Absorb the v1 cascade composer #23

New issue

Closed

opened 2026-07-23 00:04:14 +00:00 by coilyco-ops · 1 comment

coilyco-ops commented

2026-07-23 00:04:14 +00:00

Member

Copy link

What to build

Pull all of v1's functionality (agentic-os generate_agent_compose.py) into the Go tool as agent-compose cascade, superseding the coexistence framing in docs/integration.md. V2 becomes the only composer; v1 retires after a compatibility window.

Acceptance criteria

agent-compose cascade reads the existing ~/.config/agent-compose/agent-compose.yaml unchanged: no config means total no-op; sources compose in listed order, then roots walked for AGENTS.COMPOSE.md sorted.
Scope filtering (machine scopes intersect source frontmatter scopes; absent machine scopes disables filtering) and harness filtering (frontmatter harnesses) behave exactly as v1.
Source rewrites match v1: frontmatter stripped, relative markdown links absolutized against the source directory, '## See also' sections dropped.
Per-harness sibling overrides (AGENTS..md) replace matching sections by verbatim heading and append new ones; overrides feed the divergence signature.
Divergence: one COMPOSED.md when every harness sees identical content, else COMPOSED..md; byte-identical slices share.
Load-point symlinks (claude/codex defaults plus config overrides) repoint safely; the mount-eligibility manifest is emitted deterministically with the v1 banner, default mount set, and per-harness repo unions so ward's read is uninterrupted.
--dry-run touches nothing; --check reproduces the drift verification with a unified diff.
Behavior cross-checked against the Python composer on shared fixtures; divergences are bugs unless recorded.
The roster artifact composes through the native cascade, closing the loop #19 wanted - and the dormant-host decision dissolves, since no Python revival is needed.
Docs: integration.md rewritten (v2 owns the cascade), cascade.md added, aos-side retirement steps (hook repointing, script removal) filed on agentic-os rather than done here.

Execution type

AFK against the v1 source and tests as the spec.

Filed by Claude Code on Kai's direction.

## What to build Pull all of v1's functionality (agentic-os generate_agent_compose.py) into the Go tool as `agent-compose cascade`, superseding the coexistence framing in docs/integration.md. V2 becomes the only composer; v1 retires after a compatibility window. ## Acceptance criteria - [ ] `agent-compose cascade` reads the existing ~/.config/agent-compose/agent-compose.yaml unchanged: no config means total no-op; sources compose in listed order, then roots walked for AGENTS.COMPOSE.md sorted. - [ ] Scope filtering (machine scopes intersect source frontmatter scopes; absent machine scopes disables filtering) and harness filtering (frontmatter harnesses) behave exactly as v1. - [ ] Source rewrites match v1: frontmatter stripped, relative markdown links absolutized against the source directory, '## See also' sections dropped. - [ ] Per-harness sibling overrides (AGENTS.<harness>.md) replace matching sections by verbatim heading and append new ones; overrides feed the divergence signature. - [ ] Divergence: one COMPOSED.md when every harness sees identical content, else COMPOSED.<harness>.md; byte-identical slices share. - [ ] Load-point symlinks (claude/codex defaults plus config overrides) repoint safely; the mount-eligibility manifest is emitted deterministically with the v1 banner, default mount set, and per-harness repo unions so ward's read is uninterrupted. - [ ] --dry-run touches nothing; --check reproduces the drift verification with a unified diff. - [ ] Behavior cross-checked against the Python composer on shared fixtures; divergences are bugs unless recorded. - [ ] The roster artifact composes through the native cascade, closing the loop #19 wanted - and the dormant-host decision dissolves, since no Python revival is needed. - [ ] Docs: integration.md rewritten (v2 owns the cascade), cascade.md added, aos-side retirement steps (hook repointing, script removal) filed on agentic-os rather than done here. ## Execution type AFK against the v1 source and tests as the spec. Filed by Claude Code on Kai's direction.

coilyco-ops referenced this issue from a commit

2026-07-23 00:13:22 +00:00

feat: absorb the v1 cascade composer

coilyco-ops commented

2026-07-23 00:14:36 +00:00

Author

Member

Copy link

Shipped in 37e6df6, released as v0.2.0 (brew and scoop bumped).

