pantheon-opencode 1.6.2-beta.1 → 1.6.2-beta.10
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +163 -0
- package/README.md +236 -60
- package/README.pt-BR.md +19 -1
- package/bin/pantheon-init.mjs +195 -13
- package/package.json +11 -3
- package/plugin.json +1 -1
- package/prompts/README.md +58 -0
- package/prompts/debug-issue.prompt.md +46 -0
- package/prompts/dynamic/agora-generated.txt +38 -0
- package/prompts/dynamic/orchestrate-generated.txt +51 -0
- package/prompts/focus.prompt.md +42 -0
- package/prompts/implement-feature.prompt.md +39 -0
- package/prompts/optimize-database.prompt.md +58 -0
- package/prompts/orchestrate-with-zeus.prompt.md +441 -0
- package/prompts/plan-architecture.prompt.md +59 -0
- package/prompts/quick-discovery-large-codebase.prompt.md +294 -0
- package/prompts/quick-plan-large-feature.prompt.md +197 -0
- package/prompts/semantic-summarize.md +50 -0
- package/prompts/sketch.prompt.md +91 -0
- package/prompts/subtask.prompt.md +131 -0
- package/pyproject.toml +1 -1
- package/scripts/decision-router-budget.mjs +780 -0
- package/scripts/decision-router-v2-budget.mjs +218 -0
- package/scripts/decision-router-v2-egress.mjs +272 -0
- package/scripts/decision-router.mjs +758 -0
- package/scripts/docs-check-changelog.mjs +5 -3
- package/scripts/install/component-selection.mjs +9 -4
- package/scripts/install/decision-layer-preview.mjs +376 -0
- package/scripts/install/decision-router-config.mjs +560 -0
- package/scripts/install/health-check.mjs +20 -11
- package/scripts/install/interactive.mjs +103 -14
- package/scripts/install/interrupt.mjs +4 -3
- package/scripts/install/migrate.mjs +123 -72
- package/scripts/install/opencode.mjs +178 -122
- package/scripts/install/plan.mjs +8 -1
- package/scripts/install/plugin.mjs +4 -3
- package/scripts/install/state.mjs +12 -0
- package/scripts/install/strings.mjs +22 -0
- package/scripts/install/venv.mjs +34 -17
- package/scripts/mcp_resources.py +11 -9
- package/scripts/release-notes.mjs +30 -7
- package/scripts/restore.mjs +22 -10
- package/scripts/sync-tui.mjs +3 -3
- package/scripts/test-opencode-v2-sandbox.sh +10 -6
- package/scripts/versioning.mjs +41 -5
- package/src/agents/aphrodite.md +6 -1
- package/src/agents/apollo.md +1 -0
- package/src/agents/athena.md +1 -0
- package/src/agents/demeter.md +1 -1
- package/src/agents/gaia.md +1 -0
- package/src/agents/hephaestus.md +1 -1
- package/src/agents/hermes.md +8 -10
- package/src/agents/iris.md +1 -1
- package/src/agents/mnemosyne.md +1 -0
- package/src/agents/nyx.md +1 -1
- package/src/agents/prometheus.md +1 -1
- package/src/agents/talos.md +6 -1
- package/src/agents/themis.md +1 -1
- package/src/agents/zeus.md +52 -62
- package/src/mcp/eval_store.py +11 -4
- package/src/mcp/mcp_resources.py +11 -9
- package/src/mcp/memory_mcp.py +293 -150
- package/src/pantheon/cost-command.ts +30 -133
- package/src/pantheon/jev-decision-tool.ts +347 -0
- package/src/pantheon/jev-decisions.ts +625 -0
- package/src/pantheon/local-decision-agents.ts +170 -0
- package/src/pantheon/local-decision-budget.ts +1046 -0
- package/src/pantheon/local-decision-egress-gate.ts +144 -0
- package/src/pantheon/local-decision-prompt.ts +256 -0
- package/src/pantheon/local-decision-provider-matrix.ts +44 -0
- package/src/pantheon/local-decision-router.ts +225 -0
- package/src/pantheon/local-decision-skills.ts +281 -0
- package/src/pantheon/local-decision-tool.ts +160 -0
- package/src/pantheon/local-decision-turn.ts +101 -0
- package/src/pantheon/local-decision-usage-evidence.internal.ts +168 -0
- package/src/pantheon/local-orchestration.ts +322 -0
- package/src/pantheon/model-pricing.ts +1 -536
- package/src/pantheon/pantheon-decision-catalog.ts +101 -0
- package/src/pantheon/v2-decision-budget.ts +456 -0
- package/src/pantheon/v2-decision-contracts.ts +300 -0
- package/src/pantheon/v2-decision-egress.ts +203 -0
- package/src/pantheon/v2-decision-events.ts +180 -0
- package/src/pantheon/v2-decision-heuristic.ts +121 -0
- package/src/pantheon/v2-decision-points/p1-agent.ts +91 -0
- package/src/pantheon/v2-decision-points/p10-claims.ts +243 -0
- package/src/pantheon/v2-decision-points/p11-catalog.ts +220 -0
- package/src/pantheon/v2-decision-points/p2-skill.ts +83 -0
- package/src/pantheon/v2-decision-points/p3-complexity.ts +108 -0
- package/src/pantheon/v2-decision-points/p4-memory.ts +137 -0
- package/src/pantheon/v2-decision-points/p5-themis-verify.ts +190 -0
- package/src/pantheon/v2-decision-points/p6-council.ts +161 -0
- package/src/pantheon/v2-decision-points/p7-loop.ts +263 -0
- package/src/pantheon/v2-decision-points/p8-guardrail.ts +367 -0
- package/src/pantheon/v2-decision-points/p9-memory-compaction.ts +304 -0
- package/src/pantheon/v2-decision-points.ts +242 -0
- package/src/pantheon/v2-decision-policy.ts +166 -0
- package/src/pantheon/v2-decision-premises.ts +146 -0
- package/src/pantheon/v2-decision-prompt-surface.ts +115 -0
- package/src/pantheon/v2-decision-rank.ts +91 -0
- package/src/pantheon/v2-decision-registry.ts +391 -0
- package/src/pantheon/v2-decision-resource-ids.ts +127 -0
- package/src/pantheon/v2-decision-shadow.ts +123 -0
- package/src/pantheon/v2-decision-telemetry.ts +214 -0
- package/src/pantheon/v2-decision-verify.ts +51 -0
- package/src/pantheon/v2-hook-engine.ts +307 -0
- package/src/pantheon/v2-native-decisions.ts +365 -0
- package/src/pantheon/v2-shell-hooks.ts +66 -2
- package/src/pantheon/v2-tools.ts +38 -15
- package/src/plugin-v2.ts +419 -26
- package/src/plugin.ts +4 -0
- package/src/plugins/tui/THIRD_PARTY_NOTICES.md +24 -0
- package/src/plugins/tui/dist/server-v2.d.ts +19 -11
- package/src/plugins/tui/dist/server-v2.d.ts.map +1 -1
- package/src/plugins/tui/dist/server-v2.js +19 -666
- package/src/plugins/tui/dist/server-v2.js.map +1 -1
- package/src/plugins/tui/dist/tui-v2.d.ts +11 -203
- package/src/plugins/tui/dist/tui-v2.d.ts.map +1 -1
