Move non-agent launch helpers out of internal/agents

coilyco-ops commented

2026-07-08 22:04:47 +00:00

Member

Problem

internal/agents/ollamaprobe and internal/agents/modelconfig are not agents.

The internal/agents tree should hold agent harness implementations and the registry. These two packages are shared support code:

ollamaprobe is a local model endpoint/model availability probe used by Goose, OpenCode, and doctor-style checks.
modelconfig classifies model-name/config failures across Codex, Claude, OpenCode, and the Ollama probe.

Keeping them under internal/agents makes the package boundary read as if Ollama is an agent and as if model-config classification is owned by the agent registry. That is misleading, especially while debugging launch gates.

Current imports to update

internal/agents/goose/smoke.go imports internal/agents/ollamaprobe.
internal/agents/opencode/smoke.go imports internal/agents/ollamaprobe.
cmd/ward/doctor_probes.go imports internal/agents/ollamaprobe.
internal/agents/codex/smoke.go, internal/agents/claude/smoke.go, internal/agents/opencode/smoke.go, and internal/agents/ollamaprobe/ollamaprobe.go import internal/agents/modelconfig.

Do

Move these packages to a neutral shared namespace. Suggested shape:

internal/launchgate/ollamaprobe
internal/launchgate/modelconfig

A shorter internal/probes/ollama / internal/modelconfig split is also acceptable if it reads better in the tree. Pick the smallest move that makes the ownership obvious.

Then update imports, tests, and any docs/comments that refer to the old package paths.

Acceptance

No non-agent support packages remain directly under internal/agents/.
Agent implementations still import the shared launch-gate helpers cleanly.
ward exec test passes.
No behavior changes beyond package ownership/import paths.

## Problem `internal/agents/ollamaprobe` and `internal/agents/modelconfig` are not agents. The `internal/agents` tree should hold agent harness implementations and the registry. These two packages are shared support code: * `ollamaprobe` is a local model endpoint/model availability probe used by Goose, OpenCode, and doctor-style checks. * `modelconfig` classifies model-name/config failures across Codex, Claude, OpenCode, and the Ollama probe. Keeping them under `internal/agents` makes the package boundary read as if Ollama is an agent and as if model-config classification is owned by the agent registry. That is misleading, especially while debugging launch gates. ## Current imports to update * `internal/agents/goose/smoke.go` imports `internal/agents/ollamaprobe`. * `internal/agents/opencode/smoke.go` imports `internal/agents/ollamaprobe`. * `cmd/ward/doctor_probes.go` imports `internal/agents/ollamaprobe`. * `internal/agents/codex/smoke.go`, `internal/agents/claude/smoke.go`, `internal/agents/opencode/smoke.go`, and `internal/agents/ollamaprobe/ollamaprobe.go` import `internal/agents/modelconfig`. ## Do Move these packages to a neutral shared namespace. Suggested shape: * `internal/launchgate/ollamaprobe` * `internal/launchgate/modelconfig` A shorter `internal/probes/ollama` / `internal/modelconfig` split is also acceptable if it reads better in the tree. Pick the smallest move that makes the ownership obvious. Then update imports, tests, and any docs/comments that refer to the old package paths. ## Acceptance * No non-agent support packages remain directly under `internal/agents/`. * Agent implementations still import the shared launch-gate helpers cleanly. * `ward exec test` passes. * No behavior changes beyond package ownership/import paths.

coilyco-ops commented

2026-07-08 22:04:54 +00:00

Author

Member

🔒 Reserved by ward agent --harness goose — container engineer-goose-ward-704 on host kais-macbook-pro-2.local is carrying this issue (reserved 2026-07-08T22:04:53Z). Concurrent ward agent runs are blocked until it finishes or the reservation goes stale (1h TTL); --force overrides.

Do not comment on or edit this issue to steer the run while it is reserved. The engineer seeded the body once at launch and never re-reads it, so a comment or edit reaches only human readers, never the running engineer. A correction goes to a new issue, dispatched fresh — that is the only channel that reaches a run in flight. Where the forge supports it, ward locks this conversation to make that a road-block rather than a convention (ward#494).

run seed context — what this run is carrying (ward#609)

Resolved: coilyco-flight-deck/ward#704 · branch issue-704 · harness goose · workflow direct-main
Run: engineer-goose-ward-704 · ward v0.466.0 · dispatched 2026-07-08T22:04:53Z
Comment thread: 0 included in the pre-flight read, 0 stripped (ward's own automated comments).

