Changelog — ODF Agent Team
#Unreleased
#Fixed
- Single-word skill triggers now match at a word boundary:
reviewno longer selects the views skill viaview,transactionno longer selects actions viaaction, andlatestno longer selects testing viatest. - The parallel branch prompt bound is 64 KB, leaving room for the canonical and domain skill bodies.
- Linked the previously unreachable version references and replaced the OCA contributing wikilinks with real skill paths.
#Changed
- Consolidated 41 pattern, testing, and version skills into 5 domain skills:
odoo-modeling,odoo-views-owl,odoo-business-flows,odoo-testing, andodoo-versioning. Each former skill is nowreferences/<topic>.mdwith its examples, and the registry drops from 87 to 51 entries. - Skill descriptions now lead with
Use whenand describe user intent instead ofEntity. Trigger: ...; all 87 were rewritten. - Delegations also inject the body of the highest-scoring non-canonical skill (capped at 8,000 characters), so domain standards are usable without flooding the prompt.
- Added a trigger-eval dataset (
scripts/odf-skill-evals/trigger-queries.json, 57 realistic prompts) and a test that requires the expected skill in the top 3. - Odoo version filters were normalized to 16-19, and the five skills that referenced the nonexistent
grep_app_searchGitHubnow use localrgcommands. - Skills now use the Agent Skills layout: all 87 registered skills live at
skills/<name>/SKILL.md, 73 flat files were migrated, 50 version variants moved toreferences/versions/, and 23 long skills were split intoSKILL.mdplusreferences/examples.md. - Absolute install and personal paths in skill references were replaced with relative links; the OCA index and dispatcher paths now point at the flat layout.
- Delegations inject the canonical stage skill's full
SKILL.mdbody (frontmatter stripped, capped at 20,000 characters) alongside compact rules for matched skills, and list bundledreferences/,scripts/, andassets/for on-demand reads. The parallel branch prompt bound is now 32 KB.
#1.6.2 (2026-10-26)
#Added
- A real documentation site: every documentation link renders as a standalone page with a grouped sidebar, in-page table of contents, breadcrumbs, reading time, prev/next navigation, and the search palette.
scripts/odf-docs-build.jsrewrites Markdown links (registered sources → relative pages, repository files → GitHub blob URLs, external links untouched), reproduces GitHub heading anchors, and generatessearch-index.json,sitemap.xml,robots.txt, and.nojekyll(#186). npm run docs:build/npm run docs:check, a CI step, and unit tests for the slugger and link rewriter keep the generated pages in sync (#186).- A Diagrams group in every docs sidebar, plus a styled 404 page (#186, #187).
- A privacy guard test that fails when a published file gains an absolute home path, Windows home path, provider email, private-key block, known token format, URL with credentials, or literal password (#188).
#Changed
install.shand the TUI installer rewrite any/home/<user>/.config/opencodepath instead of one hardcoded author path, so the pack is portable without embedding a username (#188).- Skill frontmatter uses the public project handle; internal task logs, SDD state, and the archived verification report use generic paths (#188).
- The tracked timesheet binary is rebuilt with
go build -trimpath -ldflags="-s -w"(9.8 MB → 7.9 MB) and no longer embeds build-machine paths (#188). - The landing page links locally, keeps search inside the site, and documents the 1.6.2 docs and privacy work.
#Fixed
- The safety contract shows
password=<value>instead of a literal-looking password (#188). - Removed stale internal notes and a
/tmpreference from the landing page source (#188).
#Verification boundary
- Local validation covers 1405 Vitest tests (52 files), 331 YAML scenarios, 18 dedicated harness checks,
npm run typecheck, registry validation, skill validation,npm run docs:check,bash -n install.sh, andnode --checkon the TUI installer. - A full internal crawl of the generated site resolves every link and anchor; 32 published files were re-scanned for personal data and credentials and are clean.
- No npm package is published. Git history and the
v1.6.1tag still contain the pre-fix installer path; this release makes the newest downloadable artifact clean without rewriting history.
