Make HistoryEncoder a pluggable registry, like Router/Objective (gitea #35) #52

Merged

lars merged 1 commits from fix/issue-35 into master 2026-08-14 10:43:07 +02:00

Conversation 0 Commits 1 Files Changed 5

+133 -34

lars commented 2026-08-14 10:36:41 +02:00

Owner

Copy Link

Copy Source

Stage2Autoregressive.init_history_cache and .history_step both
isinstance-checked self.history_encoder against AttentionHistory to decide
whether to use its real incremental-cache methods or a no-op fallback, so a
third history type couldn't be added without editing Stage2Autoregressive
itself. The two-value "markov"/"attention" enum was also independently
hardcoded in three places (Stage2Autoregressive's own validation,
config.py's validate_config, and AutoregressiveConfig.from_dict's default).

Mirrors the Router (giant/model/routers.py) and Objective
(giant/model/objectives.py, gitea #32) pattern: HistoryEncoder now declares
working O(1) init_cache/step defaults (init_cache -> None, step -> one
forward() call), so every registered history type satisfies the incremental
interface without opting in; AttentionHistory overrides both with its real
KV-cache versions since its forward() needs the full prefix. Added
HISTORY_REGISTRY/register_history/build_history, registered "markov" and
"attention", and deleted both isinstance checks in models.py.

Per user decision during planning, config.py's validate_config now imports
HISTORY_REGISTRY and checks membership dynamically instead of keeping its own
hardcoded tuple, making the registry the single source of truth end to end
(verified no import cycle: config.py had no prior dependency on giant.model,
and giant.model.history has none on giant.config).

No config-schema change and no checkpoint impact — this is a pure
internal-interface refactor.

Co-Authored-By: Claude Opus 5 noreply@anthropic.com

Stage2Autoregressive.init_history_cache and .history_step both isinstance-checked self.history_encoder against AttentionHistory to decide whether to use its real incremental-cache methods or a no-op fallback, so a third history type couldn't be added without editing Stage2Autoregressive itself. The two-value "markov"/"attention" enum was also independently hardcoded in three places (Stage2Autoregressive's own validation, config.py's validate_config, and AutoregressiveConfig.from_dict's default). Mirrors the Router (giant/model/routers.py) and Objective (giant/model/objectives.py, gitea #32) pattern: HistoryEncoder now declares working O(1) init_cache/step defaults (init_cache -> None, step -> one forward() call), so every registered history type satisfies the incremental interface without opting in; AttentionHistory overrides both with its real KV-cache versions since its forward() needs the full prefix. Added HISTORY_REGISTRY/register_history/build_history, registered "markov" and "attention", and deleted both isinstance checks in models.py. Per user decision during planning, config.py's validate_config now imports HISTORY_REGISTRY and checks membership dynamically instead of keeping its own hardcoded tuple, making the registry the single source of truth end to end (verified no import cycle: config.py had no prior dependency on giant.model, and giant.model.history has none on giant.config). No config-schema change and no checkpoint impact — this is a pure internal-interface refactor. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

lars added 1 commit 2026-08-14 10:36:41 +02:00

Make HistoryEncoder a pluggable registry, like Router/Objective (gitea #35) ... f301fd98d2

Stage2Autoregressive.init_history_cache and .history_step both
isinstance-checked self.history_encoder against AttentionHistory to decide
whether to use its real incremental-cache methods or a no-op fallback, so a
third history type couldn't be added without editing Stage2Autoregressive
itself. The two-value "markov"/"attention" enum was also independently
hardcoded in three places (Stage2Autoregressive's own validation,
config.py's validate_config, and AutoregressiveConfig.from_dict's default).

Mirrors the Router (giant/model/routers.py) and Objective
(giant/model/objectives.py, gitea #32) pattern: HistoryEncoder now declares
working O(1) init_cache/step defaults (init_cache -> None, step -> one
forward() call), so every registered history type satisfies the incremental
interface without opting in; AttentionHistory overrides both with its real
KV-cache versions since its forward() needs the full prefix. Added
HISTORY_REGISTRY/register_history/build_history, registered "markov" and
"attention", and deleted both isinstance checks in models.py.

Per user decision during planning, config.py's validate_config now imports
HISTORY_REGISTRY and checks membership dynamically instead of keeping its own
hardcoded tuple, making the registry the single source of truth end to end
(verified no import cycle: config.py had no prior dependency on giant.model,
and giant.model.history has none on giant.config).

No config-schema change and no checkpoint impact — this is a pure
internal-interface refactor.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

lars merged commit c00ee91a74 into master 2026-08-14 10:43:07 +02:00

lars deleted branch fix/issue-35 2026-08-14 10:43:08 +02:00

Sign in to join this conversation.

Reviewers

No Reviewers

Labels

Clear labels

architecture

bug

Silent/wrong behavior, no crash

experiment

feature

New feature matching the v0.3 redesign

investigation

modularity

Making the network genuinely pluggable

performance

phase2

validation

wontfix

Not being fixed right now

No Label

Milestone

No items

No Milestone

Projects

Clear projects

No project

Assignees

Clear assignees

lars (Lars Bogner)

No Assignees

1 Participants

Notifications

Subscribe

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: lars/giant#52