Spec-Driven Development for Odoo

⚡ Summary

dsh-odoo-sdd turns DeepSeek Harness into a specification-driven (SDD) Odoo development pipeline. Two ideas hold it together:

• Closed feedback loop — the agent installs and upgrades modules, reads the server traceback and retries against a real, running Odoo instance. The plugin never starts Docker or odoo-bin: you point it at an instance you already have (dev/staging) through a gitignored .env, and the tools speak plain JSON-RPC.
• Pipeline safety — every phase persists to disk, the gates are fail-closed on an explicit APPROVED marker, three consecutive failures force a root-cause diagnosis, verify/fix iterations are capped, stop.md halts everything, and verdicts are honest: a failed verification is persisted as FAILED and can never be reported as success.
• No change without a spec — a request that arrives after the pipeline closed ("now also change X" in the same chat) is a new change, so it gets its own (small) spec or an explicit waiver from you. The guard covers instance mutations and source edits alike, and says which of the three ways out is available instead of quietly editing.

[!NOTE] What it is not: an infrastructure orchestrator, a credential manager over chat, or an auto-committer. It writes no commit and never asks you for a password.

Requirements

🔭 How it works

graph TD
    A(["Idea or request"]) --> C1

    subgraph P [SDD protocol - fail-closed gates]
        C1["1 CLARIFY<br/>interview and security questions"] --> R2["2 READ_SPEC<br/>immutable spec.md"]
        R2 -->|APPROVED| A3["3 ARCHITECTURE<br/>models, views, security, test plan"]
        A3 -->|APPROVED| W4["4 WRITE_CODE<br/>module source and OCA docs"]
        W4 --> V5["5 VERIFY<br/>static, install, RPC, UI"]
        V5 -->|PASSED| D9(["handoff.md - DONE"])
        V5 -->|FAILED| F6["FIX_LOOP<br/>root cause, max 5 iterations"]
        F6 --> V5
    end

    subgraph L [Closed loop against a real instance]
        W4 -.-> M7["odoo_module install or upgrade"]
        M7 -.->|traceback| E8["odoo_errors"]
        E8 -.-> F6
    end

    style P fill:#1e1e2e,stroke:#89b4fa,stroke-width:2px,color:#cdd6f4
    style L fill:#181825,stroke:#a6e3a1,stroke-width:2px,color:#cdd6f4

The specification is the single source of truth and it is immutable: the code adapts to the spec, never the other way around. Gates are human-answered by default, and can be delegated to a human-proxy agent when you choose the autonomous mode.

✨ Key features

• 🎯 Spec before code, always. spec.md carries numbered acceptance criteria; DONE is unreachable without a persisted PASSED verdict on disk.
• 🔁 A real feedback loop. odoo_module install returns the server's own output or traceback; odoo_errors reads ir.logging; failures become a persisted FAILED verdict instead of a hopeful summary.
• 🧾 Not only modules. The same machine also runs a functional spec (mode=functional): configure a live instance and load data in human-approved batches, with Odoo's own importer for CSV/Excel, and close with a runbook a person can repeat. → The functional path
• 🔒 Credentials are not consent. The first socket of a project needs an explicit human authorization bound to url + db + user (.sdd/grants.json).
• ⏪ Rollback that tells the truth. Checkpoints snapshot files and journal every odoo_execute pre-image, and a restore always reports the files created after the checkpoint. What it cannot undo, it says so.
• 🧱 Documentation as a gate. odoo_docs produces the OCA readme/ fragments, the Apps index.html and a mandatory changelog entry — and it works on an existing module with no spec, no phase and no instance.
• 🧪 Instance-free static layers. odoo_validate (structure + ACL coherence) and odoo_security_scan (raw SQL, sudo(), auth="none", QWeb t-raw…) give findings with file:line before anything is installed.
• 🧑⚖️ Policy the model cannot relax. Allowlist, guards and delegation mode all require native human approval to change.
• 🤖 Supervised or autonomous. The same pipeline runs with a human answering each gate, or with a human-proxy agent and unattended goal rounds until DONE or BLOCKED.
• 📁 Specs where you want them. Keep them beside each project, or collect every project's specs in one folder you can search.
• 🖥️ Linux, macOS and Windows. Paths, atomic writes and .env permissions are handled per platform and tested on Windows in CI.