#1.6.1 (2026-10-26)
#Added
feature-inlineroute with a conditional ASSESS gate (#180): the default standard-feature route runs DECIDE → BUILD → VERIFY and keeps the Intent + Expectations contract. A deterministic entry gate selectsskip(terminal DECIDE before BUILD),assess(one bounded ASSESS writes the canonicaldecision), orescalate(the formalfeatureroute keeps DECIDE + PLAN). ASSESS here returns strategy, scope, affected areas, risks, and unknowns — never a functional spec.- Bounded Context Manifest (ICE) (#181):
odf_context_manifestbuilds one read-only, reference-only manifest at entry withredundancy,assessment_gate, andexpectations_refincluded inmanifest_digest, and forwards it unchanged to ASSESS and every BUILD batch. Redundancy is a gate signal forfeature-inline, not a blocking user question. - Decision-quality evaluation (#171–#173):
odf-evaluation decisionsreports routing quality against golden trajectories; a local decision review at archive/verify records a human label; the report adds human/judge agreement, period comparison, a review cadence, and improvement proposals. A null judge verdict is treated as unavailable, never as agreement. - Persisted stage handoff (#142):
odf_workflow_status.next_handoffderives the next stage role's inputs from the route, selected store, and persisted artifact references so the orchestrator never rebuilds them from result prose. - Safe stop classification (#144): every
blocked/failedenvelope carriesstop_disposition(kind,user_action_required,automatic_recovery,reason,next_action). Unknown reasons fail closed asunclassified; child-reported dispositions cannot weaken the deterministic class. - Project-scoped activation (#151, #163):
.odf/project.jsonmarks an initialized Odoo project, re-scanning the same root is idempotent and preservesinitialized_at, and activation created after runtime boot printsODF runtime reload required:instead of suggesting a reinstall. - Native delegation lifecycle (#139, #140, #161, #162): child sessions bind to the parent, agent, model, workspace, and prompt digest; parent cancellation aborts the child and settles the attempt as failed;
odf_delegation_late_seal_preparerecovers an expired original token through a ten-minute, single-use capability; seal failures report a precise reason instead of a generic block. - Agent Skills validation (#182):
scripts/odf-skill-validate.js(npm run validate:skills) validates frontmatter, name/directory parity, description limits, path containment, and the compact-rule contract, and runs in CI. - Route/stage contract matrix (#169):
odf-plugin/odf-route-contract.test.tswalks every route, transition, stage/role, and artifact/gate requirement;docs/route-contract.mdmirrors it. - Boundary hardening (#145, #153, #155, #157): evidence and local security hardening, exact cross-root resolution, blocked absolute traversal destinations, rejected prose-redirect bypasses, and recoverable aborted launches.
#Changed
- Canonical status only (#164–#167): removed the legacy compatibility layer.
odf_workflow_statusno longer emitsphase,artifacts,applyProgress,lastUpdated, orlegacy_phase; the legacy state read path is gone, artifact-only changes reportstate_kind: noneand stay non-resumable, and legacy launch tokens are rejected instead of upgraded. Only theroute.legacy_phasesalias survives, for bind comparison. - Centralized artifact vocabulary (#141): canonical artifact names, aliases, route completion alternatives, and OpenSpec discovery stems live in
odf-artifact-contract.ts; store values and subsets live inodf-artifact-stores.js. - Strict VERIFY completion (#170): VERIFY completes only through a terminal
verify-report. - Delegation API on canonical stages (#168): the public delegation contract accepts the canonical stage plus a role for the composite stages only.
- Canonical status discovery (#174): active-change resolution reports
none/unambiguous/ambiguous/incompleteand surfaces Engram errors instead of swallowing them. - Delegate hardening (#175, #178, #179): bounded workspace, artifact references, and task errors; blocked envelopes preserve the resolved agent, skills, profile, and Policy Gate; Policy Gate blocks use a stable reason; nested Expectations inputs are bounded; profiles are validated and labeled advisory; skill, registry, receipt, and status previews refined.