- package/src/plugins/tui/dist/tui-v2.js +187 -1917
- package/src/plugins/tui/dist/tui-v2.js.map +1 -1
- package/src/plugins/tui/dist/tui.js +1 -1
- package/src/plugins/tui/package-lock.json +17 -2
- package/src/plugins/tui/package.json +4 -2
- package/src/plugins/tui/src/cost-data.ts +607 -0
- package/src/plugins/tui/src/index-v2.tsx +213 -54
- package/src/plugins/tui/src/model-pricing.ts +536 -0
- package/src/plugins/tui/src/server-v2.ts +18 -838
- package/src/plugins/tui/tsdown.config.ts +28 -6
- package/src/plugins/tui/dist/quota-adapters.d.ts +0 -89
- package/src/plugins/tui/dist/quota-adapters.d.ts.map +0 -1
- package/src/plugins/tui/dist/quota-adapters.js +0 -1142
- package/src/plugins/tui/dist/quota-adapters.js.map +0 -1
- package/src/plugins/tui/dist/quota-cli.d.ts +0 -17
- package/src/plugins/tui/dist/quota-cli.d.ts.map +0 -1
- package/src/plugins/tui/dist/quota-cli.js +0 -184
- package/src/plugins/tui/dist/quota-cli.js.map +0 -1
- package/src/plugins/tui/dist/quota-rpc-UL2HuFRJ.js +0 -390
- package/src/plugins/tui/dist/quota-rpc-UL2HuFRJ.js.map +0 -1
- package/src/plugins/tui/src/go-key-diagnostic-ui.ts +0 -100
- package/src/plugins/tui/src/go-key-diagnostic.ts +0 -125
- package/src/plugins/tui/src/quota-adapters.ts +0 -1598
- package/src/plugins/tui/src/quota-cli.ts +0 -237
- package/src/plugins/tui/src/quota-rpc.ts +0 -209
- package/src/plugins/tui/src/quota-v2-model.ts +0 -1032
- package/src/plugins/tui/src/quota-v2.tsx +0 -986
package/CHANGELOG.md
CHANGED
|
@@ -10,6 +10,169 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
|
|
|
10
10
|
<!-- Add new changes here. Running `node scripts/versioning.mjs apply` will
|
|
11
11
|
move this section to a versioned entry and reset the template below. -->
|
|
12
12
|
|
|
13
|
+
## [v1.6.2-beta.10] - 2026-11-03
|
|
14
|
+
|
|
15
|
+
### Added
|
|
16
|
+
|
|
17
|
+
- **routing** — Jev refusals carry the sanitized error CLASS in a `detail` field (`TypeError`, `RangeError`, …): enough to tell a detached-call failure from a host-side data failure, while the message (which can carry paths or provider detail) never reaches the chat.
|
|
18
|
+
|
|
19
|
+
### Changed
|
|
20
|
+
|
|
21
|
+
- **tui** — The native quota surface is removed: the `/quota` panel, the sidebar quota block, usage history, the go-key diagnostics, and the `pantheon.quota` RPC no longer ship. The recommended community plugin [`@slkiser/opencode-quota`](https://github.com/slkiser/opencode-quota) covers provider quota and usage (OpenCode 2.0.26+; an `npx` installer path exists for 1.x hosts) — see [Quota & usage](docs/tui-v2-quota-providers.md). `pantheon_cost` and the sidebar `Context` block are unaffected.
|
|
22
|
+
- **routing** — The visible `<!-- pantheon-decision-router:v1 … -->` marker is no longer appended to the prompt: the host chat rendered the HTML comment to the user. The router keeps running (shadow observation, telemetry, budget, presets); measured evidence showed every prompt mutation was a no-op (F-24, F-08/F-09), so no behavioral routing is lost.
|
|
23
|
+
- **agents** — Zeus's decision-routing instructions no longer reference the removed `/quota-go-check` command.
|
|
24
|
+
|
|
25
|
+
### Fixed
|
|
26
|
+
|
|
27
|
+
- **routing** — The native Jev runtime now invokes host methods with their owning domain as receiver. `model.list()` was called detached from the host object and threw on real sessions, surfacing only as `CATALOG_UNAVAILABLE`; the canary always exercised the bound call and never caught it. `decisions()` and `skill.list()` are bound the same way, with a contract test that fails on any detached call.
|
|
28
|
+
|
|
29
|
+
<!-- Add new changes here. Running `node scripts/versioning.mjs apply` will
|
|
30
|
+
move this section to a versioned entry and reset the template below. -->
|
|
31
|
+
## [v1.6.2-beta.9] - 2026-11-02
|
|
32
|
+
|
|
33
|
+
### Added
|
|
34
|
+
|
|
35
|
+
- **install** — `init --decision-model typesafe-jev/jev-1.14.0` merges the TypeSafe provider entry additively into the user's `opencode.json`; only the sign-in remains.
|
|
36
|
+
|
|
37
|
+
### Changed
|
|
38
|
+
|
|
39
|
+
- **agents** — Every agent frontmatter declares terminal permissions under `shell:` — the action a measured 2.2.5 host actually evaluates (canary-recorded evidence: a `shell` deny is enforced while `bash` falls through unruled).
|
|
40
|
+
- **agents** — Deny intents keep a `bash:` twin; the former `bash:`-only keys never matched, which made specialists' terminal grants inconsistent.
|
|
41
|
+
- **agents** — Zeus must never ask the user to type terminal commands: terminal work dispatches to a bash-capable specialist.
|
|
42
|
+
- **install** — `--opencode-version v1` is refused with a deprecation message front-running the 2.0 removal of the legacy plugin line.
|
|
43
|
+
- **docs** — New [Skill provenance search](docs/reference/skill-search-design.md) investigation (three tiers, Jev as typed ranker; deliberately unwired).
|
|
44
|
+
- **docs** — Measured MCP numbers in [Performance](docs/reference/performance.md) (fastmcp startup, FTS5 memory, vision deps).
|
|
45
|
+
|
|
46
|
+
### Added
|
|
47
|
+
|
|
48
|
+
- **install** — The wizard's decision-model question now configures the real route (consent + caps + period in one write): Console Jev, the free variant, or TypeSafe direct.
|
|
49
|
+
- **install** — Choosing TypeSafe direct merges the `providers.typesafe-ai` entry additively into the user's opencode.json; only the sign-in remains.
|
|
50
|
+
- **install** — Legacy metadata spellings degrade to skip with a hint; direct OpenAI has no native Decisions route.
|
|
51
|
+
- **install** — The capability notice prints only under `--verbose`.
|
|
52
|
+
|
|
53
|
+
### Changed
|
|
54
|
+
|
|
55
|
+
- **performance** — The in-process secret scan is gated to exfil-capable tools (shell, file writes, web); read-only tools skip it, unknown names stay scanned (fail-closed).