🚀 Quick start

1. Install into a profile

dsh plugin --profile web add dsh-odoo-sdd

That installs the published package from the npm registry — no clone, no build, nothing to compile on your side. dsh plugin is a thin pnpm forwarder: it runs pnpm add inside the profile directory and then registers the bundle (dsh.profile.bundles). Two consequences worth knowing:

• pnpm must be on your PATH (dsh plugin reports it when it is not).
• Any pnpm spec works, so you can pin a version: dsh plugin --profile web add dsh-odoo-sdd@0.12.1.

Prefer plain npm — a project that depends on the plugin, or a CI job?

npm install dsh-odoo-sdd        # 0.12.1, published with a provenance attestation

[!IMPORTANT] Restart DSH and refresh the browser tab after installing. Client-side changes (the Odoo SDD settings panel) load from the installed package.

Working on the plugin itself? Install the checkout instead. lib/ is build output and is not committed; npm install builds it through the prepare hook, and you can always ask for it explicitly:

git clone https://github.com/fhidalgodev/dsh-odoo-sdd && cd dsh-odoo-sdd
npm install          # devDependencies: typescript, then prepare builds lib/
npm run host:deps    # optional peers, needed to compile (no-save)
npm run build        # emits lib/ — required, package main is lib/index.js
dsh plugin --profile odoo add .

[!NOTE] A git install runs that prepare build on the consumer's machine, and pnpm blocks dependency build scripts until they are allowed: the command tells you the exact key to add under allowBuilds in the profile's pnpm-workspace.yaml. A registry install needs none of that — the tarball already ships lib/.

dsh plugin add records the bundle in the profile's package.json (dsh.profile.bundles), and the package ships a Cordis patch (cordis.patch.yml) that inserts its own row — so there is no manual composition step. dsh --profile <name> --dump-config prints the composed tree without booting anything.

2. Give it credentials (once per project)

Ask the agent to run odoo_setup mode=check. It writes a secret-free scaffold and you fill the password yourself:

odoo_setup mode=interactive url=http://localhost:8069 db=odoo_dev username=admin
# then fill ODOO_PASSWORD (an Odoo API key is recommended) in the printed file
odoo_setup mode=authorize   # asks YOU, once, to authorize that exact target

Or do it by hand — the plugin looks for the first of these that exists:

Several targets in one project. A workspace that needs a local CE server, a staging EE server and a client's instance no longer overwrites its only .env: each target gets its own file under .sdd/instances/, and one is active.

odoo_setup mode=instance instance=list                      # what exists, non-secret identity
odoo_setup mode=instance instance=add name=staging url=https://stg.example.com db=stg username=ci
# fill the secret in .sdd/instances/staging.env by hand, then:
odoo_setup mode=authorize name=staging                     # grants THAT target
odoo_setup mode=instance instance=use name=staging          # activate it FOR THIS SESSION
odoo_setup mode=instance instance=remove name=staging       # needs confirm_destructive=true
odoo_setup mode=revoke name=staging                         # drops only that target's grant

The active target belongs to the SESSION, not the project. Each chat keeps its own pointer (.sdd/instances/active-<sessionId>.json), so two sessions on one project can work in two environments at once — one on staging, another on a client's server — without either moving the other.

A session that has not chosen is ASKED, never given a default. The first Odoo operation in a new chat refuses and returns the question, with the available targets and their non-secret identity:

This session has no environment chosen yet, and this project defines 2 instance(s):
  - argelia: https://… db=argelia user=admin
  - farmago: https://… db=farmago user=admin   (the project's last used)
ASK THE DEVELOPER which one THIS session should use, then record the answer:
  - an existing one: `odoo_setup mode=instance instance=use name=<name>`
  - a new one: `odoo_setup mode=instance instance=add name=<name> url=… db=… username=…`, …

Inheriting the project's last-used target is convenient exactly once and dangerous afterwards: another session switching environments would silently redirect a working one, and its tool answers would still just say OK. One question per session buys that away. .sdd/instances/active.json is kept only as the suggestion shown in the question. A project with no named instances (just .sdd/.env, the single-target layout) is never asked, and requireInstanceChoice: false restores the old inheritance for anyone who prefers it.

