vague unease; mark strong-opinion vs limited-evidence explicitly; be concise; useful sounding-board moves (assumption decomposition, bad-case framing, where-I'd-bet-against-you, cheaper-version-that-proves-the-same-thing, data-first); anti- patterns (validating without engaging, hedging into fog, overreach). - CROSS-FRONTIER-COOPERATION.md (new) — durable framing doc. Different families bring different training data / cutoffs / RLHF priors / failure modes. Brokkr's discipline: consult Volva at every research gate (pre-scope, pre-survey, mid-synthesis, pre-action- shipment). Lean toward what Volva has that Claude doesn't (recent work, different priors). Don't pretend to have what you don't. - RESEARCH-PARTNER-GUIDE.md — citation discipline refined. Removed the overly-broad "always disclaim training cutoff" framing; replaced with cross-frontier framing (your cutoff likely extends past Claude's, recent citations are exactly why you're called). Added explicit: distinguish "I recall this paper" (cite directly) from "I'm reconstructing what such a paper would look like" (synthesizing). Mark training-cutoff uncertainty when load-bearing. - README.md — updated layout + roles section; cross-frontier framing surfaced at the top.
3.5 KiB
volva-context
Codex's working root when invoked by the Volva daemon. Volva makes codex a peer on the althing bus; this directory is the durable context codex reads on every call.
Why a separate repo
Volva's daemon repo (~/development/volva) deliberately keeps codex out of its own view — codex's CWD is here (~/development/volva-context/), not the volva repo. That isolation:
- Lets codex's context evolve on its own version track (this repo) without churning the daemon repo.
- Keeps codex from grepping the daemon's source while answering caller questions.
- Lets the operator update glossaries/inventories without touching daemon code.
The VOLVA_CODEX_CWD env var in ~/development/volva/env.sh points here.
Layout
.
├── AGENTS.md # codex's bootstrap entrypoint (read every call)
├── CONTEXT.md # Corviduo + Vast Blue glossary
├── INVENTORY.md # project list, paths, gitea sources, role
├── PRINCIPLES.md # the four engineering principles
├── CROSS-FRONTIER-COOPERATION.md # why Volva exists as a peer (codex vs claude)
├── REVIEW-GUIDE.md # code-review discipline (one of three roles)
├── RESEARCH-PARTNER-GUIDE.md # research-partner discipline
├── SOUNDING-BOARD-GUIDE.md # general design-talk-through discipline
└── transient/
├── README.md # per-call context convention
└── *.md # caller-seeded transient files (gitignored)
Roles
Volva operates in one of three roles per call, inferred from the caller's handle and the message body:
- Research partner when
brokkr-smithy-devasks for SOTA / probe-design / hypothesis-critique / methodology review. - Code reviewer when a project-dev handle asks for diff review, contract review, ADR critique.
- General sounding board when any peer asks for design-talk-through, gut-check, steelman/counter-position, "what am I missing?"
AGENTS.md is the entrypoint; the role guides are loaded as needed.
Why Volva exists
Cross-frontier-model cooperation is a deliberate Corviduo discipline. Volva runs on codex/gpt-5.5; most callers run on claude-opus-4-7 or sonnet variants. Different model families → different training data, different cutoffs, different priors, different blind spots. Brokkr-Smithy's research discipline consults Volva at every research gate (pre-scope / pre-survey / mid-synthesis / pre-action-ship) for cross-frontier critique. See CROSS-FRONTIER-COOPERATION.md for the pattern.
Updating
This repo is durable but mutable. When project state changes:
- New project lands in Corviduo → extend
INVENTORY.md+ add an entry toCONTEXT.md. - Glossary term shifts → update
CONTEXT.mddirectly. - New review-pattern or research-discipline lesson surfaces → extend the relevant role guide.
- Engineering principle clarification → update
PRINCIPLES.md; this is the local copy of the operator-level lodestar.
Per-call ephemera goes in transient/<slug>.md (gitignored). See transient/README.md for the convention.
Authority
Project-local CONTEXT.md files (in individual project repos) shadow entries here on conflict — most-local-wins. The definitions in this repo are the user-level baseline that Volva carries across calls.
Attribution: operator is Vuong Hoang. No AI / Claude / Anthropic / Codex attribution in artifacts Volva produces.