mirror of
https://github.com/dtzp555-max/olp.git
synced 2026-07-19 09:45:07 +00:00
179b4707a7
Records OLP-side decision for the cross-project work OCP started in
ADR 0007 (interactive-mode execution pool to address post-2026-06-15
Anthropic billing split).
OPTION 3 — wait + port:
- No OLP code change to lib/providers/anthropic.mjs until OCP
ADR 0007 P0 experiment outcome lands (>= 2026-07-15).
- Avoid duplicating the P0 risk by running an independent OLP
experiment against the same Anthropic billing pool.
- If P0 confirms Transport A (stdio NDJSON) or Transport B (PTY)
bills as subscription rather than Agent SDK credit, port the
validated pattern to OLP at that time.
- If both transports fail, shelve this ADR; OLP Anthropic users
fall back to Agent SDK $100 / month credit OR shift to multi-
provider routing (Codex / Mistral) per Phase 1 design.
DECISION TREE recorded in § 3 so a future Phase 4 brief can act
mechanically once OCP P0 lands:
Transport A wins → Option 1 (parallel impl) likely
Transport B wins → Option 1 with PTY adapter (node-pty native dep
triggers engines-bump prior PR)
Both fail → Shelve ADR 0009
Unobservable → Extend wait
IMPLEMENTATION LANES (§ 4) — informational, not selected:
Option 1 — OLP parallel implementation in lib/providers/anthropic.mjs
Option 2 — Chain OCP as backend (OLP → OCP → Claude)
Option 3 — Hybrid (prefer OCP backend, fallback to local pool)
NO PHASE 4 D-DAY scheduled. This is a decision-record placeholder
ONLY. Phase 4 standing-autopilot grant ("Phase 4+ requires new
authorization") still applies. When OCP P0 lands, maintainer issues
explicit Phase 4 "go" naming this ADR to trigger implementation
selection + D-day work.
DOCUMENTATION:
- docs/adr/0009-interactive-mode-path-placeholder.md (new, ~200 lines)
- docs/adr/README.md index: ADR 0009 row added
- Cross-machine cc-rules memory (~/.cc-rules/memory/learnings/
ocp_adr_0007_interactive_mode_pool.md, committed in cc-rules
a16b775) bridges OCP ADR 0007 + OLP ADR 0009 so future Phase 4
planning sessions in either repo pull the shared context.
Test count: 601 → 601 (docs-only; no test or .mjs file touched).
AUTHORITY:
- OCP ADR 0007 (~/ocp/docs/adr/0007-interactive-mode-pool.md,
Draft 2026-05-25) — the triggering external work.
- OLP ADR 0001 (Project Founding) — the 2026-06-15 billing-split
motivation that this ADR reaffirms.
- OLP ADR 0006 (Provider Inclusion) — the anthropic plugin's tier
that this ADR would amend if/when implemented.
- CLAUDE.md release_kit overlay phase_rolling_mode (current_phase:
Phase 4) — this ADR explicitly does NOT consume a Phase 4 D-day.
- Standing autopilot grant — Phase 4+ requires new authorization;
this placeholder is a decision-tree pre-record, not Phase 4
implementation.
ALIGNMENT.md scope check: docs-only commit (new ADR + index update).
No provider plugin / entry surface / IR change.
Co-authored-by: dtzp555 <dtzp555@gmail.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Architecture Decision Records — OLP
This directory holds the OLP Architecture Decision Records (ADRs) — short documents that capture the why behind structural choices.
Read these before proposing governance, plug-in contract, IR, fallback, cache, or provider-inclusion changes.
Numbering
ADRs in OLP start at 0001 (the project's founding decision). OLP did not inherit the 0001 placeholder convention OCP used; the project starts on a fresh numbering line.
New ADRs increment from the highest existing number. Filenames are NNNN-<short-slug>.md.
