@massa-ai/opencode-plugin 1.26.0 → 1.27.0

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.
@@ -80,12 +80,9 @@ next_step: <string>
80
80
  - References: `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
81
81
 
82
82
  ## Model Hint
83
- This charter's `metadata.model_tier` (`deep`) is the fallback every host runs when dispatch-time
84
- model selection is unavailable. The `judge-with-debate` workflow additionally requests per-slot
85
- model diversity at dispatch time on hosts that support it — `workflows/judge-with-debate.md` is
86
- the single source for the current slot assignments, not this file. When dispatch-time selection
87
- is unavailable, every slot runs the charter default and the orchestrator records
88
- `DIVERSITY DEGRADED` per the workflow contract.
83
+ See `references/agent-orchestration.md` (Model Diversity Fallback): `metadata.model_tier`
84
+ (`deep`) is the per-slot fallback; `workflows/judge-with-debate.md` owns the live slot
85
+ assignments.
89
86
 
90
87
  ## Validation Sensors
91
88
  - Every criterion score carries an exact quotation from the artifact.
@@ -71,11 +71,8 @@ overall: weighted-mean
71
71
  - References: `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
72
72
 
73
73
  ## Model Hint
74
- This charter's `metadata.model_tier` (`deep`) is the fallback every host runs when dispatch-time
75
- model selection is unavailable. The `judge-with-debate` workflow additionally requests a specific
76
- model for this slot at dispatch time on hosts that support it — `workflows/judge-with-debate.md`
77
- is the single source for the current assignment, not this file. When dispatch-time selection is
78
- unavailable, the orchestrator records a diversity warning per the workflow contract.
74
+ See `references/agent-orchestration.md` (Model Diversity Fallback): `metadata.model_tier`
75
+ (`deep`) is the fallback; `workflows/judge-with-debate.md` owns the live model assignment.
79
76
 
80
77
  ## Validation Sensors
81
78
  - Output parses as YAML; weights sum to 1.0 (±0.001); every criterion carries id, name, weight, scale (min 1, max 5), rubric anchors for 1/3/5, and a non-empty checklist.
@@ -12,7 +12,7 @@ permission: { edit: deny, bash: { "pwd": "allow", "*": "deny" } }
12
12
  Answer codebase questions through the massa-ai semantic index, reading files only once the index has narrowed the target to one to three of them.
13
13
 
14
14
  ## Core Principle
15
- The user's codebase is **already indexed** by massa-ai. The first move on any question is to query the index, not to read files blindly. File reads are expensive in context; massa-ai index queries are not.
15
+ The user's codebase is **already indexed** by massa-ai. The first move on any question is to query the index, not read files blindly file reads are expensive in context; massa-ai index queries are not.
16
16
 
17
17
  ## Responsibilities
18
18
  - Resolve the current project: run `pwd`, match the basename against `list_projects`.
@@ -80,12 +80,9 @@ next_step: <string>
80
80
  - References: `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
81
81
 
82
82
  ## Model Hint
83
- This charter's `metadata.model_tier` (`deep`) is the fallback every host runs when dispatch-time
84
- model selection is unavailable. The `judge-with-debate` workflow additionally requests per-slot
85
- model diversity at dispatch time on hosts that support it — `workflows/judge-with-debate.md` is
86
- the single source for the current slot assignments, not this file. When dispatch-time selection
87
- is unavailable, every slot runs the charter default and the orchestrator records
88
- `DIVERSITY DEGRADED` per the workflow contract.
83
+ See `references/agent-orchestration.md` (Model Diversity Fallback): `metadata.model_tier`
84
+ (`deep`) is the per-slot fallback; `workflows/judge-with-debate.md` owns the live slot
85
+ assignments.
89
86
 
90
87
  ## Validation Sensors
91
88
  - Every criterion score carries an exact quotation from the artifact.
@@ -71,11 +71,8 @@ overall: weighted-mean
71
71
  - References: `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
72
72
 
73
73
  ## Model Hint
74
- This charter's `metadata.model_tier` (`deep`) is the fallback every host runs when dispatch-time
75
- model selection is unavailable. The `judge-with-debate` workflow additionally requests a specific
76
- model for this slot at dispatch time on hosts that support it — `workflows/judge-with-debate.md`
77
- is the single source for the current assignment, not this file. When dispatch-time selection is
78
- unavailable, the orchestrator records a diversity warning per the workflow contract.
74
+ See `references/agent-orchestration.md` (Model Diversity Fallback): `metadata.model_tier`
75
+ (`deep`) is the fallback; `workflows/judge-with-debate.md` owns the live model assignment.
79
76
 