Authorization is per target (url+db+user), so two instances on the same server are two grants. authorize takes the target's NAME, which is what makes switching recoverable: grants expire (12 h), and requiring activation before authorization used to be a closed circle — use demands a live grant for the target, while authorize only ever saw the active one. Naming it breaks the circle: authorize staging without leaving main.

Activating a target that has no live grant is still refused — the pointer decides where mutations go, so it cannot be switched to something nobody approved. With several instances and none active, every connection tool refuses instead of picking one by order, and an old .sdd/.env keeps working untouched as default until you choose to move it yourself.

mkdir -p ~/.config/dsh-odoo-sdd && cd ~/.config/dsh-odoo-sdd
cp <plugin>/.env.example .env && chmod 600 .env
# fill: ODOO_URL, ODOO_DB, ODOO_USERNAME, and ONE secret:
#   ODOO_PASSWORD=<account password>   or   ODOO_API_KEY=<api key>

The secret has two accepted names. ODOO_PASSWORD and ODOO_API_KEY are both read, and the API key is the recommended one: Odoo accepts it wherever it accepts a password over RPC (Settings → Users → API Keys, and use a key with the global scope). If both are set, ODOO_PASSWORD wins and the plugin reports that the other was ignored, so a rotated credential cannot go unnoticed.

There is one place an API key does not work, and it is Odoo's rule, not this plugin's: odoo_session and odoo_import authenticate a web session, and Odoo authenticates interactive logins with interactive: True while only consulting the API-key table otherwise. Configure an account password if you need those two; everything else works with the key.

Which API the plugin speaks

On 19+ the plugin uses the modern JSON-2 API: no uid round-trip, named parameters validated by Odoo itself, read-replica routing for @api.readonly methods, and errors that arrive as an HTTP status with a structured body. It falls back to classic JSON-RPC automatically in three cases: the route is missing, the server predates it, or the credential cannot be used there at all. That last one matters: JSON-2 authenticates with Authorization: Bearer only, so a target configured with an account PASSWORD answers 401 on every call — and a 401 means the request never ran, so serving it over the other transport cannot double-apply anything. A call the server actually PROCESSED and refused (403, 422, a domain error) is never re-sent. Pin the choice with odooApi: auto | json2 | jsonrpc in the panel or with odoo_config; json2 reports a missing route instead of degrading quietly.

Business actions (action_*, button_*, do_*) always use execute_kw: JSON-2 has no positional-argument form, and inventing a position→name mapping for a method whose signature the plugin does not know is exactly the kind of silent mis-send it refuses to make.

[!WARNING] Never paste a password into the chat, a spec, a commit or an issue. The plugin refuses a group/world-readable .env, redacts the secret from every tool output, and stores session cookies in .sdd/session.json (mode 600) without ever returning them to the model.

3. Ask for the thing you want

Implement a sale order approval module for Odoo 19, using the SDD workflow.

The agent picks up odoo-sdd-workflow from the session skill catalog and follows the protocol. If you want to be explicit — or you want to be sure the full instructions are loaded — start your message with /odoo-sdd-workflow.

For configuration and data work on a running instance, ask for that instead:

Set up company, taxes and chart of accounts in my dev instance, then import
this customers.csv — functional SDD, dev environment, no production.

That selects odoo-functional-sdd (or /odoo-functional-sdd explicitly) and the functional spec mode described below.

🧭 The five phases

Are the strings translated? (translations)

CLARIFY asks it, next to the licensing question, and the answer is recorded on the spec — not as a global setting, exactly like the edition. One workspace can hold a client project in Venezuela and an internal fix that ships no languages at all.

sdd_phase operation=clarify spec_id=<id> mode=… licensed=… translations=["es_VE","es_PA"]

• Omitting translations means the work is not translated. That is a normal answer, so unlike mode and licensed it is NOT a fail-closed gate.
• The codes are gettext (ll or ll_CC: es_VE, es_PA, pt_BR, fr). A malformed one is refused while it can still be corrected, instead of becoming a file the server would never load.
• Declaring languages makes odoo_i18n part of the plan and puts the matching acceptance criterion in test-plan.md: "i18n/<lang>.po exists and no exported term is left with an empty msgstr" — which odoo_i18n operation=check verifies.
• sdd_phase status reports them, so "did we translate this?" is answerable without opening state.json.