- Skills (#182): all 87
compact_rulesregenerated from each skill's own rules (150–600 characters, complete sentences, no banners, no duplicates); selection breaks score ties by registry order instead of prompt length; five OCA tool skills,karpathy-precision, and the OCA index frontmatter corrected. - Documentation (#146, #183): artifact store persistence clarified; the protected-
mainbranch → PR → auto-merge workflow documented inAGENTS.md.
#Removed
odf_status(#165) — useodf_workflow_status.- The legacy dual-read compatibility layer, legacy status projection, and legacy state read path (#164, #166, #167).
odf_notebooklm_lookupand thenotebooklm_sourcesregistry map (#176); NotebookLM enrichment, when used, stays external to ODF.
#Fixed
- Cancellation and aborts: parent cancellation propagates to delegated children, cancelled delegations stop cleanly, and aborted children bind with a precise seal reason (#149, #159, #161).
- Late seal verifies the prepared prompt without an assistant result (#162), and aborted native children no longer dead-end recovery (#159).
- Safety: absolute traversal destinations are blocked (#155), prose-redirect bypasses are rejected (#157), false cross-root blocks no longer stop valid work (#153), and evidence/local security is hardened (#145).
- The registry fixture resolves from the repository root, so the suite no longer depends on the invocation directory (#177).
#Verification boundary
- Local validation covers 1370 Vitest tests (50 files), 331 YAML scenarios, 18 dedicated harness checks,
npm run typecheck, registry validation, andnpm run validate:skills. - No npm package is published; the release is the tagged pack plus the GitHub release. Odoo-specific end-to-end validation and efficacy claims remain ODF 2.0 gates.
#1.6.0 (2026-10-09)
#Added
- Diagnostics and safe recovery: bounded causal timelines, truthful canonical workflow status, fail-closed recovery guidance, and conversational exploration/continuation routing (#136).
- Opt-in online feedback:
/odf-feedbacksubmits only an explicit 1–5 rating and aggregates with host-supplied usage after preview and confirmation; HTTPS endpoint, 1–30-day receiver-retention contract, and no prompts, free text, durable queue, or retries (#137). - Repeatable offline evaluation journeys for diagnostics, recovery, and conversational workflows (#136).
#Changed
- Expanded the plugin to 31 tools and the command set to 23; documented the online feedback privacy and retention boundary.
#Verification boundary
- CI on Node 22 passed for PR #137. Release-candidate validation passed 1,182 Vitest tests, 331 YAML scenarios, 18 harness checks, typecheck, and registry validation.
- Online feedback is user-rated telemetry, not benchmark evidence. This release makes no efficacy claim and does not include an ODF-hosted collection service or npm publication.
#1.5.1 (2026-10-03)
#Fixed
- Workflow persistence and recovery: Policy Gate writes fail closed, ARCHIVE retries repair partial OpenSpec/Engram writes, and replanning invalidates downstream artifacts (#104–#106).
- Native delegation safety: restore V2 delegation, guard direct tool calls, check seal context before child launch, and bind recovery to the exact idle child; handle multiline prompts, V2 result text, and transport banners safely (#86, #89, #93, #100, #101, #107, #108).
- Canonical workflow artifacts: terminal BUILD behavior is explicit, and nested assessment artifacts and block-YAML status maps are recognized (#87, #91, #102).
- VERIFY evidence is command-aware; warning is terminal only for a valid VERIFY report; a BUILD start proof does not replace persisted post-child validation evidence (#109, #110, #112).
- OpenCode V2
/odf-newnormalizes sentence-final punctuation and binds workflow initialization to the active session workspace.
#Changed
- Preflight defaults, strict input validation, and the runtime/specification contract are synchronized (#111).
- Workflow route, recovery, archive, and metrics guidance reflects the merged behavior (#85, #94, #96, #97).
- Lifecycle metrics correlate mixed-flow events and deduplicate mirrored stages (#98, #99).
#Verification boundary
- CI on Node 22 passed for the implementation PRs #104 and #106–#112, whose merged suite contained 1,050 unit tests, 330 YAML scenarios, and 18 harness checks. The 1.5.1 release candidate adds one V2
/odf-newregression case; its local validation passed 1,051 unit tests, 330 YAML scenarios, and 18 harness checks. - Odoo-specific release validation and end-to-end telemetry remain outside this harness patch release; ODF 2.0 readiness is not claimed.
