@chankov/agent-fleet 0.0.1 → 0.0.3
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/.claude/commands/doctor-agent-fleet.md +1 -1
- package/.claude/commands/setup-agent-fleet.md +4 -4
- package/.opencode/commands/af-doctor-agent-fleet.md +2 -0
- package/.opencode/commands/af-setup-agent-fleet.md +1 -1
- package/.pi/agents/model-profiles.yaml +12 -12
- package/.pi/agents/peers.yaml +26 -22
- package/.pi/agents/teams.yaml +2 -2
- package/.pi/harnesses/agent-hub/README.md +57 -4
- package/.pi/harnesses/agent-hub/index.ts +236 -80
- package/.pi/harnesses/agent-hub/research-retention.js +34 -0
- package/.pi/harnesses/ask-user-remote/README.md +8 -0
- package/.pi/harnesses/ask-user-remote/index.ts +41 -1
- package/.pi/harnesses/coms/README.md +11 -0
- package/.pi/prompts/doctor-agent-fleet.md +1 -1
- package/.pi/prompts/setup-agent-fleet.md +4 -4
- package/README.md +133 -354
- package/agents/architect.md +4 -2
- package/agents/bowser.md +2 -1
- package/agents/builder.md +3 -2
- package/agents/code-reviewer.md +7 -7
- package/agents/deep-researcher.md +3 -3
- package/agents/documenter.md +3 -1
- package/agents/orchestrator.md +5 -3
- package/agents/plan-reviewer.md +5 -5
- package/agents/planner.md +7 -7
- package/agents/releaser.md +3 -1
- package/agents/researcher.md +3 -3
- package/agents/security-auditor.md +7 -7
- package/agents/test-engineer.md +5 -5
- package/agents/web-debugger.md +3 -3
- package/agents/web-performance-auditor.md +3 -3
- package/bin/snapshot-version.js +17 -1
- package/codex/CONDUCTOR.md +148 -0
- package/docs/ARCHITECTURE.md +165 -0
- package/docs/agent-fleet-setup.md +1 -0
- package/docs/claude-code-coms-bridge.md +10 -0
- package/docs/codex-remote-conductor.md +170 -0
- package/docs/coms-hermes-bridge.md +121 -0
- package/docs/getting-started.md +14 -0
- package/docs/npm-install.md +2 -0
- package/docs/pi-extensions.md +16 -0
- package/docs/pi-setup.md +2 -0
- package/hermes/README.md +48 -0
- package/hermes/skills/hub-conductor/SKILL.md +84 -0
- package/hermes/skills/hub-liaison/SKILL.md +84 -0
- package/justfile +132 -15
- package/package.json +10 -3
- package/scripts/codex-conductor.ts +41 -0
- package/scripts/codex-remote-control.ts +167 -0
- package/scripts/coms-cli.ts +311 -199
- package/scripts/coms-hermes-bridge.ts +8 -4
- package/scripts/lib/codex-conductor.ts +88 -0
- package/scripts/lib/codex-remote-control.ts +480 -0
- package/scripts/lib/coms-envelope.ts +51 -6
- package/scripts/lib/herdr-layout.ts +35 -7
- package/scripts/lib/hermes-bridge-core.ts +4 -4
- package/scripts/lib/spawn-stagger.ts +101 -0
- package/scripts/lib/team-project.ts +112 -3
- package/scripts/lib/team-snapshot.ts +3 -2
- package/scripts/team-snapshot.ts +23 -6
- package/scripts/team-up.ts +106 -18
- package/skills/guided-workspace-setup/SKILL.md +123 -97
- package/skills/guided-workspace-setup/companion-manifest.json +33 -0
- package/skills/peer-coms/SKILL.md +9 -0
- package/systemd/user/agent-fleet-codex-remote-control.service.in +23 -0
|
@@ -12,6 +12,6 @@ Also flag malformed peer entries in `.pi/agents/peers.yaml`: field lines (`perso
|
|
|
12
12
|
|
|
13
13
|
Also validate `.ai/agent-fleet-overrides.md` when it exists, against the schema in `docs/agent-fleet-setup.md`: unknown sections, unknown keys in known sections, invalid values for the mechanically parsed `agent-hub` keys, missing `rules:` folders and `docs:` entry points, and `## env` `required:` names that are neither set nor declared in the root `.env`. These findings are advisory only — report them with fix "edit by hand", never edit the overrides file.