Index
| ADR | Title | What it covers |
|---|---|---|
| 0001 | Project Founding | Why OLP exists (the 2026-06-15 Anthropic billing-split trigger), mission + non-mission boundaries, explicit supersession of OCP ADR 0005 "No Multi-Provider". |
| 0002 | Plugin Architecture for Providers | The lib/providers/<name>.mjs plug-in model, the Provider contract (name / models / auth / spawn / estimateCost / quotaStatus / healthCheck / hints), static in-tree registry, why-not full external plugin discovery. |
| 0003 | Intermediate Representation (IR) Design | The OLP-internal canonical request/response shape between the OpenAI-compat entry surface and each provider plugin. v1.0 IR fields, IR-vs-OpenAI-vs-native-provider three-shape model, IR is not exposed externally. |
| 0004 | Fallback Engine Semantics & Safety | Trigger taxonomy (Hard / Soft / Deterministic-deferred / Cost-aware-deferred), idempotent-failure safety (first-chunk rule), chain advancement one-at-a-time, observability headers. |
| 0005 | Cache Layer Cross-Provider Design | Cache key composition over (provider, model, messages, …), per-model isolation, D1+D2+D3+D4 port from OCP v3.13.0, cross-provider fallback cache behaviour (correct miss). |
| 0006 | Provider Inclusion / Exclusion + Risk-Tier Framework | The 4-tier classification (A excluded by default / B explicit consent / C opt-in / D eligible-for-default-enabled), Candidate-vs-Enabled distinction, current v0.1 candidate inventory (0 Enabled), Antigravity exclusion rationale (named prohibition + no cost advantage + reinstatement friction; pending primary-source pin), consent UX, future provider addition procedure. |
| 0007 | Multi-Key Auth (lib/keys.mjs) |
Phase 2 design ADR (D43-B, 2026-05-25). Option 2 (filesystem manifest at ~/.olp/keys/<key-id>/manifest.json) + opaque olp_<32-byte> token + SHA-256 hash. Owner / guest / anonymous tier gating with explicit config.json auth.allow_anonymous (default false). Bootstrap keygen command surface + OLP_OWNER_TOKEN env override with stable synthetic key_id. Audit ndjson append-only at ~/.olp/logs/audit.ndjson, warn+1-retry on append failure. Rejects direct SQLite port at v0.2.0 due to Node baseline (engines >=18 + CI 20/24 vs node:sqlite added 22.5.0 / RC); Option 3 hybrid documented as forward path when Phase 3+ Dashboard / SQL-aggregate quota arrives. |
| 0008 | Dashboard + Audit Query Layer | Phase 3 design ADR (D48, 2026-05-25). Static HTML dashboard + vanilla JS + fetch (no build step). In-memory ndjson scan for aggregate queries (O(N) per call; family-scale acceptable; defers SQLite migration to Option 3 hybrid trigger). Daily audit rotation audit-YYYY-MM-DD.ndjson on first append after UTC midnight; cross-file query layer for rolling 30-day windows. Owner-only gating on /dashboard + 3 /v0/management/* JSON endpoints reusing ADR 0007 § 7 auth model. 30s page poll (no SSE infra). Panels: per-provider quota / 24h request+cache+fallback / 30d spend trend / top-N fallback chains per spec § 4.6. Opens ADR 0007 § 12 Phase 3 deferral (Dashboard + audit query + rotation). |
| 0009 | Anthropic Interactive-Mode Path (Placeholder) | Placeholder ADR (2026-05-25, Draft) — blocked on OCP ADR 0007 P0 experiment outcome. Records the maintainer's "wait + port" decision: do NOT independently implement; ride OCP's P0 result. If P0 confirms Transport A (stdio NDJSON) or B (PTY) bills as subscription rather than Agent SDK credit, port to OLP lib/providers/anthropic.mjs (Option 1 parallel impl, or Option 2 OCP-as-backend; decision deferred to P0-resolution time). If P0 fails on both, shelve. No Phase 4 D-day scheduled until P0 lands AND maintainer issues explicit "go" naming this ADR. |
When to write a new ADR
Open one whenever:
- A structural rule is being added or changed (e.g., new IR field, new trigger type, new cache-key composition).
- A new provider plugin is being proposed (per ADR 0002 + ADR 0006 — ADR is a hard prerequisite for plugin merge).
- A decision encodes a lesson from an external event (provider policy change, drift incident).
- A future contributor reading the code alone could plausibly undo or re-litigate the choice.
Skip ADRs for routine implementation choices (algorithm pick, naming) — those belong in commit messages.
Format
Keep ADRs short — Context / Decision / Consequences / Alternatives is the standard skeleton. Cite incidents, PRs, or commits where useful. Length per ADR ~150–250 lines; longer than that, split.