|
|
56
|
+
- **agents** — Zeus must never ask the user to type terminal commands: terminal work dispatches to a bash-capable specialist.
|
|
57
|
+
|
|
58
|
+
<!-- Add new changes here. Running `node scripts/versioning.mjs apply` will
|
|
59
|
+
move this section to a versioned entry and reset the template below. -->
|
|
60
|
+
## [v1.6.2-beta.8] - 2026-11-02
|
|
61
|
+
|
|
62
|
+
### Added
|
|
63
|
+
|
|
64
|
+
- **install** — Added `init --decision-model <provider>/<model> --decision-monthly-usd N --decision-per-decision-usd N` to activate the Jev decision route during installation (the same chain as `decision-router setup-model`; `--decision-no-consent` refuses consent), and the post-install next steps now include the optional decision-model path in English and Portuguese.
|
|
65
|
+
|
|
66
|
+
### Changed
|
|
67
|
+
|
|
68
|
+
- **performance** — The per-tool-call secret scan and the per-dispatch delegation audit now run in-process (`v2-hook-engine.ts`): same patterns, masked trail, exit-code contract, fail-closed classifier, and `delegations.log` artifacts — without the former one `bash` child per tool call and two more per delegation (each also spawning `python3`). Post-write formatting spawns only when the tool call touched a formattable file.
|
|
69
|
+
- **agents** — Specialist prompts carry two-tier verification (small bounded fix → change plus one targeted proof; material change → full discipline), replacing the unconditional TDD mandate in Hermes; Aphrodite and Talos gained the same tier note.
|
|
70
|
+
- **docs** — New Performance and tuning reference (measured hook costs, prompt budget, decision latency, context-growth knob) and an INSTALLATION section for the Jev decision-model flow.
|
|
71
|
+
|
|
72
|
+
## [v1.6.2-beta.7] - 2026-11-02
|
|
73
|
+
|
|
74
|
+
### Added
|
|
75
|
+
|
|
76
|
+
- **install** — Added `decision-router setup-model <provider>/<model> --monthly-usd N --per-decision-usd N`: one command performs selection, enablement, egress consent, user/provider/model caps, and budget-period confirmation, then prints the verification checklist (`--no-consent` configures everything except consent).
|
|
77
|
+
- **install** — Added `decision-router doctor`: read-only diagnosis of the whole native decision route (config, consent, selection, budget admission, unresolved holds, best-effort host-catalog probe) printing the exact command to run for each failing gate.
|
|
78
|
+
|
|
79
|
+
### Changed
|
|
80
|
+
|
|
81
|
+
- **agents** — Modernized the Zeus system prompt: pruned stale release-history sections, kept the operational guards, and granted `pantheon_jev_decide` in the agent permission frontmatter so new installs get the advisory tool without manual config edits.
|
|
82
|
+
- **docs** — Documented ready-to-copy decision-provider examples (TypeSafe direct, OpenRouter-hosted Jev) with the catalog caveat that the flat `opencode models` list can omit decision-typed models.
|
|
83
|
+
- **agents** — Zeus routing policy now prefers one typed `pantheon_jev_decide` call for genuinely ambiguous routing and skill stacking, with `pantheon_local_decision` as the offline fallback.
|
|
84
|
+
- **docs** — Documented the skill-discovery loop (find, review, install, decide) and mapped the candidate MCP-gating expansions as deliberately unwired.
|
|
85
|
+
|
|
86
|
+
<!-- Add new changes here. Running `node scripts/versioning.mjs apply` will
|
|
87
|
+
move this section to a versioned entry and reset the template below. -->
|
|
88
|
+
## [v1.6.2-beta.6] - 2026-11-01
|
|
89
|
+
|
|
90
|
+
### Added
|
|
91
|
+
|
|
92
|
+
- **routing** — Added the Zeus-only `pantheon_jev_decide` advisory tool: 1–4 typed questions (choice, score, predicate) answered by the Jev decision model through the host's native Decisions API; it registers only on hosts exposing that API and never dispatches agents, runs skills, or changes permissions.
|
|
93
|
+
- **routing** — Added native route selection from the user-level decision-router config (OpenCode Console `jev-1.13` and custom `typesafe-ai` decision models) with a frozen provider→host mapping; direct OpenAI is refused and never substituted.
|
|
94
|
+
- **routing** — Added host-reported settlement: the budget reservation reconciles from the host-reported DecisionResult cost (a reported zero releases the hold), and a failed or unreconciled call stays fail-closed.
|
|
95
|
+
- **routing** — Added catalog presets to `pantheon_jev_decide`: `mode: "skills"` stacks the locally prefiltered skill shortlist (whole-catalog fallback) and `mode: "delegation"` picks a specialist, both single typed calls with `none` always offered.
|
|
96
|
+
- **routing** — Extended the `skills` preset to decide over installed host skills (`ctx.skill.list()`) in addition to the Pantheon catalog: any Agent-Skills-format skill installed in the host becomes stackable without a Pantheon change. Installs stay manual and reviewed; Pantheon never installs or updates skills.
|
|
97
|
+
- **docs** — Documented the native gate chain, routes, and verification boundary in one reference (`docs/reference/native-decisions.md`) and indexed the decision-layer references in the docs nav; added a real-host canary assertion for the new tool's registration.
|
|
98
|
+
|
|
99
|
+
### Changed
|
|
100
|
+
|
|
101
|
+
- **security** — Removed the direct-fetch decision-provider path entirely (runner, payload protocol, fetch-path usage verifier, per-turn provider cache): Pantheon owns no transport, and the only egress is the host's native layer behind the enabled/consent/budget/permission chain. The per-turn prompt hook stays local-only.
|
|
102
|
+
- **security** — The budget ledger now treats a host-reported zero cost as a real zero (releasing the hold) while still freezing user/provider/model buckets when actual cost exceeds the reservation.
|
|
103
|
+
- **docs** — Consolidated the decision-status narrative to one source of truth per surface, corrected stale env-var rows (no decision credential is read on any production path), and removed an orphan planning note (the tracked deepwork note stays: it is the checkout fixture the resources server resolves against).
|
|
104
|
+
|
|
105
|
+
<!-- Add new changes here. Running `node scripts/versioning.mjs apply` will
|
|
106
|
+
move this section to a versioned entry and reset the template below. -->
|
|
107
|
+
## [v1.6.2-beta.5] - 2026-11-01
|
|
108
|
+
|
|
109
|
+
## 🆕 What's New
|
|
110
|
+
- **routing** — wire decision points to their declared host surfaces in shadow (#304)
|
|
111
|
+
- **routing** — add V2 decision layer with measured-shape adapters (#303)
|
|
112
|
+
|
|
113
|
+
## 🐞 Fixed
|
|
114
|
+
- **mcp** — harden memory and resource MCP reliability (#306)
|
|
115
|
+
## [v1.6.2-beta.4] - 2026-10-31
|
|
116
|
+
|
|
117
|
+
### Added
|
|
118
|
+
|
|
119
|
+
- **install** — Added a user-level `decision-router` admin CLI for enablement, selection, consent, per-user/provider/model caps, and period confirmation; config is private and non-secret.