|
|
14
14
|
|
|
15
|
-
Present findings
|
|
15
|
+
Present the findings per the skill's Step 1 interaction contract: print a short text summary (counts per kind, advisory findings as report-only text), then ask one `AskUserQuestion` multi-select — *"Which fixes should I apply now?"* — each option titled `<path> — <issue>` with the proposed fix as its description, chunked at ≤ 4 options per question; an empty selection applies nothing.
|
|
16
16
|
|
|
17
17
|
Never overwrite a regular file — only act on symlinks whose target is missing. Report `repaired`, `deleted`, and `skipped` counts, and append a `## doctor-runs` line to `.ai/agent-fleet-setup.md` with the date, agent, phase (`standalone`), and counts.
|
|
@@ -10,9 +10,9 @@ Analyse the workspace. If prior install state is found (`.ai/agent-fleet-setup.m
|
|
|
10
10
|
|
|
11
11
|
The Skills group draws from **two roots**: fleet-native `skills/` and the vendored upstream import `vendor/agent-skills-upstream/skills/` (see `docs/UPSTREAM-SKILLS.md`). On a name collision the native copy wins — never offer the vendored duplicate as a separate row.
|
|
12
12
|
|
|
13
|
-
Then present the install menu
|
|
13
|
+
Then present the install menu per the skill's Step 1 interaction contract — drive every decision through `AskUserQuestion`, never a printed table awaiting a free-text reply. Open with the **Express question** (fresh workspace: `Recommended ★` / `Everything` / `Custom — group by group` / `Nothing`; existing: `Keep as-is` / `Apply updates` / `Keep + add recommended ★` / `Custom`) — any answer but `Custom` skips all group screens. On `Custom`, run the **7 groups** (4 shared: Skills, Agent personas, Commands/prompts, References & Hooks; 3 pi-only — a claude-code workspace sees just the 4 shared groups): each opens as a single-select quick screen (`Recommended ★ (n)` / `Everything (m)` / `Customise` / `Skip group`, or the installed-state variants with `Remove some…`), and multi-select drill-ins appear only behind `Customise`, chunked by sub-category (lifecycle phase for Skills, `rw`/`ro` for personas, …) at ≤ 4 options per question. Option titles carry `name ★ [st]` (`ok`/`upd`/`mod`/`cflt`/`gone`/`new`/`—`/`brk`); descriptions carry the purpose plus the state in plain words (`mod` → warn that refreshing overwrites local edits). There is **no pre-checking** — installed state shows as counts on quick screens and words in descriptions; leaving an installed item unselected in a drill-in keeps it as-is. `recommended` adds `★` items on top of what is installed — it never removes; cancel = keep-as-is/skip. `cflt` rows are resolved only by showing the three-way diff and asking per row — never by Express or `Apply updates`. Never offer `setup`, `doctor`, or `guided-workspace-setup` — those are installer-only and live in the source agent-fleet repo.
|
|
14
14
|
|
|
15
|
-
|
|
15
|
+
Removal happens **only** on an explicit `Remove some…` multi-select (empty selection = remove nothing), and it is scoped: the screen lists only items whose name is in the agent-fleet inventory **and** that are recorded in `## install-status` (or are symlinks resolving into the source repo). User-authored skills, custom commands, third-party plugins, and unrelated settings/env keys are left untouched and logged as "Skipped — not owned by agent-fleet".
|
|
16
16
|
|
|
17
17
|
**No cross-tool substitution.** Each row is offered only when the source file the chosen agent needs already exists — for `pi`, that means `.pi/prompts/<name>.md`, `.pi/extensions/<name>/`, etc. Never fall back to `.claude/commands/` (or another agent's tree) to satisfy a pi prompt request; items missing their per-agent source are filtered out of the menu entirely.
|
|
18
18
|
|
|
@@ -20,6 +20,6 @@ Unchecking an installed item means *remove it*, but **removal is scoped**: only
|
|
|
20
20
|
|
|
21
21
|
**pi harness companions.** When the agent is `pi`, installing/refreshing/removing any harness also refreshes its companions — the `justfile` launch recipes, the `team-up`/`coms-net` scripts, the peer/team YAML, `.pi/damage-control-rules.yaml`, and `.pi/harnesses/package.json`. Refresh the `justfile` from the current source (rewriting only the `agent-fleet:harnesses` managed region so user recipes survive) so retired-harness recipes are pruned and new ones added; a stale `justfile` left after a harness change is the regression this prevents.