#1.5.0 (2026-09-29)
#Added
- Native delegation (OpenCode V2):
odf_delegation_prepare+odf_delegation_sealrun a phase as a hostsubagentchild session — visible agent, description and live status — while every ODF gate stays plugin-side: boundedodf-tok-…tokens under.odf/(prompt digest, two-hour TTL, workspace containment), child-session binding checks, composite gates and a proof-backed replay of the authoritative delegate (policy gate, validation evidence, workflow commit, attempt settlement, failure receipts). The sealed envelope matchesodf_delegatefor identical inputs (delegate/seal parity matrix). - Native parallel BUILD:
odf_parallel_prepare+odf_parallel_seallaunch onesubagentper branch (background allowed) and run the authoritative aggregate scheduler: per-branch validation evidence, the parallel-join artifact, one BUILD commit and one aggregate receipt on failure, with per-branchtask_session_id. - Chokepoint guard: the V2
execute.beforehook blocks directsubagent/taskcalls from the orchestrator to registered ODF specialists without the prepared delegation marker; manual agent use from other sessions is untouched. - The plugin exposes 26 runtime tools.
#Changed
- Orchestrator and phase commands document the native single and parallel delegation flows, their recovery reasons, and the fast-lane / cross-domain boundaries.
- Native seals record one aggregate
subagentmetric (the replayed delegate metrics are suppressed), including join counts for parallel BUILD.
#Fixed
- Heavy phases: VERIFY gets the same 900000 ms timeout budget as ASSESS/QA-PLAN/DESIGN, and the orchestrator documents expected duration, child-session visibility (
ODF <phase> → <agent> · <change>,/sessionson the legacy path) and interruption semantics — interrupting aborts the child, settles the attempt as failed, applies the single transport relaunch, and/odf-continueresumes (#80). - Parallel BUILD recovery: a persisted join left
runningafter a host restart is recovered instead of dead-ending BUILD (#74, #75). - Legacy status: progress-bearing artifacts (
implement-progress,apply-progress,tasks,explore-progress,fix-progress) derive their state from content, so partial work renders asin-progressinstead ofdone(#73, #75). - Metrics: the entry-to-final-gate funnel breaks down per stage so the dominant bottleneck is localizable (#76, #77).
- Parallel scheduler tests use
waitFortimeouts above the vitest 1 s default and no longer flake under load (#78, #79).
#Verification boundary
- Local repository checks cover 998 unit tests (37 files), 325 YAML scenarios, and 18 harness checks; CI runs the same suite on Node 22.
- Native delegation is covered by the prepare/seal flow tests, the delegate-vs-seal parity matrix (composite, proof-backed, inner-failed) and the parallel BUILD end-to-end tests; the real Odoo VERIFY run is recorded as release evidence.
#1.4.0 (2026-09-28)
BREAKING — OpenCode V2 only. The plugin entrypoint no longer exports the V1
serverimplementation, and@opencode-ai/pluginis not part of the runtime graph. Packs installed from this release require an OpenCode V2 host: a V1 host will not register the ODF plugin.
#Added
- Native delegation visibility under OpenCode V2: child sessions carry a descriptive
ODF <phase> → <agent> · <change>title, the delegated agent is surfaced through tool progress while the phase runs, and the outer delegation envelope reportstask_session_id(#54, #56). - Source-authority
not_applicableevidence: non-view DESIGN/IMPLEMENT work can return a boundednot_applicableenvelope when the task names no concrete view/action XML ID orinherit_id/search_view_idrelation; concrete references still require the deterministicodf-toolkit lookup(#50, #52).
#Changed
- OpenCode V2 only: the entrypoint
plugins/odf-delegation.tsnow default-exports the officialPlugin.define({ id, setup })shape. The V1serverexport,OdfDelegationPluginandcreateODFRuntimeHookswere removed along with their V1 contract fixtures. - Runtime code no longer imports
@opencode-ai/plugin. The sharedtoolhelper moved toodf-plugin/odf-tool.ts(identity function +zodschema namespace), so the plugin graph carries only the host-provided@opencode/pluginplus the declaredzodandyamldependencies.@opencode-ai/pluginand@opencode-ai/sdkare now devDependencies, used for types and the V1/V2 schema-parity fixtures.
