These files carried no type field at all. Selection is by 'type: workplan', so
they were invisible to every projection while the hub held a record for each —
and a forge-derived reset read those correct records as no longer deriving and
queued them for retirement.
Only the type line is added.
Refs STATE-WP-0083-T05
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 2583210@bnt-lap001
Assistant-Session: f2bff2d5-e9b2-4338-92ca-10282a927006
Identifiers predating the PREFIX-WP-NNNN convention were rejected by the canon
registry, so none of this repository's work records could be registered.
One prefix per repository (ADR-007). Existing conforming identifiers keep their
numbers where possible; the pre-convention records take the next free numbers
rather than renumbering work that was already correct.
Projection UUIDs are re-derived from the new canonical ids (ADR-007 decision 2).
Nothing was registered on central under the old identifiers, so no hub record is
orphaned by this.
Refs CUST-WP-0068-T03
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 2583210@bnt-lap001
Assistant-Session: f2bff2d5-e9b2-4338-92ca-10282a927006
Records absent from central carried random pre-ADR-007 identifiers minted by
the retired local hub, which C-06 refused as stale references. Deriving from
the canonical record id takes no identity from anything.
Refs CUST-WP-0068-T06
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 2583210@bnt-lap001
Assistant-Session: f2bff2d5-e9b2-4338-92ca-10282a927006
ops-mason built the real AppRole/policy/KV path infrastructure, the
founder completed provisioning, and a real task ran through
rein-openweights with OPENROUTER_API_KEY explicitly unset -- real
AppRole login, real KV v2 read, real OpenRouter call, real commit. Full
build record (including two real bugs found and fixed along the way)
in ops-mason/plans/rein-openweights-openrouter-approle.md.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
channels/base.py: GatewayInvocation dataclass + Channel ABC
(parse_invocation/render_result), mirroring Rein one layer up -- a
channel turns an external invocation into what run_task_through_rein
needs, and turns its result back into whatever the invocation medium
expects.
channels/cli_channel.py: CLIChannel, a pure refactor of what cli.py did
inline -- argparse Namespace -> GatewayInvocation, result dict ->
json.dumps(..., indent=2). cli.py's run handler is now a thin
construct-parse-invoke-render wrapper.
docs/channel-contract.md documents the pattern and sketches (without
building) a second channel.
Found and fixed a real bug while live-testing this refactor:
ReinAharness's default cli_bin was still "agent-harness", stale from
before HARNESS-WP-0002-T02's rename.
4 new tests (27/27 passing), plus a real live run through
python3 -m glas_harness.cli against rein-aharness/real Claude Code
confirming identical output shape and a real commit.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
GLAS-WP-0002 is now fully done (4/4): formalize the CLI as the first
Channel extension (contract + refactor + tests + second-channel
documentation), not building a second channel yet -- same
generalize-from-a-real-second-example discipline as ADR-002/ADR-004.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Checked ADR-002 part 2's deferred question against the two observability
additions that landed since (rein-aharness's tool-event stream,
glas-harness's own gateway hub event) -- both turned out simpler as
direct implementations, neither needed a wrapping middleware layer.
Still zero real candidates for that shape. docs/harness-contract.md
gains the Middleware ABC as a documented, unimplemented sketch for if a
real third case ever appears -- no code written now.
Also flagged GLAS-WP-0002-T02 (live OpenBao verification) as blocked:
`bao token lookup` from this workstation returns 403, no usable vault
session to provision a new AppRole with. Needs the operator.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
hub.py mirrors the two reins' hub.py under author: agt-glas-harness.
run_task_through_rein gains report_to_hub (default True), posting one
gateway_run progress event from a finally block -- fires on both
success and failure, giving the gateway an audit trail independent of
whatever the rein itself reports. cli.py gained a matching --no-hub
flag.