|
|
120
|
+
- **install** — Added `decision-router holds` to list unresolved reservations without reserving, reconciling, releasing, or pruning.
|
|
121
|
+
- **docs** — Added an offline protocol for separately evaluating agent routing and task complexity; no benchmark results or provider selection are claimed.
|
|
122
|
+
- **routing** — Added a default-off, local-only recommendation API for exact canonical agent roles and structured complexity dimensions; it does not dispatch agents or change gates.
|
|
123
|
+
- **routing** — Added a private V2 per-turn selector: allowlisted skills, at most one specialist, one call per session/message, and deterministic local fallback.
|
|
124
|
+
- **routing** — Added a private fixed-endpoint adapter for `gpt-6-luna` and `jev-1.14.0` with no caller-supplied transport, retry, or fan-out; Console/Free and Bifrost stay ineligible.
|
|
125
|
+
- **routing** — Provider contract tests run under the real `tsx` runner (`npm run test:ts`) for the exact payload, gate denials, usage reconciliation, and one call per turn; no live call was made.
|
|
126
|
+
- **routing** — Added a user-level `enabled` switch, canonical provider/model matrix, and a single ledger mapping; provider egress also requires the host `permission.assert` gate.
|
|
127
|
+
- **routing** — Added a user-scoped SQLite ledger with explicit UTC reservations and no default caps. Admission caps are local safeguards, not invoice guarantees.
|
|
128
|
+
- **docs** — `decision-router status`/`holds` are read paths: `status` may create the SQLite ledger, and both may migrate it, but neither reserves, reconciles, releases, or prunes.
|
|
129
|
+
- **docs** — The `local-decision-router` subpath is TypeScript source needing the host runtime or a transpiler; the published CLI uses the committed ESM bundle.
|
|
130
|
+
|
|
131
|
+
### Changed
|
|
132
|
+
|
|
133
|
+
- **security** — Decision egress is fail-closed: a missing gate, cap, period, or credential means zero requests; V1 stays local-only.
|
|
134
|
+
- **release** — `prepack` now runs the `check:decision-router` drift gate, so a stale ledger bundle cannot be packed or published.
|
|
135
|
+
|
|
136
|
+
### Fixed
|
|
137
|
+
|
|
138
|
+
- **install** — `decision-router caps user` without flags now reports `Both --monthly-usd and --per-decision-usd are required` as a one-line usage error instead of a stack trace.
|
|
139
|
+
- **routing** — `permission.assert` denial (thrown or returned, including the host's `Permission denied: decision.egress` message) means zero requests; an explicit `deny` rule is the kill-switch.
|
|
140
|
+
- **routing** — Egress trusts the user-level config; `permission.assert` is only the host kill-switch. A v2.2.0 canary showed an unruled assertion resolves allow and `evaluate` runs only on that path.
|
|
141
|
+
- **routing** — A cached provider decision re-reads the user-level config/consent gate before reuse, so revoking consent takes effect without waiting for cache expiry.
|
|
142
|
+
- **security** — The prompt hook reuses one decision per turn and never logs or persists the raw request; payloads stay allowlisted.
|
|
143
|
+
- **security** — Credential rejection now requires a token boundary and structured `sk-` prefixes, so prose such as `task-force-*` or `disk-usage-*` is no longer treated as a key.
|
|
144
|
+
- **routing** — Reusing a cached provider decision does not re-prompt the same permission gate; a different or missing gate is still evaluated and denies fail-closed.
|
|
145
|
+
- **docs** — Clarified that `decision-router holds` performs no reservation, reconciliation, release, or pruning, while opening an existing ledger may apply a forward-only schema migration.
|
|
146
|
+
|
|
147
|
+
<!-- Add new changes here. Running `node scripts/versioning.mjs apply` will
|
|
148
|
+
move this section to a versioned entry and reset the template below. -->
|
|
149
|
+
## [v1.6.2-beta.3] - 2026-10-29
|
|
150
|
+
|
|
151
|
+
### Changed
|
|
152
|
+
|
|
153
|
+
- **install** — Direct `init` uses matching TTY/headless component defaults; Python runtime and prompt templates are opt-in, and `--yes` suppresses prompts without skipping preview or drift checks.
|
|
154
|
+
- **install** — Runtime health checks verify SQLite FTS5 capability and fail when it is unavailable.
|
|
155
|
+
|
|
156
|
+
### Fixed
|
|
157
|
+
|
|
158
|
+
- **install** — Explicit restore decline exits successfully; missing authorization fails closed, while cancellation exits `130`. Post-write interrupts and runtime failures record the selected target and partial/degraded state.
|
|
159
|
+
- **install** — Migration schema version is tracked separately from the installed package version and remains idempotent across prerelease package versions.
|
|
160
|
+
|
|
161
|
+
<!-- Add new changes here. Running `node scripts/versioning.mjs apply` will
|
|
162
|
+
move this section to a versioned entry and reset the template below. -->
|
|
163
|
+
## [v1.6.2-beta.2] - 2026-10-28
|
|
164
|
+
|
|
165
|
+
### Added
|
|
166
|
+
|
|
167
|
+
- **TUI** — `/quota` adds recorded usage history for 7, 15, 30 days, and Total, with daily and per-model token summaries plus a clearly non-billable catalog estimate.
|
|
168
|
+
- **quota** — OpenCode Go usage uses the canonical endpoint and falls back to the configured API key when its Console OAuth request fails.
|
|
169
|
+
|
|
170
|
+
### Fixed
|
|
171
|
+
|
|
172
|
+
- **quota** — Future-dated usage rows are excluded from rolling windows and Total.
|
|
173
|
+
|
|
174
|
+
<!-- Add new changes here. Running `node scripts/versioning.mjs apply` will
|
|
175
|
+
move this section to a versioned entry and reset the template below. -->
|
|
13
176
|
## [v1.6.2-beta.1] - 2026-10-27
|
|
14
177
|
|
|
15
178
|
### Changed
|
package/README.md
CHANGED
|
@@ -46,22 +46,25 @@ npx pantheon-opencode init
|
|
|
46
46
|
opencode
|
|
47
47
|
```
|
|
48
48
|
|
|
49
|
-
|
|
49
|
+
Direct `init` uses the same component defaults in TTY and headless runs:
|
|
50
|
+
`agents`, `skills`, `instructions`, `commands`, and `plugins`. `runtime` and
|
|
51
|
+
`prompts` are opt-in. A TTY run selects components and target, shows a preview,
|
|
52
|
+
then asks once for final authorization (default **no**). Without a TTY, `init`
|
|
53
|
+
is preview-only unless `--yes` explicitly authorizes the apply; `--yes` skips
|
|
54
|
+
prompts but still prints the preview and checks for drift.
|
|
55
|
+
|
|
56
|
+
`npm run setup` is a separate repository setup wrapper. On detected OpenCode V2
|
|
50
57
|
it reviews the global config before installer init: legacy permission rules can
|
|
51
|
-
be migrated after explicit review.
