pantheon-opencode 1.6.3-beta.15 → 1.6.3-beta.16

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 CHANGED
@@ -10,6 +10,13 @@ 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
+ ## [v1.6.3-beta.16] - 2026-11-05
14
+
15
+ ## 🆕 What's New
16
+ - `prompt-refinery` skill: a vague multi-part request is refined into a structured contract (objective, slices, acceptance criteria, open questions with defaults) shown for confirm-or-adjust BEFORE executing — one planning turn on the session model.
17
+ - Skills mode offers the full local catalog + host skills — the lexical prefilter could drop the exact skill you described (codemap → none 0.88). candidateSource still reports the pool.
18
+ - nyx returns to observability & cost analytics (owner intent), prometheus drops those words — the routing you expected now matches the catalog.
19
+
13
20
  ## [v1.6.3-beta.15] - 2026-11-05
14
21
 
15
22
  ## 🆕 What's New
package/README.md CHANGED
@@ -93,7 +93,7 @@ see [Quick Start](docs/QUICKSTART.md).
93
93
 
94
94
  - **14 specialized agents** with one orchestrator, implementation specialists,
95
95
  a quality gate, and supporting roles.
96
- - **20 skills** and reusable instructions for planning, building, reviewing,
96
+ - **21 skills** and reusable instructions for planning, building, reviewing,
97
97
  and documenting work.
98
98
  - **5 local MCP servers** for project memory, persistence, resources, confined
99
99
  script execution, and vision.
package/README.pt-BR.md CHANGED
@@ -71,7 +71,7 @@ apenas — `init` → reiniciar → `/dispatch` → primeiro resultado — veja
71
71
 
72
72
  - **14 agentes especializados**, com um orquestrador, especialistas de
73
73
  implementação, um gate de qualidade e papéis de apoio.
74
- - **20 skills** e instruções reutilizáveis para planejar, construir, revisar e
74
+ - **21 skills** e instruções reutilizáveis para planejar, construir, revisar e
75
75
  documentar.
76
76
  - **5 servidores MCP locais** para memória de projeto, persistência, recursos,
77
77
  execução confinada de scripts e visão.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "pantheon-opencode",
3
- "version": "1.6.3-beta.15",
3
+ "version": "1.6.3-beta.16",
4
4
  "description": "Multi-agent orchestration for OpenCode \u2014 14 specialized agents, TDD, Themis review gates.",
5
5
  "type": "module",
6
6
  "workspaces": [
package/plugin.json CHANGED
@@ -1,9 +1,9 @@
1
1
  {
2
2
  "name": "pantheon",
3
3
  "publisher": "ils15",
4
- "version": "1.6.3-beta.15",
4
+ "version": "1.6.3-beta.16",
5
5
  "displayName": "Pantheon",
6
- "description": "Conductor-Delegate orchestration platform with 14 specialized agents, 20 skills, and OpenCode support.",
6
+ "description": "Conductor-Delegate orchestration platform with 14 specialized agents, 21 skills, and OpenCode support.",
7
7
  "agents": "./src/agents",
8
8
  "skills": "./src/skills",
9
9
  "instructions": "./src/instructions",
package/pyproject.toml CHANGED
@@ -4,7 +4,7 @@ build-backend = "setuptools.backends._legacy:_Backend"
4
4
 
5
5
  [project]
6
6
  name = "pantheon"
7
- version = "1.6.3-beta.15"
7
+ version = "1.6.3-beta.16"
8
8
  description = "Multi-agent orchestration framework"
9
9
  requires-python = ">=3.11"
10
10
  # Python sources under src/mcp/ import fastmcp/pydantic at runtime, but those
@@ -93,7 +93,7 @@ export async function runInteractiveInstall({
93
93
 