Static container doctrine and seed boilerplate are identical every run and omitted here (they ride ward v0.466.0).

— Goose, via ward agent

🔒 Reserved by `ward agent --harness goose` — container `engineer-goose-ward-704` on host `kais-macbook-pro-2.local` is carrying this issue (reserved 2026-07-08T22:04:53Z). Concurrent `ward agent` runs are blocked until it finishes or the reservation goes stale (1h TTL); `--force` overrides. **Do not comment on or edit this issue to steer the run while it is reserved.** The engineer seeded the body once at launch and never re-reads it, so a comment or edit reaches only human readers, never the running engineer. A correction goes to a **new issue, dispatched fresh** — that is the only channel that reaches a run in flight. Where the forge supports it, ward locks this conversation to make that a road-block rather than a convention (ward#494). <details><summary>run seed context — what this run is carrying (ward#609)</summary> - **Resolved:** `coilyco-flight-deck/ward#704` · branch `issue-704` · harness `goose` · workflow `direct-main` - **Run:** `engineer-goose-ward-704` · ward `v0.466.0` · dispatched `2026-07-08T22:04:53Z` - **Comment thread:** 0 included in the pre-flight read, 0 stripped (ward's own automated comments). Static container doctrine and seed boilerplate are identical every run and omitted here (they ride ward v0.466.0). </details>  — Goose, via `ward agent`

coilyco-ops commented

2026-07-08 22:09:04 +00:00

Author

Member

⚠️ Reopened: this run's work did not land on `main`

An ephemeral ward container (goose mode) dispatched for this issue finished but its work was not merged to main, so the reaper preserved it on a branch before teardown and reopened the issue (its closes #704 never reached main). Recover from the salvage branch below.

Repo: coilyco-flight-deck/ward
Salvage branch: ward-salvage/ward-16eb4ad0
Reason: missing same-repo closing reference
Container uptime at reap: 4m (age of the baked Forgejo PAT snapshot; a long-lived container is likelier to carry a rotated token)

Reap diagnostics

--- reap diagnostics ---
ward version:      v0.466.0
version source:    pinned via WARD_VERSION/--ward-version (v0.466.0)
HEAD:              4622e276a147
origin/main:       c3442c3d180d
ancestry:          HEAD is NOT yet on origin/main - residual work remains to land
decision gate:     missing same-repo closing reference
reason:            missing same-repo closing reference
provenance:        present
run-owned landed:  no
working tree:      8 dirty path(s)
container uptime:  4m (baked Forgejo PAT age proxy)
--- end reap diagnostics ---

Recover

git fetch https://forgejo.coilysiren.me/coilyco-flight-deck/ward.git ward-salvage/ward-16eb4ad0
git checkout -b ward-salvage/ward-16eb4ad0 FETCH_HEAD

Working tree at reap time

 M cmd/ward/agent_review.go
 M cmd/ward/doctor.go
 M internal/agents/claude/smoke.go
 M internal/agents/codex/smoke.go
 M internal/agents/goose/smoke.go
 M internal/agents/opencode/smoke.go
 M internal/agents/opencode/smoke_test.go
?? internal/launchgate/

— Goose, via ward agent

## ⚠️ Reopened: this run's work did not land on `main` An ephemeral `ward container` (goose mode) dispatched for this issue finished but its work was **not merged to `main`**, so the reaper preserved it on a branch before teardown and reopened the issue (its `closes #704` never reached `main`). Recover from the salvage branch below. - **Repo:** `coilyco-flight-deck/ward` - **Salvage branch:** `ward-salvage/ward-16eb4ad0` - **Reason:** missing same-repo closing reference - **Container uptime at reap:** 4m (age of the baked Forgejo PAT snapshot; a long-lived container is likelier to carry a rotated token) ## Reap diagnostics ``` --- reap diagnostics --- ward version: v0.466.0 version source: pinned via WARD_VERSION/--ward-version (v0.466.0) HEAD: 4622e276a147 origin/main: c3442c3d180d ancestry: HEAD is NOT yet on origin/main - residual work remains to land decision gate: missing same-repo closing reference reason: missing same-repo closing reference provenance: present run-owned landed: no working tree: 8 dirty path(s) container uptime: 4m (baked Forgejo PAT age proxy) --- end reap diagnostics --- ``` ## Recover ```bash git fetch https://forgejo.coilysiren.me/coilyco-flight-deck/ward.git ward-salvage/ward-16eb4ad0 git checkout -b ward-salvage/ward-16eb4ad0 FETCH_HEAD ``` ## Working tree at reap time ``` M cmd/ward/agent_review.go M cmd/ward/doctor.go M internal/agents/claude/smoke.go M internal/agents/codex/smoke.go M internal/agents/goose/smoke.go M internal/agents/opencode/smoke.go M internal/agents/opencode/smoke_test.go ?? internal/launchgate/ ```  — Goose, via `ward agent`