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
|
|
55
|
-
|
|
56
|
-
|
|
57
|
-
|
|
58
|
-
|
|
59
|
-
|
|
60
|
-
|
|
61
|
-
converted to `mcp.servers` or removed; nested third-party servers are preserved.
|
|
62
|
-
Headless/CI/non-TTY runs are preview-only and do not invoke writing init (V1
|
|
63
|
-
included). See the [installation guide](docs/INSTALLATION.md) for layer handling,
|
|
64
|
-
conflict choices, backups, and recovery.
|
|
58
|
+
be migrated after explicit review. Config migration and installer changes are
|
|
59
|
+
preflighted before one final authorization; `--yes` alone does not authorize
|
|
60
|
+
setup writes, and headless/CI setup remains preview-only. Direct
|
|
61
|
+
`npx pantheon-opencode init` does not run that V2 config-migration review. See
|
|
62
|
+
the [installation guide](docs/INSTALLATION.md) for layer handling, conflict
|
|
63
|
+
choices, backups, and recovery.
|
|
64
|
+
Existing native V2 `permissions` arrays remain authoritative. Unsafe MCP
|
|
65
|
+
wildcard policies and ineffective `ask` rules require explicit resolution;
|
|
66
|
+
third-party flat MCP entries in `opencode.jsonc` must be converted to
|
|
67
|
+
`mcp.servers` or removed before V2 setup.
|
|
65
68
|
|
|
66
69
|
Global `init` and `setup` use `$XDG_CONFIG_HOME/opencode` when
|
|
67
70
|
`XDG_CONFIG_HOME` is absolute; otherwise they use `~/.config/opencode`.
|
|
@@ -94,51 +97,29 @@ see [Quick Start](docs/QUICKSTART.md).
|
|
|
94
97
|
and documenting work.
|
|
95
98
|
- **5 local MCP servers** for project memory, persistence, resources, confined
|
|
96
99
|
script execution, and vision.
|
|
100
|
+
- **A selective, advisory decision router** with structured local results and
|
|
101
|
+
deterministic per-turn skill/specialist recommendations when enabled.
|
|
102
|
+
Pantheon-owned direct-provider egress is inactive; native egress exists only
|
|
103
|
+
via the explicit, Zeus-only `pantheon_jev_decide` advisory tool, which calls
|
|
104
|
+
the host's native Decisions API (TypeSafe Jev via OpenCode Console or a
|
|
105
|
+
configured decision model) behind the user's consent and budget gates — it
|
|
106
|
+
never dispatches agents, runs skills, or changes permissions. This does not
|
|
107
|
+
change the separately documented Vision integration. See the
|
|
108
|
+
[router reference](docs/reference/local-decision-router.md) and the
|
|
109
|
+
[Native Decisions (Jev)](docs/reference/native-decisions.md).
|
|
97
110
|
- **An optional TUI** with a dispatch sidebar block and a full-width
|
|
98
|
-
`/dispatch` panel. The V2
|
|
99
|
-
|
|
100
|
-
|
|
101
|
-
|
|
102
|
-
|
|
103
|
-
|
|
104
|
-
the
|
|
105
|
-
|
|
106
|
-
|
|
107
|
-
|
|
108
|
-
|
|
109
|
-
|
|
110
|
-
in the sidebar and `/quota` panel (plus a `Último erro` line) instead
|
|
111
|
-
of a blind "Status indisponível"; the cause is logged as
|
|
112
|
-
`[pantheon-tui quota]`.
|
|
113
|
-
Usage severity uses warning color from 60% consumed and error color above 85%.
|
|
114
|
-
Session costs, provider balances and selected-key usage retain their distinct
|
|
115
|
-
labels and reported periods. Long values and states continue onto additional
|
|
116
|
-
lines within the sidebar's fixed 34-column content budget.
|
|
117
|
-
The installer selects the `plugins` component by default; in interactive setup
|
|
118
|
-
you can change the component selection. A component-scoped install includes
|
|
119
|
-
the TUI only when `plugins` is selected.
|
|
120
|
-
The V2 quota RPC shows providers only when OpenCode lists an active supported
|
|
121
|
-
connection and Pantheon can locally resolve a nonblank credential. This is
|
|
122
|
-
not proof that the provider accepted the credential; failed requests and
|
|
123
|
-
unsupported adapters can remain visible as unavailable. OpenCode Go checks
|
|
124
|
-
the selected Console OAuth login first, then uses an active OpenCode Go API
|
|
125
|
-
key (or its legacy OpenCode key alias) only when the Console request fails; a
|
|
126
|
-
Console 404 or a successful response without an access object reports no Go
|
|
127
|
-
subscription and does not fall back.
|
|
128
|
-
The route contract remains unofficial; see the
|
|
129
|
-
[quota provider coverage table](docs/tui-v2-quota-providers.md) for limits and
|
|
130
|
-
troubleshooting.
|
|
131
|
-
`/quota-go-check` is a separate manual, confirmation-gated diagnostic: one
|
|
132
|
-
GET to `https://opencode.ai/zen/go/v1/usage` with the configured Go API key
|
|
133
|
-
(not OAuth), at most one attempt per plugin runtime. It never refreshes quota,
|
|
134
|
-
follows redirects or retries. Only HTTP 401 bodies are inspected, up to 4096
|
|
135
|
-
bytes, for an own top-level JSON `error` property; its value is never inspected.
|
|
136
|
-
Results contain only a safe category, optional HTTP status, coarse content type,
|
|
137
|
-
and (for 401) whether that structure is present, absent, or unavailable.
|
|
138
|
-
No error code, type, message, body, request ID, or byte count is displayed;
|
|
139
|
-
a 401 rejection's cause remains unknown. `success` means
|
|
140
|
-
HTTP success only—not a stable quota contract or parsed quota correctness.
|
|
141
|
-
Require Themis security review before using this diagnostic.
|
|
111
|
+
`/dispatch` panel. The V2 sidebar keeps the Pantheon version, the active
|
|
112
|
+
preset/source, git state, and a `Context` block (tokens, a percent gauge,
|
|
113
|
+
`$<spent> spent`, and a muted `cache <n>% · <n.n> tok/s` line); the native
|
|
114
|
+
prompt footer keeps its own line, and Pantheon only appends
|
|
115
|
+
`▸<preset> · ✦<n> ativos` while delegations are running. The installer
|
|
116
|
+
selects the `plugins` component by default; in interactive setup you can
|
|
117
|
+
change the component selection. A component-scoped install includes the TUI
|
|
118
|
+
only when `plugins` is selected. The TUI ships no quota panel: for provider
|
|
119
|
+
quota and usage inside OpenCode, install the recommended community plugin
|
|
120
|
+
[`@slkiser/opencode-quota`](https://github.com/slkiser/opencode-quota) — see
|
|
121
|
+
[Quota & usage](docs/tui-v2-quota-providers.md). `pantheon_cost` and
|
|
122
|
+
`pantheon_model` keep working unchanged.
|
|
142
123
|
|
|
143
124
|
Vision requests to OpenCode Zen require a valid active session and are rejected
|
|
144
125
|
before image fetching or model-catalog lookup when the session is missing or
|
|
@@ -217,6 +198,185 @@ fan-in or job recovery without an exposed mechanism.
