kyle/boxmaker
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
55 Commits 3 Branches 0 Tags
3d876d4fa90c66ceb65304342d105b4025cdaf77
Commit Graph
55 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
kyle 3d876d4fa9 Add the assembler that folds streamed chunks into a completion 
Implemented-By: GLM-5.3 (z.ai, default settings) via OpenCode
 2026-09-18 02:56:31 -07:00
kyle f48999306e Add the llama client types and the chat request builder 
Implemented-By: Laguna S 2.1 (OpenCode)
 2026-09-18 02:40:35 -07:00
kyle f58c29e707 Add a server-sent-events reader to loopd 
Implemented-By: Laguna S 2.1 (OpenCode)
 2026-09-18 02:31:49 -07:00
kyle 4460bb241a M2a/04-loopd-http 
Implemented-By: Laguna S 2.1 (OpenCode)
 2026-09-18 02:11:25 -07:00
kyle 6e8e24794d Add loopd configuration with every M2a limit 
Implemented-By: Laguna S 2.1 (OpenCode)
 2026-09-17 23:07:38 -07:00
kyle a0495ea36a Add the inferproxy byte forwarder with its two limits 
Implemented-By: Laguna S 2.1 (OpenCode)
 2026-09-17 21:03:41 -07:00
kyle bc1e727c19 Add SHA-256 to proto, wrapping the emsha crate 
Implemented-By: Laguna S 2.1 (OpenCode)
 2026-09-17 14:11:51 -07:00
kyleandClaude Fable 5.1 db0ba081db Add tools/run-plan.sh to run a plan's tasks in fresh OpenCode sessions 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 14:02:49 -07:00
kyleandClaude Fable 5.1 76ccc251cd Add M2a plan: thirteen tasks, tests, fake server and recordings 
The tasks build the inference path: emsha-backed SHA-256, inferproxy,
config, a hand-written HTTP and SSE client, request building, delta
assembly, the chat state machine, the thinking cap, the slot gate with
retry, the startup self-test and on-device verification.

Everything the tasks copy in was checked against a private reference
implementation: the gate passes after each task in order, the timing
tests pass repeatedly under CPU load, and the reference passes the
self-test and all four device checks on straylight. Expected results
for the recorded streams were derived by a separate script.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 13:34:11 -07:00
kyleandClaude Fable 5.1 a49db39b54 Brief: add a one-sentence purpose for every role and crate 
Requested by the owner so that future readers, agents included, learn
what each piece is for first. No behaviour changes.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 13:00:21 -07:00
kyleandClaude Fable 5.1 7bff156d7e Add M2a design spec: the inference path 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 12:54:47 -07:00
kyleandClaude Fable 5.1 62ec663a0e Record M2a limits, the accepted availability risk and three more measurements 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 12:53:41 -07:00
kyleandClaude Fable 5.1 eb1b7d2da2 Record emsha and the M2 split; add dependency-vetting lesson 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 12:27:52 -07:00
kyleandClaude Fable 5.1 362f962803 Measure queued-request behaviour and reasoning_control before the M2 design 
A request pinned to a busy slot receives no bytes until the slot frees.
reasoning_control ends a thinking block on demand; the capped turn is
re-read once on the next request.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 11:03:55 -07:00
kyleandClaude Fable 5.1 35a7a4e7ea Record why task 01 had an earlier attempt 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 11:02:00 -07:00
kyleandClaude Fable 5.1 2426b45852 Rewrap a long line in CLAUDE.md 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 10:19:50 -07:00
kyleandClaude Fable 5.1 57bfc62236 Accept M1 follow-ups; add implementer lessons and promote four rules to AGENTS.md 
Tasks 08 and 09 pass the checklist and the reviewer's probes, so M1 is
complete. docs/implementer-lessons.md turns the review findings into
tips for the implementer and for task writing, each tied to its
evidence, with a column to record whether the defect comes back.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 10:19:06 -07:00
kyle 46d26e868b Make gate scripts handle table-form dependencies and fail closed 
Implemented-By: Laguna S 2.1 (OpenCode)
 2026-09-17 10:14:22 -07:00
kyle 69120af092 Reject unknown fields in every proto struct and bound Timestamp 
Implemented-By: Laguna S 2.1 (OpenCode)
 2026-09-17 09:29:48 -07:00
kyleandClaude Fable 5.1 dcdcf65d83 Review M1: accept with two follow-up tasks 
The branch passes the checklist: seven commits, copied files unchanged,
gate and audit green. Reading and probing found that AuditRecord and
ToolCall accept unknown fields, that large Timestamps panic when
formatted, and that the dependency-direction scripts miss table-form
dependencies and pass when their inputs are missing. The last two
families were gaps in the tasks, not only in the code.

Tasks 08 and 09 carry the fixes, defined by an exhaustive unknown-field
test, a bounded-Timestamp test and an extended gate-script self-test.