#Fixed
- Registry/telemetry warm-up used to live inside the retired V1
serverentrypoint, so the V2 host silently lost it. It is nowstartOdfRuntime(), awaited bysetupODFV2: metrics flushing, the skills/permissions cache refresh, unregistered-skill discovery and the learning loop all run under OpenCode V2. - OpenCode V2 now injects the one-shot context-pressure notice through the
session.contexthook, restoring parity with the retired V1experimental.chat.system.transformseam. install.shinstalls dependencies before exposing the plugin entrypoint, and reminds you to restart the OpenCode service afterwards (--restart-service/ODF_RESTART_SERVICE=1to do it immediately). A plugin that fails once staysfailedinside a running service until it restarts — this was the root cause of the plugin never loading after a fresh install.- Three new installer tests cover the dependency/plugin ordering, the default no-op dry run and the opt-in restart flag.
- Config-dir resolution no longer ignores
XDG_CONFIG_HOMEand no longer depends on the project launcher: a single resolver (scripts/lib/config-dir.js) ordersODF_CONFIG_DIR→ the pack the running module ships in (when it carriesodf-registry.json) →$XDG_CONFIG_HOME/opencode→~/.config/opencode, and the five CLI copies of that logic delegate to it. A pack installed under<project>/.opencoderesolves itself, so runningopencodedirectly there reads the right registry. The README'sXDG_CONFIG_HOME resolutionclaim holds again, the/odf-*prompts defaultPACKto the same order, and the YAML suite now passes withODF_CONFIG_DIRunset instead of reading the installed registry instead of the checkout. - The installed pack is self-verifiable:
tsconfig.pack.jsonships and installs as bothtsconfig.jsonandtsconfig.pack.json, so/odf-health --fullcan typecheck the installed pack (#32, #33). - Engram persistence is project-scoped and store-aware end to end:
odf-initreadback no longer depends on the working directory, the plugin resolves one project identity, and archive/metrics respect the selected store (#37, #38). odf_healthreports why the V2 context session is unavailable instead of a bare failure (#34), and an interrupted firstodf_healthstays retryable instead of dead-ending/odf-newwithworkflow-start-unauthorized(#35, #36).odf_delegateblocks every path inside the installed ODF pack with symlink-resolved containment: the pack root, a symlinked config dir, and pack subdirectories (#42, #45).- The ODF Result text parser is section-authoritative: it prefers
## ODF Result, parses nested bullet fields into objects (prototype-pollution safe), coercestrue/false/null, accepts the dash-less bold form, and no longer lets an unrelated fenced JSON block replace the result (#51, #53). - Workflow recovery: re-entering an archived stage reopens the archived state (#63), block-YAML
completed_canonical_stageslists parse correctly (#65), Engram state resolution reads local state before Engram (#66), and orphan workflow locks are recovered instead of dead-ending delegation (#67). - Delegation cancellation bounds the child abort wait after a timeout (#64), and the TUI installer reports a degraded install honestly instead of claiming success (#68).
- The installer only exposes the plugin entrypoint once runtime dependencies resolve (#47).
#Verification boundary
- Local repository checks cover 970 unit tests (35 files), 325 YAML scenarios, and 18 harness checks; CI runs the same suite on Node 22.
- This release is OpenCode V2 only (see the breaking note above); a V1 host cannot register the plugin.