94
94
  const componentOptions = [
95
95
  { label: 'agents', value: 'agents', hint: 'Agent configurations and routing (14 agents)' },
96
- { label: 'skills', value: 'skills', hint: `Reusable skill workflows (${20} skills)` },
96
+ { label: 'skills', value: 'skills', hint: `Reusable skill workflows (${21} skills)` },
97
97
  { label: 'instructions', value: 'instructions', hint: 'AGENTS.md and instructional files' },
98
98
  { label: 'prompts', value: 'prompts', hint: 'Prompt templates for agents' },
99
99
  { label: 'commands', value: 'commands', hint: 'OpenCode command shortcuts' },
@@ -73,14 +73,14 @@ function callDecisions(modelRef, state) {
73
73
  { value: 'athena', description: 'planning and architecture' },
74
74
  { value: 'themis', description: 'security, review and compliance gates' },
75
75
  { value: 'hermes', description: 'backend implementation' },
76
- { value: 'prometheus', description: 'infrastructure, CI and pipelines' },
76
+ { value: 'prometheus', description: 'infrastructure, Docker, CI and model providers' },
77
77
  { value: 'hephaestus', description: 'AI tooling and model integration' },
78
78
  { value: 'demeter', description: 'databases and data layer' },
79
79
  { value: 'gaia', description: 'remote sensing and geospatial' },
80
80
  { value: 'iris', description: 'GitHub operations and automation' },
81
81
  { value: 'aphrodite', description: 'UI and frontend craft' },
82
82
  { value: 'mnemosyne', description: 'memory curation and recall' },
83
- { value: 'nyx', description: 'chaos and adversarial testing' },
83
+ { value: 'nyx', description: 'observability, tracing and cost analytics; chaos testing' },
84
84
  { value: 'talos', description: 'hotfix express lane - small direct fixes, no ceremony' },
85
85
  { value: 'none', description: 'no specialist fits' },
86
86
  ],
package/skills-lock.json CHANGED
@@ -10,6 +10,7 @@
10
10
  "src/skills/incremental-implementation/SKILL.md": "7065ddb45da3c6b6751de07f290e92e6cb072e949a2e3aaae13ee7762f0a70fc",
11
11
  "src/skills/loop-engineering/SKILL.md": "f804e545821b9cca8fe0ec517307ed902446f28c2ca8ff9194c0f987cf7229e3",
12
12
  "src/skills/memory-bank/SKILL.md": "6c27623e5588b7ba44fbd0ea88e5061ed36894e1c7cbc88e50f003c2b463d9ff",
13
+ "src/skills/prompt-refinery/SKILL.md": "d2ed35b1d74ee1caef07b572ee7771e19019a9bc6ad40ea71c4b32dbccd256d9",
13
14
  "src/skills/reflect/SKILL.md": "4c7608c2a55cb8a50ac90fc0e2446bdf25e7914b1748cb7731c311d13c29dfdd",
14
15
  "src/skills/security-hardening/SKILL.md": "6d637e122421f7bc3b751f04854ad343a5a5d35249458bc8939233138fd3f20d",
15
16
  "src/skills/session-goal/SKILL.md": "2911157c8e020f62ca015a73a46f5427f41da71c83e624d6a1cecf7d64c64aea",
package/src/agents/nyx.md CHANGED
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: nyx
3
- description: "Chaos & adversarial testing specialist — fuzzing with malformed payloads, hostile-input review, boundary exploration, chaos scenarios. Analysis-only: finds the crashes and the holes, never fixes them. Routes fixes through Zeus."
3
+ description: "Observability & cost analytics specialist — OpenTelemetry tracing, per-agent cost dashboards, anomaly detection; also chaos and adversarial testing (fuzzing, hostile inputs, boundaries). Analysis-only: never fixes, routes through Zeus."
4
4
  mode: all
5
5
  reasoning_effort: low
6
6
  permission:
@@ -61,22 +61,19 @@ agent.
61
61
 
62
62
  ## Core Capabilities
63
63
 
64
- ### 1. Fuzzing & Malformed Payloads
65
- - Feed parsers, endpoints and file handlers truncated, oversized, and
66
- malformed inputs (wrong types, deep nesting, encoding tricks, NaN/dates)
67
- - Record the exact payload that broke the handler, not just the symptom
68
- - Distinguish crashes, hangs, silent corruption, and unvalidated accept
64
+ ### 1. Observability & Tracing
65
+ - OpenTelemetry distributed tracing across services and agent pipelines
66
+ - Per-agent cost/latency dashboards (token usage attribution, spans)
67
+ - Anomaly detection: latency and spend outliers, error-rate cliffs
69
68
 