|
|
|
217
198
|
The delegation model, caller/target matrix, and approval gates are documented
|
|
218
199
|
in [Architecture](docs/ARCHITECTURE.md) and
|
|
219
200
|
[Permissions, Gates & Delegation](docs/PERMISSIONS-QUALITY-DELEGATION.md).
|
|
201
|
+
The [local decision router](docs/reference/local-decision-router.md) provides a
|
|
202
|
+
default-off standalone local API (`PANTHEON_LOCAL_DECISION_ROUTER=1`), the
|
|
203
|
+
separate manual `pantheon_local_decision` advisory tool, and deterministic
|
|
204
|
+
per-turn local recommendations when the user-level `enabled` preference is on.
|
|
205
|
+
The prompt hook may add an advisory marker and narrow an existing `prompt.skills`
|
|
206
|
+
array only when identifiable skill IDs overlap the local selection; this never
|
|
207
|
+
dispatches child sessions or changes permissions or approvals. Per-turn selection
|
|
208
|
+
uses no provider egress: the formerly documented direct-provider route remains
|
|
209
|
+
historical/inactive, and legacy consent, caps, period, provider selection, or
|
|
210
|
+
credentials cannot activate it. Native child-session dispatch remains separate.
|
|
211
|
+
|
|
212
|
+
The one native egress surface is the Zeus-only `pantheon_jev_decide` tool,
|
|
213
|
+
available on hosts that expose the V2.2.5 native Decisions API; its full gate
|
|
214
|
+
chain, routes, and settlement rules are documented once in
|
|
215
|
+
[V2 native Decisions](docs/reference/native-decisions.md).
|
|
216
|
+
|
|
217
|
+
The installer may retain a legacy target-specific preference; it does not control
|
|
218
|
+
runtime routing. `npx pantheon-opencode decision-router ...` manages stored
|
|
219
|
+
user-level preferences and budget state: `enabled` gates the local per-turn
|
|
220
|
+
recommendation only; provider-selection and budget/consent state do not activate
|
|
221
|
+
egress. The separate SQLite ledger has no default caps. Installation does not
|
|
222
|
+
contact a model provider or inspect credentials. The published CLI imports
|
|
223
|
+
committed ESM bundles:
|
|
224
|
+
`npm run build:decision-router` regenerates them and `npm run check:decision-router`
|
|
225
|
+
(the `prepack`/`prepublishOnly` drift gate) fails when any is stale. The
|
|
226
|
+
`pantheon-opencode/local-decision-router` subpath itself is TypeScript source, so
|
|
227
|
+
it loads only in the host runtime or under a transpiler such as `tsx`.
|
|
228
|
+
|
|
229
|
+
Decision-layer commands are separated by effect. `decision-router help`,
|
|
230
|
+
`status`, `preview` and `holds` are read-only: they never create, migrate, or
|
|
231
|
+
write the config or the SQLite ledger, and neither does `setup` without
|
|
232
|
+
`--apply`. `select` records a preference and can never enable anything — moving
|
|
233
|
+
the target also revokes consent recorded for the previous one. `setup` prints a
|
|
234
|
+
**computed diff of the target artifacts** (snapshot + SHA-256 per file, compared
|
|
235
|
+
against the exact bytes the writer would produce); `setup --apply` is the form
|
|
236
|
+
that writes, and a second run reports `0 create · 0 update`. It is deliberately
|
|
237
|
+
not the installer's "Change plan", which announced 112 creates for an apply that
|
|
238
|
+
created nothing. `setup --target <dir>` also reconciles the
|
|
239
|
+
`.pantheon/install-state.json` provider/consent record with the user-level config;
|
|
240
|
+
that record is derived from the config and never asserts consent the config lacks.
|
|
241
|
+
Neither path creates a backup: installer backup sets accumulate once per
|
|
242
|
+
application and contain credential-bearing material (API keys/tokens), so no
|
|
243
|
+
extra copy is made. Installer file-ownership tracking is partial and asymmetric —
|
|
244
|
+
`file_inventory` indexes 53 PROJECT artifacts and no GLOBAL ones (F-15); the
|
|
245
|
+
106-project / 107-global denominators are derived from the 213-artifact total and
|
|
246
|
+
are not separately indexed — so this preview compares the decision-layer
|
|
247
|
+
artifacts it owns, not "everything the installer touched".
|
|
248
|
+
|
|
249
|
+
The old OpenAI/TypeSafe per-turn provider adapters and endpoint descriptions are
|
|
250
|
+
retained as historical, inert code; no legacy consent, cap, period, provider, or
|
|
251
|
+
permission setting wires them into the production prompt hook. The captured-hook
|
|
252
|
+
boundary test supplies an isolated synthetic consent/provider config and fake
|
|
253
|
+
test-only credential, verifies a local recommendation marker, and verifies zero
|
|
254
|
+
native Decisions or global `fetch` calls. This is an offline regression check of
|
|
255
|
+
that hook, not a claim about unexercised network paths or a live-provider test.
|
|
256
|
+
Measured surface coverage is
|
|
257
|
+
reported honestly rather than implied: P7 runs behind `PANTHEON_V2_P7_LOOP` with
|
|
258
|
+
an **advisory** execution cap (never described as enforcement), P2 is
|
|
259
|
+
**advisory-only** (an empirical no-op on the default path), P9 was measured on
|
|
260
|
+
top-level **and child** sessions with `reason:"overflow"` still unmeasured, and
|
|
261
|
+
P8 is **advisory: not activatable by measurement** — its declared rules match no
|
|
262
|
+
delivered permission payload, so it narrows nothing (PROBE-F).
|
|
263
|
+
|
|
264
|
+
### The V2 decision layer is declared in full and wired in part
|
|
265
|
+
|
|
266
|
+
The V2 decision layer declares eleven integration points (P1–P11) over three
|
|
267
|
+
decision primitives — `ask`, `rank`, and `verify` — and a deterministic policy
|
|
268
|
+
that decides which point may run. **Seven of the eleven have a production call
|
|
269
|
+
site: two behind flags that are off by default, five in shadow.**
|
|
270
|
+
|
|
271
|
+
- **P7 (loop)** is wired to `session.execution.succeeded` behind
|
|
272
|
+
`PANTHEON_V2_P7_LOOP`, which is off. It writes each observation to an
|
|
273
|
+
in-memory, bounded telemetry collector that the plugin never reads back and
|
|
274
|
+
exposes only to tests, so "records" here does not mean an operator-visible log.
|
|
275
|
+
- **P8 (guardrail)** is wired to `permission.evaluate` behind
|
|
276
|
+
`PANTHEON_V2_P8_GUARDRAIL`, which is off. C8 is closed **by measurement**, and
|
|
277
|
+
the measurement is negative: PROBE-F delivered 24 real `permission.evaluate`
|
|
278
|
+
events and every declared rule matched none of them (a valid `action` token and
|
|
279
|
+
a top-level `sessionID` are always present), the host resolves an unrecognised
|
|
280
|
+
effect as `ask` and proceeds, and `permission.evaluate.egress` is unreachable
|
|
281
|
+
(a tool declaring it is never advertised to the provider). As declared, P8 does
|
|
282
|
+
not narrow. The flag stays off.