#1.3.1 (2026-09-24)
#Fixed
- Installer:
curl | bashno longer dies silently — non-interactive stdin continues with an explicit notice (the TTY prompt is kept and tolerates EOF); regression tests cover the piped script and stdin at EOF (#17). - OpenCode V2 entry authorization: the prompt hook detects the expanded
/odf-newcommand document, and the V2 adapter shares the entry-authorization maps between the loop guard and the registered tools, so the capability minted afterodf_healthreachesodf_workflow_bind(#18). - Stale IMPLEMENT attempts: audited
odf_workflow_override action=settle-attemptappends a terminal settlement (preserving the running record and the override audit log) and requiresconfirm_no_active_runplus a human-approved reason; it refuses attempts still active in the runtime, unsafe ids, and already-terminal records (#9). - BUILD/VERIFY starts accept the completion-shape proof after an audited BUILD re-entry instead of rejecting it as a phase mismatch;
odf_workflow_advanceaccepts an explicitnullcandidate_stage for initial transitions and documents the start convention (#28). - TUI installer parity with
install.sh: copiesodf-plugin/,policies/, andpackage.json(sonpm installruns), syncs the stale-plugin cleanup list, and covers uninstall/backup; tool, command, and skill counts in the docs match the registry and are guarded by consistency tests.
#Added
- GitHub Actions CI with test-gated auto-merge: typecheck, unit tests, YAML scenarios, registry validation, and diff check run on every PR; passing same-repo PRs squash-merge automatically (Node 22, actions v7).
#Verification boundary
- Local repository checks cover 900 unit tests, 325 YAML scenarios, and 18 harness checks; CI runs the same suite on Node 22.
- ODF 2.0 remains gated on representative Odoo validation, canary/cohort evidence, and end-to-end
/odf-new//odf-fixtelemetry; this release does not claim ODF 2.0 production readiness.
#1.3.0 (2026-09-21)
#Added
- Fast-lane execution and V2 transport, including SDK child-session transport, shadow-route prediction, context manifests, and bounded implementation routing.
- Migration assessment routing, expanded agent and entry contracts, human Expectations, and stronger workflow and policy enforcement.
- Governance profiles and checks, provenance and disclosure updates, lifecycle and trace observability, installer/project-scope improvements, and resilience and ephemeral-subject validation.
#Verification boundary
- Local repository checks cover 844 unit tests, 154 YAML scenarios, and 17 harness checks.
- ODF 2.0 remains gated on representative Odoo validation, canary/cohort evidence, and end-to-end
/odf-new//odf-fixtelemetry; this release does not claim ODF 2.0 production readiness.
#1.2.1 (2026-08-23)
#Added
- Gate de precisión:
odf-toolkit lookup(IDs de vista/modelos/campos en el source local con file:line) yverify-refs(cada ref=/model= del módulo debe resolverse; exit 1 si no). Reglas "nunca inventar IDs" en odoo-sources, odf-design, odf-implement y backend engineer; el orquestador reenvíaodoo_source_root. - README reescrito: estado honesto, matriz de dependencias/degradación, pipeline, CLIs y gate de precisión.
#Fixed
- TUI: Enter en
(Y/n)confirmaba en vez de cancelar; listener raw que se tragaba el Enter siguiente; guard no-TTY con hint de automatización.
#1.2.0 (2026-08-22)
#Added
execution_mode: auto(piloto automático): auto-continuación de fases enok/warning, deteniéndose solo en gates obligatorios (health, preflight, Expectations, Policy Gate, evidencia, VERIFY, receipts)- CLIs deterministas:
odf-project-scan(config completa del entorno Doodba: addons.yaml sources, compose, linting, git, CodeGraph, matriz de dependencias; persist verificado con checksum/diff/exit codes;--deepindexa repos activos) yodf-toolkit(context/state/result/resolve/evidence/metrics/manual-evidence/redundancy) - Triage mejorado (ICE): señales de riesgo desde module/domain +
pii, claridad de intent con pregunta agrupada,standard-configsin hechos,known_modulesdesde odf-init, signals/clarity auditables - Redundancy pre-check en
/odf-new(implementaciones existentes +odf-learned/{project}como base de rechazos) - Ejecución manual de tests en VERIFY (
manual-evidence,executor: user-manual) - Completion criteria en odf-assess/design/implement/verify; smell baseline Fowler para el lens de readability; seams-first y anti-patrones de tests en implement/tdd; feedback-loop-first + redacción en odf-fix; handoff con Suggested Skills
- Descubrimiento de artefactos OpenSpec anidados (
design/design.md,qa-plan/plan.md, ...)