In ARCHITECTURE the agent also asks about the things that are cheap to decide early and expensive to discover late: extra view types beyond form/tree (including a search view for how a model is searched — custom filters, favorites), reports (PDF via ir.actions.report/QWeb, SQL, CSV/XLSX, an external tool), web tours (onboarding, test, or none — with the asset bundle that loads them, because a tour no bundle loads never runs) and demo data (which files, and what for). Each one is answered explicitly — "form + tree only", "no reports needed", "no tours needed", "no demo data". Those are guide decisions: recorded in ## Views / ## Reports / ## Tours / ## Demo data and surfaced as warnings in sdd_phase status, non-blocking by design — the security model is the only fail-closed content gate. The version-by-version tour API, the HttpCase that executes a tour and the demo traps live in resources/references/tours-and-demo.md.

Per-spec artifacts (all on disk, resumable):

specs/<NNN>-<slug>/
├── spec.md · architecture.md · test-plan.md
├── verify-verdict.txt   # honest persisted verdict
├── state.json           # phase, failures, iterations
├── kb.json              # decisions, discarded options, blockers, diagnoses
├── docs-report.md · security-report.md
└── handoff.md           # written by sdd_handoff when the run closes

🧩 The functional path (configure and import)

Not every Odoo job is code. Setting up a company, its taxes, its users and its master data is configuration and data, and it happens on a live instance — where a wrong click is not a failed test but a real record. The same SDD machine covers it with a different middle phase and stricter closing rules.

graph TD
    C1["1 CLARIFY<br/>objective, instance, ENVIRONMENT"] --> R2["2 READ_SPEC<br/>spec.md, criteria, sources"]
    R2 -->|APPROVED| A3["3 ARCHITECTURE<br/>to-be process, batches, risks"]
    A3 -->|APPROVED| X4["4 APPLY_CONFIG<br/>discovery + approved batches"]
    X4 --> V5["5 VERIFY<br/>re-read the records, evidence per AC"]
    V5 -->|PASSED| D9(["runbook.md + handoff.md - DONE"])
    V5 -->|FAILED| F6["FIX_LOOP"]
    F6 --> X4

    style X4 fill:#1e1e2e,stroke:#f9e2af,stroke-width:2px,color:#cdd6f4

How a change reaches the instance. Nothing is written "to see what happens":

1. Discovery first, under its OWN approval: which models, which fields, how many records. Reads are not mutations, but an approved scope is what stops "just looking around" from turning into a change.
2. Plan: the design becomes batches. Each one declares its destination and environment, the version and capabilities used, company and context, the acceptance criteria it covers, its ordered operations, record identity, preconditions, expected result, risks, recovery and manual steps.
3. Approve: the human sees the exact batch and approves it through the native approval seam. The receipt is bound to the hashes of the spec, the design, the plan and the batch — change any of them and the approval is void.
4. Apply: one operation at a time, re-checking those hashes, persisting each operation's state before the call and after the result.
5. An unknown outcome is not a retry. A timeout after a mutation may mean Odoo already committed, so the operation is marked indeterminate, the batch stops and the run parks until a human reconciles it.
6. Close honestly: sdd_phase succeed demands an explicit pass per acceptance criterion, the security review is mandatory, and so is the runbook (who does it, in which company, prerequisites, the verified menu path, the steps with their field labels, the expected result, how to check it and how to undo it) — whatever the documentation policy says.

The environment is declared, never assumed. ODOO_SDD_ENVIRONMENT on the target says dev, staging or production. A plan that declares a different environment than the target is refused (environment-mismatch), an undeclared target asks for it (NEEDS_ENVIRONMENT), and production additionally needs a declared backup reference plus its own approval. High-risk changes are proven in staging first.