80
77
  ## Validation Sensors
81
78
  - Output parses as YAML; weights sum to 1.0 (±0.001); every criterion carries id, name, weight, scale (min 1, max 5), rubric anchors for 1/3/5, and a non-empty checklist.
@@ -12,7 +12,7 @@ permission: { edit: deny, bash: { "pwd": "allow", "*": "deny" } }
12
12
  Answer codebase questions through the massa-ai semantic index, reading files only once the index has narrowed the target to one to three of them.
13
13
 
14
14
  ## Core Principle
15
- The user's codebase is **already indexed** by massa-ai. The first move on any question is to query the index, not to read files blindly. File reads are expensive in context; massa-ai index queries are not.
15
+ The user's codebase is **already indexed** by massa-ai. The first move on any question is to query the index, not read files blindly file reads are expensive in context; massa-ai index queries are not.
16
16
 
17
17
  ## Responsibilities
18
18
  - Resolve the current project: run `pwd`, match the basename against `list_projects`.
@@ -80,12 +80,9 @@ next_step: <string>
80
80
  - References: `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
81
81
 
82
82
  ## Model Hint
83
- This charter's `metadata.model_tier` (`deep`) is the fallback every host runs when dispatch-time
84
- model selection is unavailable. The `judge-with-debate` workflow additionally requests per-slot
85
- model diversity at dispatch time on hosts that support it — `workflows/judge-with-debate.md` is
86
- the single source for the current slot assignments, not this file. When dispatch-time selection
87
- is unavailable, every slot runs the charter default and the orchestrator records
88
- `DIVERSITY DEGRADED` per the workflow contract.
83
+ See `references/agent-orchestration.md` (Model Diversity Fallback): `metadata.model_tier`
84
+ (`deep`) is the per-slot fallback; `workflows/judge-with-debate.md` owns the live slot
85
+ assignments.
89
86
 
90
87
  ## Validation Sensors
91
88
  - Every criterion score carries an exact quotation from the artifact.
@@ -71,11 +71,8 @@ overall: weighted-mean
71
71
  - References: `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
72
72
 
73
73
  ## Model Hint
74
- This charter's `metadata.model_tier` (`deep`) is the fallback every host runs when dispatch-time
75
- model selection is unavailable. The `judge-with-debate` workflow additionally requests a specific
76
- model for this slot at dispatch time on hosts that support it — `workflows/judge-with-debate.md`
77
- is the single source for the current assignment, not this file. When dispatch-time selection is
78
- unavailable, the orchestrator records a diversity warning per the workflow contract.
74
+ See `references/agent-orchestration.md` (Model Diversity Fallback): `metadata.model_tier`
75
+ (`deep`) is the fallback; `workflows/judge-with-debate.md` owns the live model assignment.
79
76
 
80
77
  ## Validation Sensors
81
78
  - Output parses as YAML; weights sum to 1.0 (±0.001); every criterion carries id, name, weight, scale (min 1, max 5), rubric anchors for 1/3/5, and a non-empty checklist.
@@ -12,7 +12,7 @@ permission: { edit: deny, bash: { "pwd": "allow", "*": "deny" } }
12
12
  Answer codebase questions through the massa-ai semantic index, reading files only once the index has narrowed the target to one to three of them.
13
13
 
14
14
  ## Core Principle
15
- The user's codebase is **already indexed** by massa-ai. The first move on any question is to query the index, not to read files blindly. File reads are expensive in context; massa-ai index queries are not.
15
+ The user's codebase is **already indexed** by massa-ai. The first move on any question is to query the index, not read files blindly file reads are expensive in context; massa-ai index queries are not.
16
16
 
17
17
  ## Responsibilities
18
18
  - Resolve the current project: run `pwd`, match the basename against `list_projects`.
@@ -80,12 +80,9 @@ next_step: <string>
80
80
  - References: `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
81
81
 
82
82
  ## Model Hint
83
- This charter's `metadata.model_tier` (`deep`) is the fallback every host runs when dispatch-time
84
- model selection is unavailable. The `judge-with-debate` workflow additionally requests per-slot
85
- model diversity at dispatch time on hosts that support it — `workflows/judge-with-debate.md` is
86
- the single source for the current slot assignments, not this file. When dispatch-time selection
87
- is unavailable, every slot runs the charter default and the orchestrator records
88
- `DIVERSITY DEGRADED` per the workflow contract.
83
+ See `references/agent-orchestration.md` (Model Diversity Fallback): `metadata.model_tier`
84
+ (`deep`) is the per-slot fallback; `workflows/judge-with-debate.md` owns the live slot
85
+ assignments.
89
86
 