coilyco-ops commented

2026-07-09 00:06:57 +00:00

Author

Member

🔒 Reserved by ward agent --harness codex — container engineer-codex-ward-704 on host kais-macbook-pro-2.local is carrying this issue (reserved 2026-07-09T00:06:54Z). Concurrent ward agent runs are blocked until it finishes or the reservation goes stale (1h TTL); --force overrides.

Do not comment on or edit this issue to steer the run while it is reserved. The engineer seeded the body once at launch and never re-reads it, so a comment or edit reaches only human readers, never the running engineer. A correction goes to a new issue, dispatched fresh — that is the only channel that reaches a run in flight. Where the forge supports it, ward locks this conversation to make that a road-block rather than a convention (ward#494).

run seed context — what this run is carrying (ward#609)

Resolved: coilyco-flight-deck/ward#704 · branch issue-704 · harness codex · workflow pr
Run: engineer-codex-ward-704 · ward v0.470.0 · dispatched 2026-07-09T00:06:54Z
Comment thread: 1 included in the pre-flight read, 1 stripped (ward's own automated comments).
- included: @coilyco-ops (2026-07-08T22:09:04Z)
- stripped: @coilyco-ops (2026-07-08T22:04:54Z)

Static container doctrine and seed boilerplate are identical every run and omitted here (they ride ward v0.470.0).

— Codex, via ward agent

🔒 Reserved by `ward agent --harness codex` — container `engineer-codex-ward-704` on host `kais-macbook-pro-2.local` is carrying this issue (reserved 2026-07-09T00:06:54Z). Concurrent `ward agent` runs are blocked until it finishes or the reservation goes stale (1h TTL); `--force` overrides. **Do not comment on or edit this issue to steer the run while it is reserved.** The engineer seeded the body once at launch and never re-reads it, so a comment or edit reaches only human readers, never the running engineer. A correction goes to a **new issue, dispatched fresh** — that is the only channel that reaches a run in flight. Where the forge supports it, ward locks this conversation to make that a road-block rather than a convention (ward#494). <details><summary>run seed context — what this run is carrying (ward#609)</summary> - **Resolved:** `coilyco-flight-deck/ward#704` · branch `issue-704` · harness `codex` · workflow `pr` - **Run:** `engineer-codex-ward-704` · ward `v0.470.0` · dispatched `2026-07-09T00:06:54Z` - **Comment thread:** 1 included in the pre-flight read, 1 stripped (ward's own automated comments). - included: @coilyco-ops (2026-07-08T22:09:04Z) - stripped: @coilyco-ops (2026-07-08T22:04:54Z) Static container doctrine and seed boilerplate are identical every run and omitted here (they ride ward v0.470.0). </details>  — Codex, via `ward agent`

coilyco-ops commented

2026-07-09 00:12:52 +00:00

Author

Member

WARD-OUTCOME: blocked - review summary: blocked: codex: exit status 1

Review panel verdicts:

codex: ERROR: codex: exit status 1 (conf 0.00)
claude: ERROR: claude: exit status 1 (conf 0.00)
goose: ERROR: goose: exit status 1 (conf 0.00)

— Codex, via ward agent

WARD-OUTCOME: blocked - review summary: blocked: codex: exit status 1 Review panel verdicts: - codex: ERROR: codex: exit status 1 (conf 0.00) - claude: ERROR: claude: exit status 1 (conf 0.00) - goose: ERROR: goose: exit status 1 (conf 0.00)  — Codex, via `ward agent`

coilyco-ops commented

2026-07-09 00:13:36 +00:00

Author

Member

WARD-OUTCOME: blocked - review gate blocked before PR creation
review summary: blocked: codex: exit status 1
The review panel failed closed on reviewer auth, so I stopped before opening a PR. The namespace move itself is clean and the test gate passed, but the land step is blocked until the reviewer can run.