Imports go through Odoo's importer, never through a hand-written parser:

odoo_import use=prepare file=... model=res.partner   # uploads, with its own approval
odoo_import use=preview   ...                        # what ODOO read: sheets, headers, sample
odoo_import use=map       ...                        # one decision per column, no blanks
odoo_import use=plan      ...                        # becomes an `apply` batch
odoo_functional operation=approve / apply            # the batch path, unchanged

The version contract is explicit (majors 10–19: file/import_id + JSONP on the old endpoint, ufile/id + JSON on the new one, do/execute_import for the apply), and a version outside the verified families is refused with what to investigate instead of guessed. A file that changed after the upload invalidates the mapping; a nextrow in the answer means the importer stopped mid-file and is reported as partial, never as success — and the rows it counted are never re-sent. The session cookie stays in .sdd/session.json (mode 600) and out of every tool result.

[!NOTE] The functional path needs an instance, and the importer needs a web session: run odoo_session once before odoo_import use=prepare.

🧰 The 16 tools

🎛️ Delegation mode

The pipeline starts by asking how much of it to delegate — recorded once per project with odoo_setup mode=autonomy decision=...:

[!TIP] In autonomous mode the brakes stay armed: stop.md, the iteration ceiling and the diagnosis ladder all remain, and BLOCKED is the only way the run pages a human. Connection grants are not covered by the switch — a human still authorizes the instance once.

🧠 Context engineering layers

🛡️ Safety, rollback and traceability

The pipeline assumes the agent will eventually be wrong, so every mutation path has a way back and a way to prove what happened.

• Credentials are not consent. Before any tool opens a socket towards the instance, a HUMAN must have approved that exact target. odoo_setup mode=authorize asks through the host's native approval seam and only the allowed-once outcome stores a receipt in .sdd/grants.json (0600, gitignored). The receipt is bound to a fingerprint of url + db + username, so changing any of them invalidates it; mode=revoke drops it. Without a live receipt, no client is handed out at all, so a configured .env cannot be used silently. In AUTONOMOUS mode there are no answerers, so the run reports NOT AUTHORIZED and parks — which is the point.

• The model cannot relax its own policy. Changing the allowlist or the policy guards (odoo_config mode=set) and switching delegation mode (odoo_setup mode=autonomy) each require a native approval.

• No change without a spec — or your explicit waiver. Whatever the request ("now also change X" in the same chat), a change needs a spec in a writing phase (WRITE_CODE, VERIFY, FIX_LOOP, APPLY_CONFIG) or a waiver you approved for THAT session. The gate covers both surfaces: instance mutations (odoo_execute, odoo_module, odoo_import prepare) and source edits through the host's write/edit tools. Writing the spec documents themselves (specs/, .sdd/) is never blocked — otherwise the way out would be blocked too. A small change is a small spec: mode=bug, one acceptance criterion, no design interview. If you would rather not specify it, sdd_phase operation=waive detail="..." records your words, needs your approval, and covers this session only: the next chat starts under the policy again, and every change made under it still lands in the KB as a decision. requireSpecForChanges: false is the human off-switch. Honest hole: the guard sees host tool calls, so a change made through bash (a heredoc, sed -i) is not gated — the pipeline is the path, not a jail.

  Where the question is asked (specPolicyScope, default "odoo"). A spec requirement is only meaningful where there is Odoo work, and the gate used to check one thing only: whether the path fell inside the session's root. So a plugin installed at profile level blocked writes in folders that have nothing to do with Odoo — notes, a pipeline of your own, anything. With "odoo", a file edit is gated only where the directory shows a sign of Odoo work:

  • .sdd/ holding real plugin state (config, specs, checkpoints, a waiver) — not a .sdd/ containing only audit.jsonl, which the audit listener writes for every tool call and which therefore means "something ran here", not "this is an Odoo project";
  • __manifest__.py in the root — the directory IS a module;
  • __manifest__.py one level down — the directory holds modules;
  • an odoo_* tool already used against that root in this session.

  An instance mutation is always gated: it is an odoo_* call, which is itself the evidence. stop.md still halts everything, adopted or not, because it is an emergency stop and not a scope question. "everywhere" restores the old blanket behaviour, and the refusal now names the signal that armed it rather than leaving you to guess.

  Three ways out, and all three work. (1) a small spec for this change, (2) continue the spec that already covers it, (3) ask the developer to waive — sdd_phase operation=waive detail="...". The third used to require a spec_id, which made it unreachable in the one situation it exists for: a directory with no specs, where you would have to create one to say you did not want one. A waiver is per project and per session, and spec_id is now optional for it (and for waive revoke=true) while every other operation still demands it.