agent-compose cascade reads the existing agent-compose.yaml unchanged: absent config no-ops; explicit sources compose in order, then roots walked sorted; duplicates collapse to first occurrence; missing sources degrade with a warning in run and fail in check, matching v1.
Scope filtering (absent key = off, untagged sources drop under active filtering, empty match refuses to write) and harness frontmatter filtering: tested.
Rewrites match v1: frontmatter stripped, See-also sections dropped, relative links absolutized with symlink resolution and fragment preservation.
Sibling AGENTS..md overrides replace by verbatim heading, append new sections, and fail loudly on ambiguous anchors; overrides feed the divergence signature; converging removes stale banner-carrying outputs and repoints symlinks (all tested).
Load-point symlinks: claude/codex defaults, config overrides, null opt-out, .bak backup of pre-existing regular files. Mount-eligibility manifest byte-matches v1 (defaults unioned per harness, deterministic JSON).
--dry-run previews only real changes and previews converged hosts as no-ops; --check reproduces drift verification with a bounded diff.
Cross-check: Go and Python composers ran on a shared fixture (scoped source in a projects repo, claude override, links, See-also, untagged root source); all outputs byte-identical after matching Python's symlink resolution in link absolutization. One knowing simplification: the drift diff is a bounded minus/plus rendering rather than difflib's full unified format.
The roster artifact now composes through the native cascade; #19's dormant-host decision is dissolved - no Python revival needed. Note recorded in docs/integration.md: this workstation's hand-edited COMPOSED snapshots must be reconciled into sources before the first native cascade run here.
Remaining aos-side retirement (drift-hook repointing, generator removal, fleet cutover) deliberately not done here; needs filing on agentic-os.

Closed by Claude Code working the issue queue.

Shipped in 37e6df6, released as v0.2.0 (brew and scoop bumped). - agent-compose cascade reads the existing agent-compose.yaml unchanged: absent config no-ops; explicit sources compose in order, then roots walked sorted; duplicates collapse to first occurrence; missing sources degrade with a warning in run and fail in check, matching v1. - Scope filtering (absent key = off, untagged sources drop under active filtering, empty match refuses to write) and harness frontmatter filtering: tested. - Rewrites match v1: frontmatter stripped, See-also sections dropped, relative links absolutized with symlink resolution and fragment preservation. - Sibling AGENTS.<harness>.md overrides replace by verbatim heading, append new sections, and fail loudly on ambiguous anchors; overrides feed the divergence signature; converging removes stale banner-carrying outputs and repoints symlinks (all tested). - Load-point symlinks: claude/codex defaults, config overrides, null opt-out, .bak backup of pre-existing regular files. Mount-eligibility manifest byte-matches v1 (defaults unioned per harness, deterministic JSON). - --dry-run previews only real changes and previews converged hosts as no-ops; --check reproduces drift verification with a bounded diff. - Cross-check: Go and Python composers ran on a shared fixture (scoped source in a projects repo, claude override, links, See-also, untagged root source); all outputs byte-identical after matching Python's symlink resolution in link absolutization. One knowing simplification: the drift diff is a bounded minus/plus rendering rather than difflib's full unified format. - The roster artifact now composes through the native cascade; #19's dormant-host decision is dissolved - no Python revival needed. Note recorded in docs/integration.md: this workstation's hand-edited COMPOSED snapshots must be reconciled into sources before the first native cascade run here. - Remaining aos-side retirement (drift-hook repointing, generator removal, fleet cutover) deliberately not done here; needs filing on agentic-os. Closed by Claude Code working the issue queue.