WARD-OUTCOME: blocked - review gate blocked before PR creation review summary: blocked: codex: exit status 1 The review panel failed closed on reviewer auth, so I stopped before opening a PR. The namespace move itself is clean and the test gate passed, but the land step is blocked until the reviewer can run.

coilyco-ops referenced this issue from a pull request that will close it,

2026-07-09 00:13:48 +00:00

ward salvage: ward-salvage/ward-14f676cf #717

coilyco-ops commented

2026-07-09 00:13:49 +00:00

Author

Member

⚠️ Reopened: this run's work did not land on `main`

An ephemeral ward container (codex mode) dispatched for this issue finished but its work was not merged to main, so the reaper preserved it on a branch before teardown and reopened the issue (a closing reference for #704 never reached main). Recover from the salvage branch below.

Repo: coilyco-flight-deck/ward
Salvage branch: ward-salvage/ward-14f676cf
Pull request: not opened - PR creation failed: forgejo: parse created pull request: unexpected end of JSON input
Reason: run workflow does not land on main (--workflow pr/patch-only)
Container uptime at reap: 6m (age of the baked Forgejo PAT snapshot; a long-lived container is likelier to carry a rotated token)

Reap diagnostics

--- reap diagnostics ---
ward version:      v0.470.0
version source:    pinned via WARD_VERSION/--ward-version (v0.470.0)
HEAD:              79f67cb7aebc
origin/main:       a2a544f1a892
ancestry:          HEAD is NOT yet on origin/main - residual work remains to land
decision gate:     workflow does not land on main (--workflow pr/patch-only)
reason:            run workflow does not land on main (--workflow pr/patch-only)
provenance:        not read (workflow hold)
run-owned landed:  no
working tree:      clean
container uptime:  6m (baked Forgejo PAT age proxy)
--- end reap diagnostics ---

Recover

git fetch https://forgejo.coilysiren.me/coilyco-flight-deck/ward.git ward-salvage/ward-14f676cf
git checkout -b ward-salvage/ward-14f676cf FETCH_HEAD

— Codex, via ward agent

## ⚠️ Reopened: this run's work did not land on `main` An ephemeral `ward container` (codex mode) dispatched for this issue finished but its work was **not merged to `main`**, so the reaper preserved it on a branch before teardown and reopened the issue (a closing reference for #704 never reached `main`). Recover from the salvage branch below. - **Repo:** `coilyco-flight-deck/ward` - **Salvage branch:** `ward-salvage/ward-14f676cf` - **Pull request:** not opened - PR creation failed: forgejo: parse created pull request: unexpected end of JSON input - **Reason:** run workflow does not land on main (--workflow pr/patch-only) - **Container uptime at reap:** 6m (age of the baked Forgejo PAT snapshot; a long-lived container is likelier to carry a rotated token) ## Reap diagnostics ``` --- reap diagnostics --- ward version: v0.470.0 version source: pinned via WARD_VERSION/--ward-version (v0.470.0) HEAD: 79f67cb7aebc origin/main: a2a544f1a892 ancestry: HEAD is NOT yet on origin/main - residual work remains to land decision gate: workflow does not land on main (--workflow pr/patch-only) reason: run workflow does not land on main (--workflow pr/patch-only) provenance: not read (workflow hold) run-owned landed: no working tree: clean container uptime: 6m (baked Forgejo PAT age proxy) --- end reap diagnostics --- ``` ## Recover ```bash git fetch https://forgejo.coilysiren.me/coilyco-flight-deck/ward.git ward-salvage/ward-14f676cf git checkout -b ward-salvage/ward-14f676cf FETCH_HEAD ```  — Codex, via `ward agent`

coilyco-ops added the

headless

P2

labels

2026-07-09 18:09:22 +00:00

coilyco-ops commented

2026-07-09 22:44:08 +00:00

Author

Member

WARD-RESERVATION: held 🔒

reservation details

Holder: container engineer-codex-ward-704 on host kais-macbook-pro-2.local.

Reserved by ward agent --harness codex (reserved 2026-07-09T22:44:06Z). Concurrent ward agent runs are blocked until it finishes or the reservation goes stale (1h TTL). --force overrides.