• Checkpoint before mutating. With requireCheckpointBeforeMutation on (default), instance mutations are denied until sdd_checkpoint create has snapshotted the active spec — and denied outright before WRITE_CODE. The rule covers odoo_execute (CRUD and business actions), odoo_module install|upgrade, odoo_import use=prepare and odoo_functional operation=apply, which used to be missing from that classification. Snapshots skip symlinks (lstat) and never copy .env or key material.

• Fail-closed guard. An internal guard failure denies with a visible reason instead of allowing the call through. The guard is also a MOUNT requirement while either policy is armed: a host that exposes no tools.guard (or whose guard cannot be installed) makes the plugin refuse to mount with the reason and the way out, instead of staying up and looking protected.

• The canonical phase decides. Authorization reads the phase from specs/<id>/state.json; the pointer only says WHICH spec and checkpoint the session works on. A stale pointer can no longer authorize a change for a spec that has already gone BLOCKED.

• The pointer belongs to the session. It lives in .sdd/active/<sessionId>.json, so two chats open on one project no longer overwrite each other and neither can authorize its changes against the other's spec — the failure this scoping exists for. .sdd/active.json remains only as the project's last spec: a new session adopts it as a hint when it is fresh (< 12 h) and names a spec that still exists, and otherwise starts with no spec at all. Checkpoint snapshots stay shared (they are the project's), while which checkpoint is your rollback target is per session; dropping one clears the reference in every pointer that held it. Set adoptProjectPointerHint: false to remove the hint entirely: every session then starts with no spec until it declares one (sdd_phase status spec_id=…), which is the strictest reading of "one session, one spec".

• File rollback. sdd_checkpoint restore puts the snapshotted files back byte-for-byte; sdd_phase rollback returns the spec to the phase its MODE works in — WRITE_CODE, or APPLY_CONFIG for a functional spec — with the failure recorded, so the loop restarts from a known state. It refuses a checkpoint that belongs to another spec. A checkpoint snapshots the project tree, so with the central specs layout the spec documents (which live outside the project) are deliberately not part of it: the spec is the immutable source of truth, not code to roll back.

• Data rollback (best effort, and honest about it). Every create/write/unlink through odoo_execute records its pre-image in the checkpoint journal, stamped with the database and the destination (url+db+user) it was applied to; restore restore_data=true confirm_destructive=true replays it in reverse and refuses a journal from another destination. The replay runs under the company context the mutation used, converts read shapes into write values (many2one, x2many), marks each operation as it is compensated so a retry never repeats one, and reports the fields it could not restore (binary content, read-only or non-stored fields). Re-created records get NEW ids — the report says so. This covers data written through the plugin — not side effects of a module install/upgrade, which are not reverted at database level.

• Restore reports drift. restore always lists the files created after the checkpoint, so nothing is silently left behind; remove_created=true deletes them (inside the snapshotted roots only) to match the snapshot exactly.

• Documentation is a gate, not a footnote. ARCHITECTURE records the decision in ## Documentation, WRITE_CODE produces the OCA fragments + the Apps index.html + the mandatory changelog entry, and DONE is gated by documentationPolicy (required by default; optional and off available). What the plugin cannot do, it says so: gen-odoo-readme, towncrier, Ruff and pylint need a shell, so the fragments are the source of truth and compiling README.rst stays your step.

• Lifecycle: the plugin owns its state and can give it back. odoo_setup mode=purge prints a plan (what it owns and what it deliberately keeps) and deletes only after confirm_destructive=true plus native human approval. It never touches .env (your credentials), stop.md (your brake) or specs/ (your documents).

• Durable state. Pipeline state, KB, verdicts, grants and the journal are written with an atomic replace, and a corrupt file is quarantined next to the original instead of being overwritten: sdd_phase status reports the recovery.

• Traceability. .sdd/audit.jsonl records every tool call with outcome (ok / error / denied), duration and phase; sdd_phase status prints the logbook; sdd_handoff freezes the whole run into handoff.md.

• Emergency brakes. stop.md (at .sdd/stop.md or specs/<active>/stop.md) halts every tool; iteration ceilings and the diagnosis ladder route to BLOCKED instead of looping forever.