#Fixed
- Agente DESIGN/PLAN bloqueado por
design_closed: "true"(string): coerciónasBooleanen el validador - Resolver de agentes elegía frontend por el token genérico "odoo": scoring por coincidencias + stop word
odf-initcolgado buscando el pack: ruta determinista$ODF_CONFIG_DIRsin filesystem search- Scan degradado con
--reporelativo (resolución contraodoo/custom/src) + guarda anti-sobrescritura - Persist de config truncado por el límite de ~50KB de Engram: persist compacto + readback verificado
- Falso positivo de seguridad con el guard obligatorio de base de datos (masking de prohibiciones)
- Hybrid BUILD/VERIFY escribía solo Engram: ahora escribe OpenSpec (autoridad) + espejo Engram
odf-qahardcodeabamem_save: ahora persiste en el store seleccionado conartifact_ref
#1.1.0 (2026-06-18)
#Added
- Orquestador conversacional (
agent/odoo_orchestrator.md) con preflight gate y máquina de estados - Comandos nativos
/odf-new,/odf-continue,/odf-status,/odf-exploreregistrados enodf-registry.json - Plugin
odf-delegation.tsinvoca la API nativatask()de OpenCode con fallback determinista install.shidempotente con--yes,--dry-run,--force, backup con timestamp y soporteODF_SOURCE_DIRpackage.jsoncon dependencias, scripts de test y peer dependencies del plugin SDK- Validación de Node.js 18+ en
install.sh - Resolución de rutas relativas en
odf-registry.jsoncon flaguse_relative_paths - Metadatos de paquete en
odf-registry.json(name, version, repository, dependencies) scripts/odf-registry-validate.jspara verificar que todas las rutas registradas resuelven- Helpers de preflight y orchestrator en
scripts/lib/con tests unitarios - Parser CLI mínimo en
scripts/odf-cli.jspara los comandos nativos - Tests unitarios con Vitest (92 tests) y escenarios YAML (118 aserciones)
#Changed
- README actualizado con instalación via
./install.sh, referencia de comandos nativos y mención del orquestador/preflight - Versión del proyecto a 1.1.0 (VERSION, package.json, odf-registry.json, install.sh)
#1.0.0 (2026-05-14)
#Added
- 31 skills organizados por categoría (ODF, OCA Governance, OCA Style, Patterns)
- 12 agentes especializados en desarrollo Odoo
- Plugin
odf-delegation.tscon auto-refresh, cache, métricas, y learning loop - Pipeline completo: ASSESS → QA-PLAN → DESIGN → IMPLEMENT → VERIFY
- Skill Registry CLI (
/odf-registry-refresh) - Multi-profile switching (
/odf-profilelist|switch|create|delete) - Backup & Rollback (
/odf-backupcreate|list|restore) - Skill version tracking (
/odf-skill-log) - Agent Observatory (
/odf-metrics) con delegación metrics + learning loop - Strict TDD mode (
/odf-tddon|off) - Chained PRs para PRs >400 líneas
- PR Size Budget check (
/odf-pr-size) - Issue-First workflow check (
/odf-issue-check) - Health Checks (
/odf-health--quick|--full) - Uninstall Flow seguro (
/odf-uninstall) - 36 test cases para resolución de skills y agentes
- OCA commit messages con 12 tags y formato completo
- OCA work-unit commits
- Judgment Day adversarial review (3-pass: reviewer, maintainer, attacker)
- Auto-descubrimiento de skills en subagentes
- Perfiles de modelo: default (deepseek-r1 + kimi-k2.6), cheap (kimi-k2.6)
#Changed
- Todos los skills restructurados al estándar gentle-ai (180-450 tokens)
- Registry convertido a formato named profiles
- Plugin de 766→1044 líneas con metrics + learning loop
#Fixed
- Rutas relativas de skills → absolutas (34 archivos)
- Permisos de agentes (12 agentes con acceso completo)
- mgrep → fff/fff_grep en todos los skills
#0.1.0 (2026-04-01)
#Added
- Initial ODF workflow with 5 phases
- Basic OCA compliance skills
- odf-registry.json with 22 skills
- ODF delegation plugin