Do not comment on or edit this issue to steer the run while it is reserved. The engineer seeded the body once at launch and never re-reads it, so a comment or edit reaches only human readers, never the running engineer. A correction goes to a new issue, dispatched fresh. That is the only channel that reaches a run in flight. Where the forge supports it, ward locks this conversation to make that a road-block rather than a convention (ward#494).

run seed context — what this run is carrying (ward#609)

Resolved: coilyco-flight-deck/ward#704 · branch issue-704 · harness codex · workflow pull-requests-and-merge
Run: engineer-codex-ward-704 · ward v0.540.0 · dispatched 2026-07-09T22:44:06Z
Comment thread: 4 included in the pre-flight read, 2 stripped (ward's own automated comments).
- included: @coilyco-ops (2026-07-08T22:09:04Z), @coilyco-ops (2026-07-09T00:12:52Z), @coilyco-ops (2026-07-09T00:13:36Z), @coilyco-ops (2026-07-09T00:13:49Z)
- stripped: @coilyco-ops (2026-07-08T22:04:54Z), @coilyco-ops (2026-07-09T00:06:57Z)

Static container doctrine and seed boilerplate are identical every run and omitted here (they ride ward v0.540.0).

— Codex, via ward agent

WARD-RESERVATION: held 🔒 <details><summary>reservation details</summary> Holder: container `engineer-codex-ward-704` on host `kais-macbook-pro-2.local`. Reserved by `ward agent --harness codex` (reserved 2026-07-09T22:44:06Z). Concurrent `ward agent` runs are blocked until it finishes or the reservation goes stale (1h TTL). `--force` overrides. **Do not comment on or edit this issue to steer the run while it is reserved.** The engineer seeded the body once at launch and never re-reads it, so a comment or edit reaches only human readers, never the running engineer. A correction goes to a **new issue, dispatched fresh**. That is the only channel that reaches a run in flight. Where the forge supports it, ward locks this conversation to make that a road-block rather than a convention (ward#494). <details><summary>run seed context — what this run is carrying (ward#609)</summary> - **Resolved:** `coilyco-flight-deck/ward#704` · branch `issue-704` · harness `codex` · workflow `pull-requests-and-merge` - **Run:** `engineer-codex-ward-704` · ward `v0.540.0` · dispatched `2026-07-09T22:44:06Z` - **Comment thread:** 4 included in the pre-flight read, 2 stripped (ward's own automated comments). - included: @coilyco-ops (2026-07-08T22:09:04Z), @coilyco-ops (2026-07-09T00:12:52Z), @coilyco-ops (2026-07-09T00:13:36Z), @coilyco-ops (2026-07-09T00:13:49Z) - stripped: @coilyco-ops (2026-07-08T22:04:54Z), @coilyco-ops (2026-07-09T00:06:57Z) Static container doctrine and seed boilerplate are identical every run and omitted here (they ride ward v0.540.0). </details> </details>  — Codex, via `ward agent`

coilyco-ops referenced this issue from a pull request that will close it,

2026-07-09 22:47:35 +00:00

Move non-agent launch helpers out of internal/agents #877

coilyco-ops commented

2026-07-09 22:50:20 +00:00

Author

Member

WARD-OUTCOME: merge-ready

details

workflow: pull-requests-and-merge; review summary: review gate skipped by ~/.ward/config.yaml default

implementation felt mechanical. the move was already in place, so this run validated the branch, opened PR #877, and waited for CI.
confidence: high.
surprises: forgejo had no open PR for issue 704, and the mergeable flag lagged behind the green status.
follow-ups: merge PR #877 when the director loop is ready.

WARD-OUTCOME: merge-ready <details><summary>details</summary> workflow: pull-requests-and-merge; review summary: review gate skipped by ~/.ward/config.yaml default - implementation felt mechanical. the move was already in place, so this run validated the branch, opened PR #877, and waited for CI. - confidence: high. - surprises: forgejo had no open PR for issue 704, and the mergeable flag lagged behind the green status. - follow-ups: merge PR #877 when the director loop is ready. </details>

coilyco-ops referenced this issue

2026-07-10 00:49:21 +00:00

Repair ward PR merge queue from failed prior runs #903

coilyco-ops referenced this issue

2026-07-10 00:56:45 +00:00

Repair merge conflicts on PR #877 from its existing branch #912

coilyco-ops closed this issue

2026-07-10 06:26:08 +00:00