90
87
  ## Validation Sensors
91
88
  - Every criterion score carries an exact quotation from the artifact.
@@ -71,11 +71,8 @@ overall: weighted-mean
71
71
  - References: `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
72
72
 
73
73
  ## Model Hint
74
- This charter's `metadata.model_tier` (`deep`) is the fallback every host runs when dispatch-time
75
- model selection is unavailable. The `judge-with-debate` workflow additionally requests a specific
76
- model for this slot at dispatch time on hosts that support it — `workflows/judge-with-debate.md`
77
- is the single source for the current assignment, not this file. When dispatch-time selection is
78
- unavailable, the orchestrator records a diversity warning per the workflow contract.
74
+ See `references/agent-orchestration.md` (Model Diversity Fallback): `metadata.model_tier`
75
+ (`deep`) is the fallback; `workflows/judge-with-debate.md` owns the live model assignment.
79
76
 
80
77
  ## Validation Sensors
81
78
  - Output parses as YAML; weights sum to 1.0 (±0.001); every criterion carries id, name, weight, scale (min 1, max 5), rubric anchors for 1/3/5, and a non-empty checklist.
@@ -12,7 +12,7 @@ permission: { edit: deny, bash: { "pwd": "allow", "*": "deny" } }
12
12
  Answer codebase questions through the massa-ai semantic index, reading files only once the index has narrowed the target to one to three of them.
13
13
 
14
14
  ## Core Principle
15
- The user's codebase is **already indexed** by massa-ai. The first move on any question is to query the index, not to read files blindly. File reads are expensive in context; massa-ai index queries are not.
15
+ The user's codebase is **already indexed** by massa-ai. The first move on any question is to query the index, not read files blindly file reads are expensive in context; massa-ai index queries are not.
16
16
 
17
17
  ## Responsibilities
18
18
  - Resolve the current project: run `pwd`, match the basename against `list_projects`.
@@ -80,12 +80,9 @@ next_step: <string>
80
80
  - References: `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
81
81
 
82
82
  ## Model Hint
83
- This charter's `metadata.model_tier` (`deep`) is the fallback every host runs when dispatch-time
84
- model selection is unavailable. The `judge-with-debate` workflow additionally requests per-slot
85
- model diversity at dispatch time on hosts that support it — `workflows/judge-with-debate.md` is
86
- the single source for the current slot assignments, not this file. When dispatch-time selection
87
- is unavailable, every slot runs the charter default and the orchestrator records
88
- `DIVERSITY DEGRADED` per the workflow contract.
83
+ See `references/agent-orchestration.md` (Model Diversity Fallback): `metadata.model_tier`
84
+ (`deep`) is the per-slot fallback; `workflows/judge-with-debate.md` owns the live slot
85
+ assignments.
89
86
 
90
87
  ## Validation Sensors
91
88
  - Every criterion score carries an exact quotation from the artifact.
@@ -71,11 +71,8 @@ overall: weighted-mean
71
71
  - References: `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
72
72
 
73
73
  ## Model Hint
74
- This charter's `metadata.model_tier` (`deep`) is the fallback every host runs when dispatch-time
75
- model selection is unavailable. The `judge-with-debate` workflow additionally requests a specific
76
- model for this slot at dispatch time on hosts that support it — `workflows/judge-with-debate.md`
77
- is the single source for the current assignment, not this file. When dispatch-time selection is
78
- unavailable, the orchestrator records a diversity warning per the workflow contract.
74
+ See `references/agent-orchestration.md` (Model Diversity Fallback): `metadata.model_tier`
75
+ (`deep`) is the fallback; `workflows/judge-with-debate.md` owns the live model assignment.
79
76
 
80
77
  ## Validation Sensors
81
78
  - Output parses as YAML; weights sum to 1.0 (±0.001); every criterion carries id, name, weight, scale (min 1, max 5), rubric anchors for 1/3/5, and a non-empty checklist.
@@ -12,7 +12,7 @@ permission: { edit: deny, bash: { "pwd": "allow", "*": "deny" } }
12
12
  Answer codebase questions through the massa-ai semantic index, reading files only once the index has narrowed the target to one to three of them.
13
13
 
14
14
  ## Core Principle
15
- The user's codebase is **already indexed** by massa-ai. The first move on any question is to query the index, not to read files blindly. File reads are expensive in context; massa-ai index queries are not.
15
+ The user's codebase is **already indexed** by massa-ai. The first move on any question is to query the index, not read files blindly file reads are expensive in context; massa-ai index queries are not.
16
16
 