|
|
283
|
+
- **P1 and P2** are registered on `session.hook('prompt')` in **shadow**. They
|
|
284
|
+
observe the same admission payload through a projection that carries only
|
|
285
|
+
`prompt.agents` and `prompt.skills`: no text, no file bytes, no metadata, no
|
|
286
|
+
mutation, no throw. Every record says `effect: none` and goes to an in-memory,
|
|
287
|
+
bounded collector the plugin never reads back (test-visible only).
|
|
288
|
+
- **P3** is wired at its declared `tool.invoke` in **shadow**: the
|
|
289
|
+
`pantheon_local_decision` tool hands the adapter its own input, whose schema
|
|
290
|
+
requires `complexity` and `gateStatus`. It records a classification when the
|
|
291
|
+
tool is invoked — never a permanent `complexity.invalid` refusal from a payload
|
|
292
|
+
that cannot carry the vector — and applies nothing.
|
|
293
|
+
- **P9** is wired at its declared `session.hook('compaction')` in **shadow**, on
|
|
294
|
+
the carrier that was actually measured: the top-level `sessionID` and the
|
|
295
|
+
`system` part array. It records the decision key and the payload shape and
|
|
296
|
+
pushes nothing — the injected compaction context is unchanged — and a payload
|
|
297
|
+
whose only session id is a nested `session.id` (a field the 2.2.5 host never
|
|
298
|
+
sends) produces no decision at all. The same shape was measured in a **child**
|
|
299
|
+
session (PROBE-G: hook fires 3/3, child `sessionID` at top level, `system` an
|
|
300
|
+
array of 4), so no child-specific branch exists. `reason:"overflow"` was not
|
|
301
|
+
inducible and is not designed for. No measured surface carries the memory
|
|
302
|
+
candidate list it would retain or discard, so its record states that absence
|
|
303
|
+
rather than a retention or a priority.
|
|
304
|
+
- **P11** is wired inside `ctx.tool.transform` in **shadow**: it reads the draft
|
|
305
|
+
the host hands that callback and calls none of its mutators. Shadow has no
|
|
306
|
+
responder, so it records the validated `choice` question over the draft ids —
|
|
307
|
+
never a selection.
|
|
308
|
+
|
|
309
|
+
**The other four — P4, P5, P6 and P10 — are library code with no production call
|
|
310
|
+
site.** Nothing constructs or registers them outside the per-point test suites —
|
|
311
|
+
the offline harness imports no adapter module. P6 and P10 declared the prompt
|
|
312
|
+
hook, but that payload never carries council candidates or counsellor claims, so
|
|
313
|
+
they stay unwired instead of recording a refusal from a surface that cannot feed
|
|
314
|
+
them. P4 ranks a memory candidate array and the measured `context` payload
|
|
315
|
+
carries `system` text parts, not candidates; P5 verifies a declared
|
|
316
|
+
`{ requirements, responses }` pair and the `execute.after` event carries
|
|
317
|
+
neither. On a host they do not read the turn, record no telemetry and have no
|
|
318
|
+
switch to turn off, because nothing registers them.
|
|
319
|
+
|
|
320
|
+
"Shadow" therefore means no behavioural change, not a claim of effect: the five
|
|
321
|
+
shadow points read a narrow slice of their surface and decide nothing from it,
|
|
322
|
+
and the two flag-gated points are off. No activation flag is set in a default
|
|
323
|
+
install.
|
|
324
|
+
|
|
325
|
+
The CLI separates effects: `npx pantheon-opencode decision-router help`, `status`,
|
|
326
|
+
`preview` and `holds` never write, `setup` writes only under `--apply`, `preview`
|
|
327
|
+
is an alias of `setup`, and `select` records a preference without enabling
|
|
328
|
+
anything. Egress stays opt-in and off, and only the explicit `enable`, `consent`,
|
|
329
|
+
`caps` and `period` actions can change that; no read-only command can.
|
|
330
|
+
|
|
331
|
+
What the layer does **not** do today, stated as measured rather than implied:
|
|
332
|
+
|
|
333
|
+
- **P2 (skills) is advisory-only and does not filter.** It is an empirical no-op
|
|
334
|
+
on the default path, because the host sends `prompt.skills` absent. Effective
|
|
335
|
+
project-skill filtering was cancelled by measurement, not emulated, and no
|
|
336
|
+
token reduction is claimed.
|
|
337
|
+
- **P7 (loop) is behind `PANTHEON_V2_P7_LOOP`, off by default, and does not
|
|
338
|
+
enforce loop limits.** It counts executions and writes an `effect: none`
|
|
339
|
+
observation to an in-memory collector that nothing reads back. Its
|
|
340
|
+
12-execution cap is **advisory**: no measured host surface signals a new user
|
|
341
|
+
turn, so nothing is claimed to reset the streak.
|
|
342
|
+
- **P9 (compaction) is measured in top-level and child sessions.** PROBE-G fired
|
|
343
|
+
the hook in a real child 3/3 with the child's `sessionID` at top level and the
|
|
344
|
+
same payload shape. `reason: "overflow"` was **not inducible** in 6 error
|
|
345
|
+
shapes — the host retried and completed, and the one failure-recovery
|
|
346
|
+
compaction was persisted as `reason:"auto"` — so that path stays unmeasured;
|
|
347
|
+
the checkpoint reinjection inside a child was not exercised, and the `messages`
|
|
348
|
+
channel remains UNKNOWN. The memory candidate list is not available on any
|
|
349
|
+
measured surface, so the wired P9 record names that absence and claims no
|
|
350
|
+
retention or priority.
|
|
351
|
+
- **P8 (guardrail) is not activatable by measurement.** PROBE-F delivered 24 real
|
|
352
|
+
`permission.evaluate` events: the payload is
|
|
353
|
+
`["sessionID","agent","action","resources","metadata","source","effect"]` with
|
|
354
|
+
`effect` an own writable data property pre-populated by the host, and a written
|
|
355
|
+
`deny` **is** honoured. But neither declared rule can match a delivered payload
|
|
356
|
+
(valid `action` token, `sessionID` always present), the host lets an
|
|
357
|
+
unrecognised effect resolve as `ask` and execute, and
|
|
358
|
+
`permission.evaluate.egress` is unreachable — so the current rule set matches
|
|
359
|
+
nothing and does not narrow. The point is recorded as **advisory**, not as
|
|
360
|
+
awaiting review, and the inertness is the measured verdict rather than a design
|
|
361
|
+
claim. `execute.before` remains the only hard barrier.
|
|
362
|
+
- **The embeddings-versus-BM25 comparison has not been run.** The environment is
|
|
363
|
+
offline with no embedding model available, so BM25 remains the baseline and no
|
|
364
|
+
gain or loss in retrieval or tokens is claimed in either direction.