70
- ### 2. Hostile-Input Review
71
- - Read validation paths the way an attacker would: injection seams, path
72
- traversal, race windows, trust boundaries crossed without re-validation
73
- - Complement Themis (security gate): Nyx attacks the RUNNING behavior;
74
- Themis reviews the code — send code-level findings to Zeus for Themis
69
+ ### 2. Adversarial & Chaos (secondary)
70
+ - Fuzzing with malformed payloads; hostile-input boundary exploration
71
+ - Chaos scenarios for the monitored paths; findings feed the dashboards
72
+ - Complement Themis (security gate): Nyx attacks the RUNNING behavior
75
73
 
76
- ### 3. Boundary & Chaos Exploration
77
- - Drive boundaries deliberately: empty sets, max sizes, unicode extremes,
78
- concurrent duplicates, clock skew, network-less runs
79
- - Report which boundaries the code defends and which it ignores
74
+ ### 3. Cost & Metric Review
75
+ - Token/cost attribution per agent and per phase (feeds `pantheon_cost`)
76
+ - Alert thresholds and anomaly reports on the agent pipeline
80
77
 
81
78
  ## Handoffs
82
79
  - **Discovery:** Send discovery needs and any findings to Zeus. Zeus may dispatch to targets; only root Athena/Hermes sessions may call @apollo directly. Child sessions must not dispatch another Pantheon agent.
@@ -22,6 +22,7 @@ skills:
22
22
  - agent-coordination
23
23
  - artifact-management
24
24
  - auto-continue
25
+ - prompt-refinery
25
26
  - codemap
26
27
  - context-compression
27
28
  - incremental-implementation
@@ -93,6 +94,18 @@ call before firing it.
93
94
  cheap and typed, an MCP call is the LAST resort for state the session
94
95
  cannot reconstruct.
95
96
 
97
+ ## Vague multi-part request? Refine into a contract first
98
+
99
+ When the user's request spans multiple concerns without explicit acceptance
100
+ criteria (refactor + fix + redesign in one paragraph), refine it into a
101
+ structured contract BEFORE executing: objective, numbered scope slices,
102
+ acceptance criteria per slice, deliverables, and open questions with your
103
+ recommended defaults. Load `skill: prompt-refinery` for the shape and rules.
104
+ Show the contract once for confirm-or-adjust — silence proceeds with the
105
+ stated defaults — then route the confirmed slices through the normal ladder.
106
+ One refinement turn on the session model; never a dialogue, never a Jev call
107
+ (decision models answer scalars, they do not write prose).
108
+
96
109
  ## Missing capability? Find a skill before inventing one
97
110
 
98
111
  The skill-discovery ladder — installed pool first, ecosystem second, and the user always owns the install:
@@ -585,11 +585,15 @@ export function prepareJevPresetRequest(
585
585
  return { ok: true, request: Object.freeze(request) }
586
586
  }
587
587
 