|
|
22
22
|
|
|
23
|
-
**No mid-apply overwrite prompts.** The
|
|
23
|
+
**No mid-apply overwrite prompts.** The `mod` description already warns that refreshing overwrites local edits. The user's selection is the consent; the Step 9 confirmation is the single gate. During apply, refresh selected items unconditionally — never pause to ask "should I overwrite this file?". Genuine errors (permission denied, missing source) still stop and report.
|
|
24
24
|
|
|
25
|
-
Offer override sections for the workspace's `.ai/agent-fleet-overrides.md` based on the analysis, and record what was installed in `.ai/agent-fleet-setup.md`.
|
|
25
|
+
Offer override sections for the workspace's `.ai/agent-fleet-overrides.md` based on the analysis (print each draft, then `Accept` / `Edit` / `Skip` per section), and record what was installed in `.ai/agent-fleet-setup.md`. Print the plan as compact action-grouped lines (Add / Refresh / Remove / Keep-count / Records / Method), then confirm with one question whose options are `Apply — and remove the installer commands` (default) / `Apply — keep the installer commands` / `Adjust picks` / `Cancel` — write nothing until an Apply is chosen. Then perform the setup, re-scan for any new breakage, and report what changed.
|
|
@@ -12,4 +12,6 @@ Also flag malformed peer entries in `.pi/agents/peers.yaml`: field lines (`perso
|
|
|
12
12
|
|
|
13
13
|
Also validate `.ai/agent-fleet-overrides.md` when it exists, against the schema in `docs/agent-fleet-setup.md`: unknown sections, unknown keys in known sections, invalid values for the mechanically parsed `agent-hub` keys, missing `rules:` folders and `docs:` entry points, and `## env` `required:` names that are neither set nor declared in the root `.env`. These findings are advisory only — report them with fix "edit by hand", never edit the overrides file.
|
|
14
14
|
|
|
15
|
+
Present the findings per the skill's Step 1 interaction contract: print a short text summary (counts per kind, advisory findings as report-only text), then ask one native multi-select — *"Which fixes should I apply now?"* — each option titled `<path> — <issue>` with the proposed fix as its description; an empty selection applies nothing. Without a widget, print a `# | Path | Issue | Suggested fix` table instead and take the picks as text.
|
|
16
|
+
|
|
15
17
|
Never overwrite a regular file — only act on symlinks whose target is missing. Report `repaired`, `deleted`, and `skipped` counts, and append a `## doctor-runs` line to `.ai/agent-fleet-setup.md` with the date and counts.
|
|
@@ -8,7 +8,7 @@ Run the guided install for a target workspace. If the user passed a workspace pa
|
|
|
8
8
|
|
|
9
9
|
The Skills group draws from **two roots**: fleet-native `skills/` and the vendored upstream import `vendor/agent-skills-upstream/skills/` (see `docs/UPSTREAM-SKILLS.md`). On a name collision the native copy wins — never offer the vendored duplicate as a separate row.
|
|
10
10
|
|
|
11
|
-
Analyse the workspace, then present a
|
|
11
|
+
Analyse the workspace, then present the install menu per the skill's Step 1 interaction contract: with a native select widget, open with the **Express question** (`Recommended ★` / `Everything` / `Custom — group by group`, or the installed-state variants), and on `Custom` run the **7 groups** (4 shared: Skills, Agent personas, Commands/prompts, References & Hooks; 3 pi-only — an opencode workspace sees just the 4 shared groups) as single-select quick screens with multi-select drill-ins only behind `Customise`, chunked by sub-category; installed state shows as counts and plain-words descriptions (no pre-checking), removal only via an explicit `Remove some…` selection, and cancel = keep-as-is. Without a widget, fall back to the skill's tabular format (pre-checked `[x]` tables with text replies). On `pi`, installing/refreshing/removing any harness also refreshes its companions — the `justfile` launch recipes (managed region only, so user recipes survive), the `team-up` script, the peer/team YAML, `.pi/damage-control-rules.yaml`, and `.pi/harnesses/package.json` — refreshed from the current source so retired-harness recipes are pruned and new ones added.