|
|
365
|
+
|
|
366
|
+
Calibration that was run: the offline harness
|
|
367
|
+
(`npx tsx tests/pantheon/v2-decision-harness.test.ts`) executed 264 synthetic
|
|
368
|
+
cases — 132 normal, 66 refusal, 66 adversarial — across the eleven points, with
|
|
369
|
+
24 cases per point and the suite asserting at least 20 cases, 5 refusals and 5
|
|
370
|
+
adversarial cases per point. All 264 cases passed on 2026-10-31. This harness is
|
|
371
|
+
the only place all eleven points are exercised in one run, but it imports no
|
|
372
|
+
adapter module: it iterates the registry and exercises the shared primitives,
|
|
373
|
+
while the adapters are covered by their per-point suites
|
|
374
|
+
(`v2-decision-p1.test.ts` … `v2-decision-p11.test.ts`). Passing it says nothing
|
|
375
|
+
about whether a point is registered in a host.
|
|
376
|
+
The harness measures contracts (admission, refusal, shadow no-op, telemetry
|
|
377
|
+
redaction, offline discipline, registry integrity), **not** token use, quality,
|
|
378
|
+
latency or any effect inside a host turn. Numbers and unmeasured surfaces are
|
|
379
|
+
recorded in the [router reference](docs/reference/local-decision-router.md).
|
|
220
380
|
|
|
221
381
|
## Documentation
|
|
222
382
|
|
|
@@ -228,15 +388,31 @@ in [Architecture](docs/ARCHITECTURE.md) and
|
|
|
228
388
|
| [Compatibility](docs/COMPATIBILITY.md) | [OpenCode V2](docs/opencode-v2.md) |
|
|
229
389
|
| [Agents & Skills](docs/agents/README.md) | [Platforms](docs/PLATFORMS.md) |
|
|
230
390
|
| [Release Process](docs/RELEASING.md) | [Branch Protection](docs/BRANCH-PROTECTION.md) |
|
|
231
|
-
| [Model Routing](docs/reference/model-routing.md) | [Env Vars](docs/reference/env-vars.md) · [Code Mode](docs/reference/code-mode.md) |
|
|
391
|
+
| [Model Routing](docs/reference/model-routing.md) | [Local Decision Router](docs/reference/local-decision-router.md) · [V2 Native Decisions](docs/reference/native-decisions.md) · [Offline Evaluation Protocol](docs/reference/offline-evaluation.md) · [Env Vars](docs/reference/env-vars.md) · [Code Mode](docs/reference/code-mode.md) |
|
|
232
392
|
| [Contributing](CONTRIBUTING.md) | [Roadmap](ROADMAP.md) · [Changelog](CHANGELOG.md) |
|
|
233
393
|
|
|
394
|
+
Memory writes through `pantheon-memory` are serialized, and failed writes are
|
|
395
|
+
reported as failures rather than as stored entries. Eval resources wait for
|
|
396
|
+
SQLite locks and close their connections; project-specific resources resolve
|
|
397
|
+
the current project root per request while preserving the trusted
|
|
398
|
+
`PANTHEON_HOME` fallback. See [Memory](docs/MEMORY.md) for store separation and
|
|
399
|
+
[MCP tools](docs/mcp-tools.md) for details.
|
|
400
|
+
|
|
234
401
|
The release install gate's tool canary loads the installed tarball's V2 plugin
|
|
235
402
|
entry under OpenCode 2.0.30 and verifies `hashline_edit` registration, Code Mode
|
|
236
403
|
visibility, and a bounded edit in an isolated project. It does not prove npm
|
|
237
404
|
publication or compatibility with untested host versions; details are in the
|
|
238
405
|
[release process](docs/RELEASING.md).
|
|
239
406
|
|
|
407
|
+
Generate beta release notes from commits since the latest prior beta tag with
|
|
408
|
+
`node scripts/versioning.mjs apply --beta --notes`. See the [release
|
|
409
|
+
procedure](docs/RELEASING.md) for details.
|
|
410
|
+
After the version bump, verify and rebuild the TUI workspace from the repository
|
|
411
|
+
root with `npm run typecheck --workspace=src/plugins/tui` and
|
|
412
|
+
`npm run build --workspace=src/plugins/tui`.
|
|
413
|
+
The maintainer-only `release` scope is excluded from public notes and their
|
|
414
|
+
Closed Issues references; see the [release-notes policy](docs/RELEASING.md#release-notes).
|
|
415
|
+
|
|
240
416
|
## Status
|
|
241
417
|
|
|
242
418
|
The manifests in this checkout express the version being prepared, not a
|
package/README.pt-BR.md
CHANGED
|
@@ -75,8 +75,26 @@ apenas — `init` → reiniciar → `/dispatch` → primeiro resultado — veja
|
|
|
75
75
|
documentar.
|
|
76
76
|
- **5 servidores MCP locais** para memória de projeto, persistência, recursos,
|
|
77
77
|
execução confinada de scripts e visão.
|
|
78
|
+
- **Um roteador de decisão seletivo e consultivo**, com resultados locais
|
|
79
|
+
estruturados e recomendações por turno quando habilitado. O egress direto
|
|
80
|
+
pertencente ao Pantheon é inativo; o egress nativo existe apenas na tool
|
|
81
|
+
explícita `pantheon_jev_decide` (só para o Zeus), que chama a API nativa de
|
|
82
|
+
Decisions do host (Jev/TypeSafe via OpenCode Console ou modelo configurado)
|
|
83
|
+
atrás do consentimento e dos limites de orçamento do usuário — ela nunca
|
|
84
|
+
despacha agentes, executa skills ou altera permissões. Veja a
|
|
85
|
+
[referência do roteador](docs/reference/local-decision-router.md) e o
|
|
86
|
+
[Decisions nativas (Jev)](docs/reference/native-decisions.md).
|
|
78
87
|
- **Uma TUI opcional**, com bloco de dispatch na sidebar e painel `/dispatch`
|
|
79
|
-
em largura total.
|
|
88
|
+
em largura total. A sidebar V2 mantém a versão do Pantheon, o preset/fonte
|
|
89
|
+
ativos, o estado do git e um bloco `Context` (tokens, medidor de percentual,
|
|
90
|
+
`$<gasto> gastos` e uma linha mutada `cache <n>% · <n.n> tok/s`); o rodapé
|
|
91
|
+
nativo do prompt segue intacto, e o Pantheon só acrescenta
|
|
92
|
+
`▸<preset> · ✦<n> ativos` enquanto há delegações rodando. A TUI não traz mais
|
|
93
|
+
painel de quota: para ver quota e uso de provedores dentro do OpenCode,
|
|
94
|
+
instale o plugin comunitário recomendado
|
|
95
|
+
[`@slkiser/opencode-quota`](https://github.com/slkiser/opencode-quota) — veja
|
|
96
|
+
[Quota & uso](docs/tui-v2-quota-providers.md). As tools `pantheon_cost` e
|
|
97
|
+
`pantheon_model` seguem funcionando sem alterações.
|
|
80
98
|
|
|
81
99
|
A memória MCP fica disponível para busca explícita: o coordenador consulta o
|
|
82
100
|
histórico uma vez quando ele pode mudar a tarefa e repassa apenas resultados
|