588
- const shortlist = selectPantheonSkills(state).skillIds
588
+ // Field report beta.15 §skills: the lexical prefilter dropped the exact
589
+ // skill the state described (codemap → none 0.88 from a prefiltered pool).
590
+ // The local catalog is 12 entries and the choice bound is 24 — recall beats
591
+ // a filter that saves half of $0.00003. The full local catalog + host
592
+ // skills always ride; `candidateSource` keeps reporting which pool the
593
+ // caller got.
589
594
  const hostHasSkills = Array.isArray(hostSkills) && hostSkills.length > 0
590
- const candidateSource: JevSkillCandidateSource =
591
- shortlist.length > 0 ? 'prefilter' : hostHasSkills ? 'host-skills' : 'full-catalog'
592
- const pool = shortlist.length > 0 ? shortlist : CATALOG_SKILL_IDS
595
+ const candidateSource: JevSkillCandidateSource = hostHasSkills ? 'host-skills' : 'full-catalog'
596
+ const pool = CATALOG_SKILL_IDS
593
597
  const descriptions = new Map(PANTHEON_SKILL_CATALOG.map((entry) => [entry.id, entry.description]))
594
598
  const request = {
595
599
  model: route.model,
@@ -53,10 +53,14 @@ export const PANTHEON_AGENT_CATALOG: readonly DecisionCatalogEntry[] = Object.fr
53
53
  { id: 'themis', description: 'Quality and security review gate.' },
54
54
  {
55
55
  id: 'prometheus',
56
- description: 'Infrastructure, Docker, CI, observability and tracing, model providers.',
56
+ description: 'Infrastructure, Docker, CI, model providers and cloud costs.',
57
57
  },
58
58
  { id: 'hephaestus', description: 'AI pipelines: LangChain, RAG, vector stores.' },
59
- { id: 'nyx', description: 'Chaos and adversarial testing: fuzzing, hostile inputs, boundaries.' },
59
+ {
60
+ id: 'nyx',
61
+ description:
62
+ 'Observability and cost analytics: tracing, per-agent metrics; chaos and fuzz testing.',
63
+ },
60
64
  { id: 'gaia', description: 'Remote sensing and geospatial analysis.' },
61
65
  { id: 'iris', description: 'GitHub branches, pull requests, issues, releases.' },
62
66
  { id: 'mnemosyne', description: 'Memory bank and ADR authoring on request.' },
@@ -367,7 +367,7 @@ async function readChangelogForBundle(bundleUrl) {
367
367
  }
368
368
  /** The ambient build-time version, or null outside a tsdown build. */
369
369
  function embeddedVersion() {
370
- return "1.6.3-beta.14";
370
+ return "1.6.3-beta.15";
371
371
  }
372
372
  /**
373
373
  * Resolve the running Pantheon version for the what's-new window: the plugin
@@ -3752,7 +3752,7 @@ function Sidebar(props) {
3752
3752
  setProp(_el$12, "width", "100%");
3753
3753
  setProp(_el$12, "padding", 1);
3754
3754
  setProp(_el$13, "attributes", 1);
3755
- insert(_el$13, `Pantheon v1.6.3-beta.14`);
3755
+ insert(_el$13, `Pantheon v1.6.3-beta.15`);
3756
3756
  insert(_el$14, () => presetHeaderLine(model.preset().name ?? "", model.provider()));
3757
3757
  insert(_el$12, createComponent(Show, {
3758
3758
  get when() {
@@ -4473,7 +4473,7 @@ function HomeStatus(props) {
4473
4473
  const muted = () => props.context.theme?.text?.muted ?? props.context.theme?.text?.base;
4474
4474
  return (() => {
4475
4475
  var _el$72 = createElement("text");
4476
- insert(_el$72, () => `Pantheon v1.6.3-beta.14${preset().name ? ` ▸ ${preset().name}` : ""}`);
4476
+ insert(_el$72, () => `Pantheon v1.6.3-beta.15${preset().name ? ` ▸ ${preset().name}` : ""}`);
4477
4477
  effect((_$p) => setProp(_el$72, "fg", muted(), _$p));
4478
4478
  return _el$72;
4479
4479
  })();
@@ -167,7 +167,7 @@ async function detectVersion(api) {
167
167
  if (ver) return ver;
168
168
  }
169
169
  } catch {}
170
- return "1.6.3-beta.14";
170
+ return "1.6.3-beta.15";
171
171
  }
172
172
  /**
173
173
  * usage-bar — AI subscription usage gauge for the opencode TUI.
@@ -1,12 +1,12 @@
1
1
  {
2
2
  "name": "pantheon-tui",
3
- "version": "1.6.3-beta.15",
3
+ "version": "1.6.3-beta.16",
4
4
  "lockfileVersion": 3,
5
5
  "requires": true,
6
6
  "packages": {
7
7
  "": {
8
8
  "name": "pantheon-tui",
9
- "version": "1.6.3-beta.15",
9
+ "version": "1.6.3-beta.16",
10
10
  "license": "MIT",
11
11
  "dependencies": {
12
12
  "@opencode-ai/plugin": "1.18.33",
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "name": "pantheon-tui",
3
3
  "type": "module",
4
- "version": "1.6.3-beta.15",
4
+ "version": "1.6.3-beta.16",
5
5
  "description": "Pantheon TUI plugin — V1 rich sidebar and usage gauges; native V2 status, session and delegation sidebar",
6
6
  "license": "MIT",
7
7
  "engines": {
package/src/routing.yml CHANGED
@@ -177,6 +177,7 @@ agents:
177
177
  - artifact-management
178
178
  - auto-continue
179
179
  - codemap
180
+ - prompt-refinery
180
181
  - context-compression
181
182
  - incremental-implementation
182
183
  - loop-engineering
@@ -4,7 +4,7 @@
4
4
 