|
|
12
12
|
|
|
13
13
|
**Personas are generated for opencode.** The personas group lists the full availability roster from `node <source-root>/bin/cli.js transform-persona --list --agent opencode` (pi-only personas — `bowser`, `orchestrator` — are excluded). The apply step installs them into `.opencode/agent/<name>.md` via `transform-persona --agent opencode --workspace <workspace> <name…>` — always a generated copy, even in symlink mode — and records the rows with `transformed: true`; status checks diff against the generated output, not the raw canonical source.
|
|
14
14
|
|
|
@@ -5,16 +5,16 @@
|
|
|
5
5
|
# Profiles only switch the personas they list; everyone else keeps their
|
|
6
6
|
# current model. They never touch delegate-children (`subagents:`) models.
|
|
7
7
|
max:
|
|
8
|
-
code-reviewer: openai-codex/gpt-5.
|
|
9
|
-
builder: openai-codex/gpt-5.
|
|
10
|
-
planner: openai-codex/gpt-5.
|
|
11
|
-
plan-reviewer: openai-codex/gpt-5.
|
|
12
|
-
security-auditor: openai-codex/gpt-5.
|
|
13
|
-
test-engineer: openai-codex/gpt-5.
|
|
8
|
+
code-reviewer: openai-codex/gpt-5.6-sol
|
|
9
|
+
builder: openai-codex/gpt-5.6-sol
|
|
10
|
+
planner: openai-codex/gpt-5.6-sol
|
|
11
|
+
plan-reviewer: openai-codex/gpt-5.6-sol
|
|
12
|
+
security-auditor: openai-codex/gpt-5.6-sol
|
|
13
|
+
test-engineer: openai-codex/gpt-5.6-sol
|
|
14
14
|
budget:
|
|
15
|
-
code-reviewer: openai-codex/gpt-5.
|
|
16
|
-
builder: openai-codex/gpt-5.
|
|
17
|
-
planner: openai-codex/gpt-5.
|
|
18
|
-
plan-reviewer: openai-codex/gpt-5.
|
|
19
|
-
security-auditor: openai-codex/gpt-5.
|
|
20
|
-
test-engineer: openai-codex/gpt-5.
|
|
15
|
+
code-reviewer: openai-codex/gpt-5.6-terra
|
|
16
|
+
builder: openai-codex/gpt-5.6-terra
|
|
17
|
+
planner: openai-codex/gpt-5.6-terra
|
|
18
|
+
plan-reviewer: openai-codex/gpt-5.6-terra
|
|
19
|
+
security-auditor: openai-codex/gpt-5.6-terra
|
|
20
|
+
test-engineer: openai-codex/gpt-5.6-terra
|
package/.pi/agents/peers.yaml
CHANGED
|
@@ -26,106 +26,110 @@
|
|
|
26
26
|
# runner: claude-code
|
|
27
27
|
# model: opus
|
|
28
28
|
|
|
29
|
+
# Hub-only workspace: `just hub-team base --project <name>` creates a Herdr
|
|
30
|
+
# workspace containing only the guarded hub, with no reusable coms peer panes.
|
|
31
|
+
base:
|
|
32
|
+
|
|
29
33
|
full:
|
|
30
34
|
- name: web-debugger
|
|
31
35
|
persona: web-debugger
|
|
32
|
-
model: openai-codex/gpt-5.
|
|
36
|
+
model: openai-codex/gpt-5.6-terra
|
|
33
37
|
extensions: chrome-devtools-mcp
|
|
34
38
|
- name: documenter
|
|
35
39
|
persona: documenter
|
|
36
|
-
model: openai-codex/gpt-5.
|
|
40
|
+
model: openai-codex/gpt-5.6-terra
|
|
37
41
|
- name: researcher
|
|
38
42
|
persona: researcher
|
|
39
|
-
model: openai-codex/gpt-5.
|
|
43
|
+
model: openai-codex/gpt-5.6-luna
|
|
40
44
|
|
|
41
45
|
web:
|
|
42
46
|
- name: web-debugger
|
|
43
47
|
persona: web-debugger
|
|
44
|
-
model: openai-codex/gpt-5.
|
|
48
|
+
model: openai-codex/gpt-5.6-terra
|
|
45
49
|
extensions: chrome-devtools-mcp
|
|
46
50
|
|
|
47
51
|
docs:
|
|
48
52
|
- name: documenter
|
|
49
53
|
persona: documenter
|
|
50
|
-
model: openai-codex/gpt-5.