coilyco-ops closed this issue

2026-07-23 00:14:38 +00:00

coilyco-ops referenced this issue

2026-07-23 00:14:40 +00:00

Publish the roster artifact into the v1 cascade #19

No Branch/Tag specified

main

feat/gamedev-role

feat/boundary-omit

aos/claude/eval-context

aos/claude/eval-current-state

aos/claude/eval-refs-restore

aos/claude/eval-docs-one-page

aos/claude/personality-anchors

aos/claude/favorite-color-spread

aos/claude/personality-catalog-gaps

aos/claude/gh297-binding-skill-selector

aos/claude/personality-prose-distinctiveness

aos/claude/gh56-adopt-aos-eval

aos/claude/aw85-bands

aos/claude/xu59-just

aos/claude/xu59-eval-export

aos/claude/xu59-comment-caps

aos/claude/xu59-pr-ci

aos/claude/xu59-role-attribution

aos/claude/ck78-banner

aos/claude/mg96-fm

rescue/precommit-v0.18-uncommitted

evals/262-board-run

claude/agents-temp-clone-note

assets/compose-mark

adjacency/262-role-adjacents

chore/precommit-bump

prose/257-258-233-second-person

boundary/254-primitive-rename

fix/acompose-undefined-role-bindings

comms/rescope-counterpart

native-home/968-user-scope-projection

meld/248-evidence-acquisition

meld/231-shared-role-melds

evals/240-baseline

evals/240-model-arms

spike/claude-native-ui-surfaces

issue-225-compact-director-eval

issue-210

issue-218

issue-215-remove-context-levels

codex/luna-medium-ai-evaluation

issue-206-align-role-tiers

codex/luna-medium-roster-prose

issue-196-remove-legacy-role-providers

issue-197-role-provider-graph

feat/model-tiers

feat/remove-context-levels

issue-187

issue-178-content-communication-ownership

issue-163-designer-evals

codex/issue-794-preserve-canonical-projections

issue-163-ornith-direct-eval

issue-163-design-current-eval

issue-150-v2-baseline

issue-156-content-code

issue-150-v2-evidence

issue-150-v2-evaluation

issue-154-v2-main-integration

issue-148-remove-v1-integrations

issue-146-core-roster

issue-144-aos-catalogue-manifest

issue-152-release-classifier

issue-139-role-metadata-last

issue-138-designer-visual-web

issue-785-first-person

ward-salvage/agent-compose-078db83c

ward-salvage/agent-compose-74e37165

issue-130

recovery/2026-07-27-local-work

v2.39.0

v2.38.0

v2.37.0

v2.36.0

v2.35.0

v2.34.0

v2.33.0

v2.32.0

v2.31.0

v2.30.0

v2.29.0

v2.28.0

v2.27.0

v2.26.0

v2.25.0

v2.24.0

v2.23.0

v2.22.0

v2.21.0

v2.20.0

v2.19.0

v2.18.0

v2.17.0

v2.16.0

v2.15.0

v2.14.0

v2.13.0

v2.12.0

v2.11.0

v2.10.0

v2.9.0

v2.8.0

v2.7.0

v2.6.0

v2.5.0

v2.4.0

v2.3.0

v2.2.0

v2.1.0

v2.0.0

v1.49.0

v1.48.0

v1.47.0

v1.46.0

v1.45.0

v1.44.0

v1.43.0

v1.42.0

v1.41.0

v1.40.0

v1.39.0

v1.38.0

v1.37.0

v1.36.0

v1.35.0

v1.34.0

v1.33.0

v1.32.0

v1.31.0

v1.30.0

v1.29.0

v1.28.0

v1.27.0

v1.26.0

v1.25.0

v1.24.0

v1.23.0

v1.22.0

v1.21.0

v1.20.0

v1.19.0

v1.18.0

v1.17.0

v1.16.0

v1.15.0

v1.14.0

v1.13.0

v1.12.0

v1.11.0

v1.10.0

v1.9.0

v1.8.0

v1.7.0

v1.6.0

v1.5.0

v1.4.0

v1.3.0

v1.2.0

v1.1.0

v1.0.0

v0.70.0

v0.69.0

v0.68.0

v0.67.0

v0.66.0

v0.65.0

v0.64.0

v0.63.0

v0.62.0

v0.61.0

v0.60.0

v0.59.0

v0.58.0

v0.57.0

v0.56.0

v0.55.0

v0.54.0

v0.53.0

v0.52.0

v0.51.0

v0.50.0

v0.49.0

v0.48.0

v0.47.0

v0.46.0

v0.45.0

v0.44.0

v0.43.0

v0.42.0

v0.41.0

v0.40.0

v0.39.0

v0.38.0

v0.37.0

v0.36.0

v0.35.0

v0.34.0

v0.33.0

v0.32.0

v0.31.0

v0.30.0

v0.29.0

v0.28.0

v0.27.0

v0.26.0

v0.25.0

v0.24.0

v0.23.0

v0.22.0

v0.21.0

v0.20.0

v0.19.0

v0.18.0

v0.17.0

v0.16.0

v0.15.0

v0.14.0

v0.13.0

v0.12.0

v0.11.0

v0.10.0

v0.9.0

v0.8.0

v0.7.0

v0.6.0

v0.5.0

v0.4.1

v0.4.0

v0.3.0

v0.2.1

v0.2.0

v0.1.2

v0.1.1

v0.1.0

Labels

Clear labels

autonomy

async-consult

A human needs to consult on the issue to upgrade it to headless

autonomy

epic

This issue has many units of sub work - its size makes it meaningfully exclusive with other autonomy types

autonomy

headless

The agent can perform the work on its own

autonomy

live-collab

The agent and the human need to work together in realtime

coherence-core

Core review set for the warded control plane coherence milestone. These issues form the release spine; adjacent milestone issues are stretch or supporting work.

Disposable issue admitted to the bounded Ward QA verification lane.

role/ai

requires work from the AI Engineer role

role/creator

requires work from Content Creator role

role/design

requires work from the design role

role/director

requires work from the director role

role/engineer

requires work from the engineer role

role/exec

requires work from the exec role

role/human

requires a person, and specifically not an agent seat

role/ops

requires work from the ops role

role/qa

requires work from the QA role

No labels

Milestone

Clear milestone

No items

No milestone

Projects

Clear projects

No items

No project

Assignees

Clear assignees

No assignees

1 participant

Notifications

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set

Reference

coilyco-flight-deck/agent-compose#23

Reference in a new issue

Repository

coilyco-flight-deck/agent-compose

Title

Body

No description provided.

Delete branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?

Rows
Columns