Live-verified: ran a real task through ReinOpenWeights with hub
reporting enabled, confirmed the gateway_run event landed with correct
detail and a real commit sha. 4 new tests, 23/23 passing.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Bundles the four items surfaced while closing out GLAS-WP-0001/
HARNESS-WP-0002/SAND-WP-0013/REIN-OW-WP-0001: composable-reins-as-
middleware design (ADR-002 part 2), live-verifying rein-openweights'
OpenBao path, wiring the gateway's own State Hub reporting, and scoping
a first slice of glas-harness's remaining charter pillars. None were
blocking; all are worth doing.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Refined the auto-generated SCOPE.md/AGENTS.md from generic templates
to real repo specifics, added a Developer Workflow section with
actual install/test/run commands. Real workplan (GLAS-WP-0001) was
already seeded and done.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Ran run_task_through_rein for real (user's explicit go-ahead) with
rein=ReinAharness(): real ext.bwrap sandbox, real kaizen-agentic schedule
prepare persona load, real claude --print --permission-mode acceptEdits
session under green-commit-only, real commit (8b63424a) in 11.4s,
verified via git rev-parse HEAD, sandbox torn down, executor-sandbox
untouched. Both reins now have a live end-to-end proof through the same
gateway code -- the parity proof this task and HARNESS-WP-0002 were
gated on. GLAS-WP-0001 is now fully done (6/6).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Ran run_task_through_rein for real (user's explicit go-ahead): profile.bwrap-local
sandbox, ReinOpenWeights against qwen/qwen-2.5-72b-instruct on the real
OpenRouter API. 2-turn tool-calling loop produced a real commit
(2effe57a), verified via git rev-parse HEAD, sandbox torn down,
executor-sandbox itself untouched. Proves the glas-harness -> sand-boxer
-> rein -> verified-commit path end-to-end for one rein; the same proof
against rein-aharness/Claude Code CLI specifically remains open (T04).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
glas_harness/reins/rein_openweights.py implements the Rein ABC by
shelling out to `rein-openweights run --task-file ... --no-hub
[--model ...]`, mirroring reins/rein_aharness.py exactly. Factored the
duplicated git_head/write_task_file logic into reins/_shared.py, used
by both adapters now. registry/reins/rein-openweights.yaml flipped to
status: implemented. 8 new tests (mocked subprocess), 18/18 passing.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
REIN-OW-WP-0001 T01-T04 landed in the rein-openweights repo. The
glas_harness/reins/rein_openweights.py adapter (mirroring
reins/rein_aharness.py) that actually plugs it into the gateway is the
remaining piece.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
rein-openweights acquires its OpenRouter credential directly
(OpenBao/ops-warden), consistent with rein-aharness's existing
credential-holder principle — glas-harness does not broker
LLM-provider credentials. Confirmed llm-connect itself never brokers
credentials either (resolve_api_key() only reads an
already-materialized key from explicit/env/file), so routing through
llm-connect vs. a leaner wrapper doesn't change this. Composable reins
as middleware (monitoring/eval/optimization) is recorded as a separate,
deliberately deferred question in the same ADR — one candidate
capability isn't evidence of a recurring pattern yet.
GLAS-WP-0001-T06 done; T05 (bootstrap rein-openweights) unblocked.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
- src/glas_harness/contract.py: Rein ABC (start_session/dispatch_tool/
end_session), SandboxHandle/ToolCall/ToolResult, per docs/harness-contract.md.
- reins/rein_aharness.py: adapter around the rein-aharness CLI. Collapses
a whole `agent-harness run` into one dispatch_tool call for now (no
per-tool hooks yet — tracked in rein-aharness HARNESS-WP-0002-T03);
verifies success via new-commit detection, mirroring rein-aharness's
own success signal.
- gateway.py + cli.py: resolves a sand-boxer sandbox, runs one task
through a rein, tears the sandbox down.
- registry/reins/*.yaml (rein-aharness implemented, rein-openweights
planned) and profiles/harness.agent-dev{,-local}.yaml, pairing with
sand-boxer's profile.agent-dev and the new profile.bwrap-local.
Tested against a real local git repo + mocked SandboxManager/CLI
subprocess (10 tests, all passing). A real live run against the actual
Claude Code CLI is deliberately left for a human-triggered follow-up —
not executed autonomously since it spends real API credits/credentials.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
start_session/dispatch_tool/end_session, mirroring sand-boxer's
SandboxExtension ABC one layer up: sand-boxer establishes where work
runs, this contract governs how an agent session runs on top of it.
Unblocks the rein-aharness parity proof (T04) and rein-openweights
bootstrap (T05).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Establishes glas-harness as the framework routing between concrete
harness backends ("reins"): rein-aharness (renamed from agent-harness)
and the newly chartered rein-openweights. GLAS-WP-0001 defines the
harness contract, rein registry, and a minimal gateway proving parity
against rein-aharness.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