🔐 Security & network posture

• No phone-home. The plugin's ONLY outbound network calls go to the instance URL you put in .env. No telemetry, no update checks, no third-party endpoints.
• Transport guard (fail-closed). http:// is accepted only for loopback hosts (localhost, 127.x, ::1, *.localhost); anything else must be https://, otherwise credential loading is refused — plain http to a remote host would ship the API key in clear text.
• Secret containment. The secret is read once by credentials.ts and only injected into RPC parameters. Every tool output passes through two-layer redaction (known secret + generic password= / Bearer / api_key= / session_id shapes) and home-path masking (/home/user/… → ~/…) before being shown to the model or persisted to the KB.
• Session cookies never reach the model. odoo_session writes the cookie to .sdd/session.json (chmod 600) and returns only the path.
• No install scripts beyond the build. The only lifecycle scripts are prepare/prepack, which compile src/ into the shipped lib/ and do nothing else — no network, no postinstall, no shell. The two have opposite failure policies on purpose: prepare (which runs on an install) never fails one — without the devDependencies or the optional host peers it says what it could not check and emits without type checking so the plugin still loads — while prepack (which runs on a publish) refuses to package a build it could not typecheck. prepack is also what guarantees a published tarball is never missing the entry point its main promises (that failure was real: a clean clone packed 39 files and zero of them under lib/; so was its sequel, a prepare that typechecked during npm install and failed every CI job before the step that installs those peers could run).
• Host requirement declared twice, following dsh-market discovery conventions: engines.dsh and lockstep optional peer ranges on @deepseek-ai/{cordis,dsh-tools,schemastery}. On a host without the tools service the plugin refuses to mount with an explicit error instead of booting broken.

🖥️ Platform support

The plugin runs wherever DSH does and claims Linux, macOS and Windows — a claim the CI matrix tests rather than asserts (ubuntu-latest and windows-latest, on Node 20 and 22).

📁 Where specs live

The project root is the folder open in the current session, so it is not a plugin-wide setting. Spec documents follow it:

In the central layout each project gets its own subfolder with a .dsh-project-root marker, plus a hash suffix if two projects share a directory name — a foreign folder is never adopted. .sdd/ always stays with the project.

<projectRoot>/
├── .sdd/                       # plugin-owned, gitignored
│   ├── .env                    # credentials, single-target layout (chmod 600)
│   ├── instances/<name>.env    # one file per Odoo target (chmod 600)
│   ├── instances/active.json   # which target is in use
│   ├── config.json             # project configuration
│   ├── grants.json             # human authorization receipts
│   ├── session.json            # Playwright cookie
│   ├── audit.jsonl             # every tool call, sanitized
│   ├── setup-state.json        # onboarding + delegation decision
│   ├── active/<sessionId>.json  # THIS session's pointer (spec, phase, checkpoint)
│   ├── active.json             # the project's last spec (a hint for new sessions)
│   └── checkpoints/<id>/       # manifest + file snapshot + data journal
└── specs/<NNN>-<slug>/         # or the central folder

[!TIP] With several projects open, read the Project root: … [provenance] line that every tool result carries, or ask odoo_config mode=read — it returns the resolved root, its provenance and the effective spec directory.

⚙️ Configuration

Open Settings → Odoo SDD in the Web UI. Everything is editable there, plus a few copy-paste presets where you need them.

Host requirement: the Settings panel needs dsh >= 0.2.0-rc.1. That host removed the settingsScope service this panel used to bind to, and it now renders the form from the plugin's own Config schema (entry odoo-sdd). On an older host the section is absent and the plugin says so in the console; the tools and the pipeline keep working, and odoo_config mode=read|set edits the same values from the conversation.