|
|
54
|
+
model: openai-codex/gpt-5.6-terra
|
|
51
55
|
- name: researcher
|
|
52
56
|
persona: researcher
|
|
53
|
-
model: openai-codex/gpt-5.
|
|
57
|
+
model: openai-codex/gpt-5.6-luna
|
|
54
58
|
|
|
55
59
|
# Mirrored from .pi/agents/teams.yaml for `just team-up <team>`.
|
|
56
60
|
default:
|
|
57
61
|
- name: planner
|
|
58
62
|
persona: planner
|
|
59
|
-
model: openai-codex/gpt-5.
|
|
63
|
+
model: openai-codex/gpt-5.6-sol
|
|
60
64
|
- name: plan-reviewer
|
|
61
65
|
runner: claude-code
|
|
62
66
|
- name: builder
|
|
63
67
|
persona: builder
|
|
64
|
-
model: openai-codex/gpt-5.
|
|
68
|
+
model: openai-codex/gpt-5.6-terra
|
|
65
69
|
- name: test-engineer
|
|
66
70
|
persona: test-engineer
|
|
67
|
-
model: openai-codex/gpt-5.
|
|
71
|
+
model: openai-codex/gpt-5.6-terra
|
|
68
72
|
- name: code-reviewer
|
|
69
73
|
runner: claude-code
|
|
70
74
|
- name: documenter
|
|
71
75
|
persona: documenter
|
|
72
|
-
model: openai-codex/gpt-5.
|
|
76
|
+
model: openai-codex/gpt-5.6-terra
|
|
73
77
|
|
|
74
78
|
debug:
|
|
75
79
|
- name: test-engineer
|
|
76
80
|
persona: test-engineer
|
|
77
|
-
model: openai-codex/gpt-5.
|
|
81
|
+
model: openai-codex/gpt-5.6-terra
|
|
78
82
|
- name: builder
|
|
79
83
|
persona: builder
|
|
80
|
-
model: openai-codex/gpt-5.
|
|
84
|
+
model: openai-codex/gpt-5.6-terra
|
|
81
85
|
- name: code-reviewer
|
|
82
86
|
runner: claude-code
|
|
83
87
|
|
|
84
88
|
frontend:
|
|
85
89
|
- name: planner
|
|
86
90
|
persona: planner
|
|
87
|
-
model: openai-codex/gpt-5.
|
|
91
|
+
model: openai-codex/gpt-5.6-sol
|
|
88
92
|
- name: builder
|
|
89
93
|
persona: builder
|
|
90
|
-
model: openai-codex/gpt-5.
|
|
94
|
+
model: openai-codex/gpt-5.6-terra
|
|
91
95
|
- name: bowser
|
|
92
96
|
persona: bowser
|
|
93
|
-
model: openai-codex/gpt-5.
|
|
97
|
+
model: openai-codex/gpt-5.6-luna
|
|
94
98
|
- name: code-reviewer
|
|
95
99
|
runner: claude-code
|
|
96
100
|
|
|
97
101
|
security:
|
|
98
102
|
- name: security-auditor
|
|
99
103
|
persona: security-auditor
|
|
100
|
-
model: openai-codex/gpt-5.
|
|
104
|
+
model: openai-codex/gpt-5.6-sol
|
|
101
105
|
- name: builder
|
|
102
106
|
persona: builder
|
|
103
|
-
model: openai-codex/gpt-5.
|
|
107
|
+
model: openai-codex/gpt-5.6-terra
|
|
104
108
|
- name: test-engineer
|
|
105
109
|
persona: test-engineer
|
|
106
|
-
model: openai-codex/gpt-5.
|
|
110
|
+
model: openai-codex/gpt-5.6-terra
|
|
107
111
|
- name: code-reviewer
|
|
108
112
|
runner: claude-code
|
|
109
113
|
|
|
110
114
|
hotfix:
|
|
111
115
|
- name: builder
|
|
112
116
|
persona: builder
|
|
113
|
-
model: openai-codex/gpt-5.
|
|
117
|
+
model: openai-codex/gpt-5.6-terra
|
|
114
118
|
- name: code-reviewer
|
|
115
119
|
runner: claude-code
|
|
116
120
|
|
|
117
121
|
release:
|
|
118
122
|
- name: releaser
|
|
119
123
|
persona: releaser
|
|
120
|
-
model: openai-codex/gpt-5.