17
17
  ## Responsibilities
18
18
  - Resolve the current project: run `pwd`, match the basename against `list_projects`.
@@ -80,12 +80,9 @@ next_step: <string>
80
80
  - References: `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
81
81
 
82
82
  ## Model Hint
83
- This charter's `metadata.model_tier` (`deep`) is the fallback every host runs when dispatch-time
84
- model selection is unavailable. The `judge-with-debate` workflow additionally requests per-slot
85
- model diversity at dispatch time on hosts that support it — `workflows/judge-with-debate.md` is
86
- the single source for the current slot assignments, not this file. When dispatch-time selection
87
- is unavailable, every slot runs the charter default and the orchestrator records
88
- `DIVERSITY DEGRADED` per the workflow contract.
83
+ See `references/agent-orchestration.md` (Model Diversity Fallback): `metadata.model_tier`
84
+ (`deep`) is the per-slot fallback; `workflows/judge-with-debate.md` owns the live slot
85
+ assignments.
89
86
 
90
87
  ## Validation Sensors
91
88
  - Every criterion score carries an exact quotation from the artifact.
@@ -71,11 +71,8 @@ overall: weighted-mean
71
71
  - References: `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
72
72
 
73
73
  ## Model Hint
74
- This charter's `metadata.model_tier` (`deep`) is the fallback every host runs when dispatch-time
75
- model selection is unavailable. The `judge-with-debate` workflow additionally requests a specific
76
- model for this slot at dispatch time on hosts that support it — `workflows/judge-with-debate.md`
77
- is the single source for the current assignment, not this file. When dispatch-time selection is
78
- unavailable, the orchestrator records a diversity warning per the workflow contract.
74
+ See `references/agent-orchestration.md` (Model Diversity Fallback): `metadata.model_tier`
75
+ (`deep`) is the fallback; `workflows/judge-with-debate.md` owns the live model assignment.
79
76
 
80
77
  ## Validation Sensors
81
78
  - Output parses as YAML; weights sum to 1.0 (±0.001); every criterion carries id, name, weight, scale (min 1, max 5), rubric anchors for 1/3/5, and a non-empty checklist.
@@ -12,7 +12,7 @@ permission: { edit: deny, bash: { "pwd": "allow", "*": "deny" } }
12
12
  Answer codebase questions through the massa-ai semantic index, reading files only once the index has narrowed the target to one to three of them.
13
13
 
14
14
  ## Core Principle
15
- The user's codebase is **already indexed** by massa-ai. The first move on any question is to query the index, not to read files blindly. File reads are expensive in context; massa-ai index queries are not.
15
+ The user's codebase is **already indexed** by massa-ai. The first move on any question is to query the index, not read files blindly file reads are expensive in context; massa-ai index queries are not.
16
16
 
17
17
  ## Responsibilities
18
18
  - Resolve the current project: run `pwd`, match the basename against `list_projects`.
@@ -80,12 +80,9 @@ next_step: <string>
80
80
  - References: `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
81
81
 
82
82
  ## Model Hint
83
- This charter's `metadata.model_tier` (`deep`) is the fallback every host runs when dispatch-time
84
- model selection is unavailable. The `judge-with-debate` workflow additionally requests per-slot
85
- model diversity at dispatch time on hosts that support it — `workflows/judge-with-debate.md` is
86
- the single source for the current slot assignments, not this file. When dispatch-time selection
87
- is unavailable, every slot runs the charter default and the orchestrator records
88
- `DIVERSITY DEGRADED` per the workflow contract.
83
+ See `references/agent-orchestration.md` (Model Diversity Fallback): `metadata.model_tier`
84
+ (`deep`) is the per-slot fallback; `workflows/judge-with-debate.md` owns the live slot
85
+ assignments.
89
86
 
90
87
  ## Validation Sensors
91
88
  - Every criterion score carries an exact quotation from the artifact.
@@ -71,11 +71,8 @@ overall: weighted-mean
71
71
  - References: `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
72
72
 
73
73
  ## Model Hint
74
- This charter's `metadata.model_tier` (`deep`) is the fallback every host runs when dispatch-time
75
- model selection is unavailable. The `judge-with-debate` workflow additionally requests a specific
76
- model for this slot at dispatch time on hosts that support it — `workflows/judge-with-debate.md`
77
- is the single source for the current assignment, not this file. When dispatch-time selection is
78
- unavailable, the orchestrator records a diversity warning per the workflow contract.
74
+ See `references/agent-orchestration.md` (Model Diversity Fallback): `metadata.model_tier`
75
+ (`deep`) is the fallback; `workflows/judge-with-debate.md` owns the live model assignment.
79
76
 