# ~/.dsh/profiles/<profile>/cordis.patch.yml (optional: same fields, as a patch)
- insert:
    - id: odoo-sdd
      config:
        specsMode: project      # project | central
        specsRoot: ''           # absolute folder when specsMode=central
        specsDir: specs         # folder inside the project when specsMode=project
        executeAllowlist: []    # models odoo_execute may create/write/unlink
        methodAllowlist: []     # "model.method" pairs a functional batch may call (any model)
                                # the ad-hoc RPC needs no list: any public method + confirm_destructive
        communityRepoUrl: https://github.com/odoo/odoo
        enterpriseRepoUrl: https://github.com/odoo/enterprise
        communityRepoPath: ''   # local OS path; when set it OVERRIDES communityRepoUrl
        enterpriseRepoPath: ''  # same for enterprise
        odooApi: auto           # auto | json2 | jsonrpc (auto falls back on a 401)
        autonomy: supervised    # supervised | autonomous
        licensed: community     # community | enterprise (OCA is always searched)
        requireCheckpointBeforeMutation: true
        requireSpecForChanges: true     # every change needs a spec in a writing phase (or a waiver)
        specPolicyScope: odoo           # odoo (only where Odoo work is detected) | everywhere
        securityReviewRequired: true
        securityInterviewRequired: true
        auditAllTools: true
        maxCheckpoints: 5
        documentationPolicy: required   # required | optional | off
        documentationLanguage: ''       # empty = English unless the project says otherwise

[!IMPORTANT] There are two configuration stores, and the more specific one wins: Settings (user-wide, ~/.dsh/settings.yaml) and the project's .sdd/config.json (written by odoo_config mode=set, per project). If a key looks ignored after you change it in the panel, the project file is pinning it — odoo_config mode=read reports the effective values.

🤖 Model experience

The agent sees 16 tools with self-contained descriptions. Typical flow: sdd_phase init → security interview + odoo_connect → gated phases with APPROVED → sdd_checkpoint create → code → odoo_security_scan → odoo_module install → on traceback, odoo_errors + sdd_phase fail (which may force a diagnosis) → fix (or sdd_phase rollback) → re-verify → sdd_phase succeed → sdd_handoff → DONE. Tool responses are actionable text: server tracebacks, gate rejection reasons and remediation instructions.

The workflow skill is registered at mount time, so its name and description appear in every session's skill catalog automatically. The full instructions load when the model selects it (the catalog is summaries only) or when you type /odoo-sdd-workflow.

⚠️ Known limitations and deferred work

• Remote tests — without shell access to the instance there is no way to run --test-enable; the second verification layer is RPC/UI testing. Pending: an optional odoo_run_tests tool if you expose a test runner.
• Data rollback is best effort — the tests write to the connected database and there is no ephemeral cloning (by design: you provision and own the target). sdd_checkpoint reverses data written through odoo_execute, but a module install/upgrade is not reverted at database level. Use a disposable database.
• Static security scan scope — odoo_security_scan is rule-based over source text (no AST, no taint tracking), so it catches the common Odoo mistakes, not everything; it complements a human review, never replaces it.
• The change policy covers tool calls, not the shell — write/edit and the Odoo tools are gated; a file written through bash (heredoc, sed -i) is not, because the host exposes no after-the-fact inspection of what a shell command wrote. The policy makes the pipeline the path of least resistance and the exception visible; it is not a sandbox.
• Multi-instance — one target per project (.env). Pending: named instance profiles (dev, staging).
• Panel fields that are informational — autonomy and securityInterviewRequired are stored and reported, but the pipeline reads the delegation decision from .sdd/setup-state.json (set with odoo_setup mode=autonomy) and enforces the security interview through the ARCHITECTURE content gate. Tracked as pending work.
• No rich UI renderer — tool output is text in the DSH web GUI.

❓ Troubleshooting

🧩 Implementation internals

npm run typecheck   # tsc --noEmit
npm run build       # emits lib/ (required: package main is lib/index.js)
npm test            # server invariants + Cordis host contract + client bundle + README + functional/import
npm run test:package  # tarball contents (a file the runtime loads but `files` omits)

npm login                 # once; then `npm whoami` should answer
npm publish               # prepack runs `tsc` and packs the result
npm view dsh-odoo-sdd version   # verify what the registry actually has

⭐ Star History

Chart generated live by the star-history.com API.

🙏 Acknowledgments

Built for the Odoo developer community, this plugin rests on two ecosystems:

• Odoo Community Association (OCA) — the coding conventions, module layout and quality gates this pipeline enforces.
• DeepSeek Harness (DSH) — the plugin architecture (Cordis tools/plugins, skills, subagents) this plugin runs on.

Thank you to everyone who contributes patterns, reviews and ideas that shape the SDD workflow. Contributors:

📜 License

MIT © Franyer Hidalgo