All three were checked against the reference implementation and fail on
the current branch.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 09:14:29 -07:00
kyle 8c1852ec47 Add Decision, decide and the runner stub to brokerd 
Implemented-By: Laguna S 2.1 (OpenCode)
 2026-09-17 09:05:48 -07:00
kyle b9f3ab45c1 Add audit and session log record types to proto 
Implemented-By: Laguna S 2.1 (OpenCode)
 2026-09-17 08:36:44 -07:00
kyle 78e13195ea Add Grant, Mode and Constraints to proto 
Implemented-By: Laguna S 2.1 (OpenCode)
 2026-09-17 08:23:48 -07:00
kyle d6308c976b Add length-prefixed frame codec to proto 
Implemented-By: Laguna S 2.1 (OpenCode)
 2026-09-17 08:11:14 -07:00
kyle 56e12f40a6 Add IPC envelope and tool messages to proto 
Implemented-By: Laguna S 2.1 (OpenCode)
 2026-09-17 07:53:40 -07:00
kyle 1e1b543a7c Add validated identifiers, Hash32, Timestamp and DataClass to proto 
Implemented-By: Laguna S 2.1 (OpenCode)
 2026-09-17 07:41:49 -07:00
kyle 8dc04b1d48 Add Cargo workspace, crate skeletons and the gate 
Implemented-By: Laguna S 2.1 (OpenCode)
 2026-09-17 06:45:02 -07:00
kyleandClaude Fable 5.1 3e26c2e3c0 Add M1 plan, given tests and fixtures, AGENTS.md and implementer log 
Seven task files for the implementing model under docs/plans/M1/, with
the test files, byte-exact fixtures, Makefile, deny.toml and gate-script
self-test they copy into place. All of it was verified against a private
reference implementation: the gate passes after every task in order.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 01:22:43 -07:00
kyleandClaude Fable 5.1 19104a9629 Mark per-milestone review as an M1 experiment 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 01:09:08 -07:00
kyleandClaude Fable 5.1 bafe3f9fff Rewrap a long line in the pre-M1 spec 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 01:08:36 -07:00
kyleandClaude Fable 5.1 afdac9ad3e Add pre-M1 design spec 
Threat model, data classes and provenance, approvals, IPC framing and
socket topology, the proto type list, log file rules, runtime layout,
the M1 gate, and how work is handed to the implementing model.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 01:08:27 -07:00
kyleandClaude Fable 5.1 2a1fe5576c Record pre-M1 design decisions 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 00:58:49 -07:00
kyleandClaude Fable 5.1 34b2b47656 Note expected extra compute against the M5b open decision 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 00:41:43 -07:00
kyleandClaude Fable 5.1 5555d6a7d1 Rewrap CLAUDE.md line 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 00:39:01 -07:00
kyleandClaude Fable 5.1 fbc0f218dc Sync CLAUDE.md and decisions log with the amended brief 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 00:38:54 -07:00
kyleandClaude Fable 5.1 0612d80aa2 Brief P12: inferproxy is required 
Approved 2026-09-17. Evidence is in docs/decisions.md.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 00:38:32 -07:00
kyleandClaude Fable 5.1 a4ebdc11af Brief P11: serving settings are recorded here and owned by the NixOS config 
Approved 2026-09-17. Evidence is in docs/decisions.md.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 00:38:32 -07:00
kyleandClaude Fable 5.1 adab43add1 Brief P10: separate limit for waiting on a slot or a model load 
Approved 2026-09-17. Evidence is in docs/decisions.md.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 00:38:32 -07:00
kyleandClaude Fable 5.1 27b7ff45ee Brief P9: slots are pinned but not reserved; cache loss is a normal event 
Approved 2026-09-17. Evidence is in docs/decisions.md.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 00:38:32 -07:00
kyleandClaude Fable 5.1 e07fddf0ad Brief P8: describe the shared router as deployed 
Approved 2026-09-17. Evidence is in docs/decisions.md.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 00:38:32 -07:00
kyleandClaude Fable 5.1 46918e5208 Brief P7: split the gate into offline and on-device parts 
Approved 2026-09-17. Evidence is in docs/decisions.md.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 00:38:32 -07:00
kyleandClaude Fable 5.1 4fc7ad3deb Brief P6: define Decision in brokerd, DecisionRecord in proto 
Approved 2026-09-17. Evidence is in docs/decisions.md.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 00:38:32 -07:00
kyleandClaude Fable 5.1 e353cd57fa Brief P5: settle on chat-completions with server-side tool parsing 
Approved 2026-09-17. Evidence is in docs/decisions.md.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 00:38:32 -07:00
kyleandClaude Fable 5.1 367573b11e Brief P4: enforce the thinking cap through reasoning_control 
Approved 2026-09-17. Evidence is in docs/decisions.md.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 00:38:32 -07:00
kyleandClaude Fable 5.1 59666e0130 Brief P3: request prompt-processing progress so prefill counts as liveness 
Approved 2026-09-17. Evidence is in docs/decisions.md.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 00:38:32 -07:00
kyleandClaude Fable 5.1 8421d80e87 Brief P2: log and replay assistant messages exactly, drop the thinking-block risk 
Approved 2026-09-17. Evidence is in docs/decisions.md.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 00:38:32 -07:00
kyleandClaude Fable 5.1 790136e94f Brief P1: fix the tools array per epoch, reach other tools through call_tool 
Approved 2026-09-17. Evidence is in docs/decisions.md.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 00:38:32 -07:00
kyleandClaude Fable 5.1 065fe8ce1d Add slot pinning and eviction measurements to M0 findings 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 00:35:36 -07:00
kyleandClaude Fable 5.1 4b6ea143c7 Replace dedicated-instance recommendation with shared-router consequences 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 00:30:50 -07:00
kyleandClaude Fable 5.1 e104b77289 Add idle-GPU throughput numbers to M0 findings 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-17 00:30:38 -07:00