5
5
  Skills are reference modules loaded on demand by agents. Each skill provides domain-specific knowledge — architecture patterns, security checklists, optimization strategies, and implementation guides. Agents load skills when their task matches the skill's description, keeping context focused and token-efficient.
6
6
 
7
- There are **20 skills** divided into **5 domains**.
7
+ There are **21 skills** divided into **5 domains**.
8
8
 
9
9
  ## Skills by Domain
10
10
 
@@ -0,0 +1,41 @@
1
+ ---
2
+ name: prompt-refinery
3
+ description: "Turn a rough, vague, or one-line request into a structured execution contract (objective, scope slices, acceptance criteria, deliverables, open questions) shown to the user BEFORE executing. Use when a request spans multiple concerns or lacks explicit acceptance criteria."
4
+ ---
5
+
6
+ # Prompt Refinery
7
+
8
+ > **A vague request executes expensively and wrong. Refine it into a contract, show the contract, then execute what was confirmed.**
9
+
10
+ ---
11
+
12
+ ## When this fires
13
+
14
+ - The request spans multiple concerns ("refatora o dashboard, corrige os cálculos, melhora a UI") with no explicit acceptance criteria.
15
+ - The request names a desired OUTCOME but not the slices, nomenclature, data sources, or quality bar.
16
+ - The user pastes a long context dump and asks for "melhorar/refatorar/revisar" without structure.
17
+
18
+ A one-line bounded fix ("troque essa cor", "corrija esse typo") does NOT fire this skill — execute directly.
19
+
20
+ ---
21
+
22
+ ## The contract shape (the rewrite target)
23
+
24
+ Produce ALL of the following sections, filling from the request and marking real gaps as open questions — never invent requirements silently:
25
+
26
+ 1. **Objetivo do projeto** — one paragraph: what changes and why.
27
+ 2. **Escopo em fatias numeradas** — each slice independently verifiable (audit/corrections; architecture/IA; nomenclature/statistics; UI/UX; …). Slices the user did not ask for go under "fora de escopo", not here.
28
+ 3. **Critérios de aceite por fatia** — testable statements ("toda moeda passa por Decimal; nenhum float em valor monetário"), not vibes.
29
+ 4. **Entregáveis esperados** — the concrete artifacts (report, route map, dictionary, implementation).
30
+ 5. **Perguntas abertas** — the gaps that change the plan, with your recommended default for each so silence means "proceed with the default".
31
+ 6. **Glossário/nomenclatura proposta** — when the domain has ambiguous terms, propose the canonical names up front.
32
+
33
+ ---
34
+
35
+ ## Operating rules
36
+
37
+ - **Show, then execute.** The refined contract is presented to the user for confirm-or-adjust BEFORE implementation — one confirmation, not a dialogue. Silence or "ok" proceeds with the defaults stated in Perguntas abertas.
38
+ - **Domain mapping stays the ladder's**: after confirmation, slices route through the normal discovery ladder (local selector → Jev → specialist dispatch). The contract is the SPEC, not the dispatcher.
39
+ - **Preserve the user's language** (a PT-BR request refines into PT-BR).
40
+ - **One refinement turn.** The rewrite is a single planning pass on the session model — no extra provider call, no Jev needed for the rewrite itself (decision models answer typed scalars, they do not write prose).
41
+ - **Cost honesty**: the refinement costs roughly one planning turn (~1–4K tokens each way). The expensive thing is executing a mis-specified request; this skill buys that back.