|
|
124
|
+
model: openai-codex/gpt-5.6-terra
|
|
121
125
|
- name: documenter
|
|
122
126
|
persona: documenter
|
|
123
|
-
model: openai-codex/gpt-5.
|
|
127
|
+
model: openai-codex/gpt-5.6-terra
|
|
124
128
|
|
|
125
129
|
info:
|
|
126
130
|
- name: documenter
|
|
127
131
|
persona: documenter
|
|
128
|
-
model: openai-codex/gpt-5.
|
|
132
|
+
model: openai-codex/gpt-5.3-codex-spark
|
|
129
133
|
- name: code-reviewer
|
|
130
134
|
runner: claude-code
|
|
131
135
|
|
package/.pi/agents/teams.yaml
CHANGED
|
@@ -1,5 +1,5 @@
|
|
|
1
|
-
#
|
|
2
|
-
# researcher / deep-researcher
|
|
1
|
+
# The first team is activated at startup. Switch with: /agents-team
|
|
2
|
+
# researcher / deep-researcher are not listed — they are always available through spawn_research.
|
|
3
3
|
|
|
4
4
|
default:
|
|
5
5
|
- planner
|
|
@@ -13,10 +13,38 @@ another main agent** and **use a coms peer as a subagent**.
|
|
|
13
13
|
> P2P layer from [`pi-vs-claude-code`](https://github.com/disler/pi-vs-claude-code) by
|
|
14
14
|
> [disler](https://github.com/disler) (MIT). See the
|
|
15
15
|
> [extension catalog](../../../docs/pi-extensions.md) and the
|
|
16
|
-
> [design plan](../../../docs/plans/agent-hub
|
|
16
|
+
> [design plan](../../../docs/plans/agent-hub/).
|
|
17
|
+
|
|
18
|
+
**Optional phone control:** `just hub-team <team> --project <name>` can supply the live peers for the experimental [Codex Android conductor](../../../docs/codex-remote-conductor.md). Configure Codex for the same project; do not also launch a second `conductor-codex <team>` peer workspace. Hermes remains the inbound `ask_user` route, while Codex performs only human-confirmed, approval-gated outbound delegation.
|
|
17
19
|
|
|
18
20
|
## What it does
|
|
19
21
|
|
|
22
|
+
The whole dispatch loop, end to end:
|
|
23
|
+
|
|
24
|
+
```mermaid
|
|
25
|
+
sequenceDiagram
|
|
26
|
+
autonumber
|
|
27
|
+
actor U as You
|
|
28
|
+
participant H as Hub (dispatcher)
|
|
29
|
+
participant S as Specialist (e.g. builder)
|
|
30
|
+
participant R as Research helper
|
|
31
|
+
participant D as Disk (.pi/agent-sessions/)
|
|
32
|
+
|
|
33
|
+
U->>H: task
|
|
34
|
+
H->>D: set_assertions — Verification Contract persisted
|
|
35
|
+
H->>S: dispatch_agent (task + advisory scope)
|
|
36
|
+
S-->>H: NEEDS_RESEARCH: how does X work?
|
|
37
|
+
H->>R: spawn_research (researcher / deep-researcher)
|
|
38
|
+
R->>D: write findings file
|
|
39
|
+
R-->>H: one-line notice + path
|
|
40
|
+
H->>S: resume with file paths — never raw findings
|
|
41
|
+
S-->>H: structured return + named evidence
|
|
42
|
+
H->>D: update_assertion
|
|
43
|
+
H-->>U: Assertions: 2✓ 1○ 1✗ · open: A4
|
|
44
|
+
```
|
|
45
|
+
|
|
46
|
+
Every borrowed idea from another harness passes one test before it lands: *does this persistently enter the dispatcher context?* If yes, it goes to disk or a one-line status instead.
|
|
47
|
+
|
|
20
48
|
`agent-hub` is the supported home for the former standalone dispatcher features:
|
|
21
49
|
|
|
22
50
|
- **Dispatcher grid** — a live dashboard of fixed specialists from `.pi/agents/teams.yaml`.
|
|
@@ -25,6 +53,12 @@ another main agent** and **use a coms peer as a subagent**.