80
77
  ## Validation Sensors
81
78
  - Output parses as YAML; weights sum to 1.0 (±0.001); every criterion carries id, name, weight, scale (min 1, max 5), rubric anchors for 1/3/5, and a non-empty checklist.
@@ -12,7 +12,7 @@ permission: { edit: deny, bash: { "pwd": "allow", "*": "deny" } }
12
12
  Answer codebase questions through the massa-ai semantic index, reading files only once the index has narrowed the target to one to three of them.
13
13
 
14
14
  ## Core Principle
15
- The user's codebase is **already indexed** by massa-ai. The first move on any question is to query the index, not to read files blindly. File reads are expensive in context; massa-ai index queries are not.
15
+ The user's codebase is **already indexed** by massa-ai. The first move on any question is to query the index, not read files blindly file reads are expensive in context; massa-ai index queries are not.
16
16
 
17
17
  ## Responsibilities
18
18
  - Resolve the current project: run `pwd`, match the basename against `list_projects`.
@@ -80,12 +80,9 @@ next_step: <string>
80
80
  - References: `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
81
81
 
82
82
  ## Model Hint
83
- This charter's `metadata.model_tier` (`deep`) is the fallback every host runs when dispatch-time
84
- model selection is unavailable. The `judge-with-debate` workflow additionally requests per-slot
85
- model diversity at dispatch time on hosts that support it — `workflows/judge-with-debate.md` is
86
- the single source for the current slot assignments, not this file. When dispatch-time selection
87
- is unavailable, every slot runs the charter default and the orchestrator records
88
- `DIVERSITY DEGRADED` per the workflow contract.
83
+ See `references/agent-orchestration.md` (Model Diversity Fallback): `metadata.model_tier`
84
+ (`deep`) is the per-slot fallback; `workflows/judge-with-debate.md` owns the live slot
85
+ assignments.
89
86
 
90
87
  ## Validation Sensors
91
88
  - Every criterion score carries an exact quotation from the artifact.
@@ -71,11 +71,8 @@ overall: weighted-mean
71
71
  - References: `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
72
72
 
73
73
  ## Model Hint
74
- This charter's `metadata.model_tier` (`deep`) is the fallback every host runs when dispatch-time
75
- model selection is unavailable. The `judge-with-debate` workflow additionally requests a specific
76
- model for this slot at dispatch time on hosts that support it — `workflows/judge-with-debate.md`
77
- is the single source for the current assignment, not this file. When dispatch-time selection is
78
- unavailable, the orchestrator records a diversity warning per the workflow contract.
74
+ See `references/agent-orchestration.md` (Model Diversity Fallback): `metadata.model_tier`
75
+ (`deep`) is the fallback; `workflows/judge-with-debate.md` owns the live model assignment.
79
76
 
80
77
  ## Validation Sensors
81
78
  - Output parses as YAML; weights sum to 1.0 (±0.001); every criterion carries id, name, weight, scale (min 1, max 5), rubric anchors for 1/3/5, and a non-empty checklist.
@@ -12,7 +12,7 @@ permission: { edit: deny, bash: { "pwd": "allow", "*": "deny" } }
12
12
  Answer codebase questions through the massa-ai semantic index, reading files only once the index has narrowed the target to one to three of them.
13
13
 
14
14
  ## Core Principle
15
- The user's codebase is **already indexed** by massa-ai. The first move on any question is to query the index, not to read files blindly. File reads are expensive in context; massa-ai index queries are not.
15
+ The user's codebase is **already indexed** by massa-ai. The first move on any question is to query the index, not read files blindly file reads are expensive in context; massa-ai index queries are not.
16
16
 
17
17
  ## Responsibilities
18
18
  - Resolve the current project: run `pwd`, match the basename against `list_projects`.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@massa-ai/opencode-plugin",
3
- "version": "1.26.0",
3
+ "version": "1.27.0",
4
4
  "description": "massa-ai plugin for OpenCode - Semantic code search, memory, and context compression",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",
@@ -22,8 +22,8 @@
22
22
  "dependencies": {
23
23
  "@opencode-ai/plugin": "^1.2.15",
24
24
  "@opencode-ai/sdk": "^1.2.15",
25
- "@massa-ai/core": "^1.26.0",
26
- "@massa-ai/shared": "^1.26.0"
25
+ "@massa-ai/core": "^1.27.0",
26
+ "@massa-ai/shared": "^1.27.0"
27
27
  },
28
28
  "devDependencies": {
29
29
  "@types/node": "^22.10.5",