|
|
|
25
53
|
`kind: research` personas ship by default: `researcher` (fast `gpt-5.3-codex-spark`) for simple
|
|
26
54
|
reads and `deep-researcher` (`gpt-5.5` / xhigh) for hard, cross-cutting investigation. The
|
|
27
55
|
orchestrator routes by persona; each persona's model + thinking level is shown in its catalog.
|
|
56
|
+
Finished helpers are **auto-pruned** so the research row doesn't grow without bound: auto-research
|
|
57
|
+
pipe helpers disappear as soon as they finish (their findings persist as `findings/*.md` files and
|
|
58
|
+
their handles are never resumed), while manual/persona helpers keep only the `research-keep` most
|
|
59
|
+
recently finished (default 4 — resumable via `/agents-cont rN`; older cards, and their session
|
|
60
|
+
files, are dropped oldest-first). Set `research-keep: <n>|all` in the overrides file to change
|
|
61
|
+
the cap. Running helpers are never pruned and `rN` handles are never reused.
|
|
28
62
|
- **Human handoff path** — `ask_user` is exposed by the `ask-user-remote` wrapper (capturing stock
|
|
29
63
|
`pi-ask-user` and optionally racing a `user-remote` bridge), so specialists can bubble decisions
|
|
30
64
|
back through the dispatcher.
|
|
@@ -82,7 +116,15 @@ another main agent** and **use a coms peer as a subagent**.
|
|
|
82
116
|
- **Agent controls** — `/zoom` inspects a live agent timeline; `/agents-history` replays the run as a
|
|
83
117
|
timeline (orchestrator turns, dispatches, research helpers) with per-agent durations, parallel-run
|
|
84
118
|
markers, and a grand total; kill/restart controls manage running child agents; per-agent `model:`
|
|
85
|
-
fields select models from team config.
|
|
119
|
+
fields select models from team config. The `agents-*` commands address **both target kinds** —
|
|
120
|
+
team specialists by persona name, research helpers by `rN` handle (mirroring `/zoom`):
|
|
121
|
+
`/agents-kill <name|rN|all>` SIGTERMs a specialist (keeping its standing card), while on a
|
|
122
|
+
research helper it kills **and removes** the card + session — helpers are disposable by design
|
|
123
|
+
(`all` clears every helper); `/agents-restart <name|rN>` re-runs the last task fresh (a research
|
|
124
|
+
helper must be finished first); `/agents-cont rN <prompt>` resumes a finished helper's session.
|
|
125
|
+
The old `/research-rm` and `/research-clear` spellings remain as aliases of the kill semantics,
|
|
126
|
+
`/research-cont` of `/agents-cont`.
|
|
127
|
+
Restartable team specialists at or above 70% context render
|
|
86
128
|
their context percentage with a warning marker/color in dashboard and compact views, and their next
|
|
87
129
|
`dispatch_agent` result adds a `/agents-restart <persona>` hint. Research helpers are not warned,
|
|
88
130
|
and the hub never restarts specialists automatically.
|
|
@@ -280,9 +322,20 @@ task and follow their links instead of bulk-reading doc trees. The code-reviewer
|
|
|
280
322
|
changes that alter documented behavior without a doc update; the documenter treats the entry
|
|
281
323
|
points and the trees they link as the documentation it maintains.
|
|
282
324
|
|
|
325
|
+
The same section also tunes research-helper retention:
|
|
326
|
+
|
|
327
|
+
```markdown
|
|
328
|
+
## agent-hub
|
|
329
|
+
research-keep: 8
|
|
330
|
+
```
|
|
331
|
+
|
|
332
|
+
`research-keep:` caps how many **finished** manual/persona research helpers stay resumable
|
|
333
|
+
(LRU by finish time, default 4; `all` disables the cap). Auto-research pipe helpers are
|
|
334
|
+
always pruned as soon as they finish, regardless of this key.
|
|
335
|
+
|
|
283
336
|
Paths that don't exist produce a session-start warning, never an error. The full key list for
|
|
284
|
-
`## agent-hub` (models, sub-roles, depth budgets, persona gate) is
|
|
285
|
-
`docs/agent-fleet-setup.md`.
|
|
337
|
+
`## agent-hub` (models, sub-roles, depth budgets, persona gate, research retention) is
|
|
338
|
+
documented in `docs/agent-fleet-setup.md`.
|
|
286
339
|
|
|
287
340
|
## The coms layer
|
|
288
341
|
|